Compare commits

..
Author SHA1 Message Date
jarvis-at-skic e22d3a5c13 docs: separate workflow effectiveness from skill health
Build and publish Eldorado documentation / build (pull_request) Successful in 52s
2026-10-08 11:05:00 +00:00
jarvis-at-skic 386133c8b6 Merge pull request 'docs: separate Measurement registry and workflow Baseline' (#35) from feat/measurement-baseline-separation into main
Build and publish Eldorado documentation / build (push) Successful in 44s
2026-10-07 06:47:31 -07:00
jarvis-at-skic abe00994a1 docs: [verified] separate Measurement registry and workflow Baseline
Build and publish Eldorado documentation / build (pull_request) Successful in 46s
2026-10-07 13:33:07 +00:00
jarvis-at-skic c4b4c38e62 Merge pull request 'docs: separate metric pages under Measurement' (#34) from feat/measurement-metric-pages into main
Build and publish Eldorado documentation / build (push) Successful in 41s
2026-10-06 16:26:44 -07:00
31 changed files with 688 additions and 720 deletions

No files matched your search

@@ -19,7 +19,7 @@
"type": "external",
"label": "Delivery first",
"tag": "Start with a real workflow",
"sublabel": "Baseline + bounded canary",
"sublabel": "Workflow baseline + canary",
"pos": [
60,
120
@@ -67,7 +67,7 @@
"type": "external",
"label": "Learn from real work",
"tag": "Ongoing, reviewed improvement",
"sublabel": "Feedback + friction + measures\nRetain a manual path\nNo quotas or rankings",
"sublabel": "Feedback + selected measures\nRetain a manual path\nNo quotas or rankings",
"pos": [
60,
490
+2 -2
View File
@@ -19,7 +19,7 @@
"type": "external",
"label": "Delivery first",
"tag": "Start with a real workflow",
"sublabel": "Baseline + bounded canary",
"sublabel": "Workflow baseline + canary",
"pos": [
60,
350
@@ -67,7 +67,7 @@
"type": "external",
"label": "Learn from real work",
"tag": "Ongoing, reviewed improvement",
"sublabel": "Feedback + friction + measures\nRetain a manual path\nNo quotas or rankings",
"sublabel": "Feedback + selected measures\nRetain a manual path\nNo quotas or rankings",
"pos": [
700,
800
@@ -0,0 +1,144 @@
{
"schema_version": 1,
"diagram_type": "architecture",
"meta": {
"title": "Workflow baseline",
"output": "static/diagrams/strategy-baseline-mobile/index.html",
"quality_profile": "showcase",
"legend": {
"mode": "hidden"
},
"viewBox": [
880,
2050
]
},
"components": [
{
"id": "workflow",
"type": "external",
"label": "Current workflow",
"tag": "01 / Understand",
"sublabel": "Task, scope, people\nTools + handoffs\nCurrent practice",
"pos": [
90,
50
],
"size": [
700,
350
],
"icon": "none"
},
{
"id": "selection",
"type": "frontend",
"label": "Relevant selection",
"tag": "02 / Choose",
"sublabel": "Registry candidates\nReasons for inclusion\nDefer what does not fit",
"pos": [
90,
450
],
"size": [
700,
350
],
"icon": "none"
},
{
"id": "evidence",
"type": "frontend",
"label": "Feasible evidence",
"tag": "03 / Agree",
"sublabel": "Sources + period\nPrivacy, access, owner\nTest joins + coverage",
"pos": [
90,
850
],
"size": [
700,
350
],
"icon": "none"
},
{
"id": "position",
"type": "backend",
"label": "Starting position",
"tag": "04 / Record",
"sublabel": "Actual values + limits\nOr unavailable gaps\nNo invented baseline",
"pos": [
90,
1250
],
"size": [
700,
350
],
"icon": "none"
},
{
"id": "comparison",
"type": "backend",
"label": "Later comparison",
"tag": "05 / Evaluate",
"sublabel": "Comparable rules\nContext + uncertainty\nNot causal ROI",
"pos": [
90,
1650
],
"size": [
700,
350
],
"icon": "none"
}
],
"connections": [
{
"id": "workflow-selection",
"from": "workflow",
"to": "selection",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default"
},
{
"id": "selection-evidence",
"from": "selection",
"to": "evidence",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default"
},
{
"id": "evidence-position",
"from": "evidence",
"to": "position",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default"
},
{
"id": "position-comparison",
"from": "position",
"to": "comparison",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default"
}
]
}
@@ -0,0 +1,184 @@
{
"schema_version": 1,
"diagram_type": "architecture",
"meta": {
"title": "Workflow baseline",
"output": "static/diagrams/strategy-baseline/index.html",
"quality_profile": "showcase",
"legend": {
"mode": "hidden"
},
"viewBox": [
2400,
1120
]
},
"components": [
{
"id": "workflow",
"type": "external",
"label": "Current workflow",
"tag": "01 / Understand",
"sublabel": "Task, scope, people\nTools + handoffs\nCurrent practice",
"pos": [
40,
55
],
"size": [
440,
290
],
"icon": "none"
},
{
"id": "selection",
"type": "frontend",
"label": "Relevant selection",
"tag": "02 / Choose",
"sublabel": "Registry candidates\nReasons for inclusion\nDefer what does not fit",
"pos": [
510,
235
],
"size": [
440,
290
],
"icon": "none"
},
{
"id": "evidence",
"type": "frontend",
"label": "Feasible evidence",
"tag": "03 / Agree",
"sublabel": "Sources + period\nPrivacy, access, owner\nTest joins + coverage",
"pos": [
980,
415
],
"size": [
440,
290
],
"icon": "none"
},
{
"id": "position",
"type": "backend",
"label": "Starting position",
"tag": "04 / Record",
"sublabel": "Actual values + limits\nOr unavailable gaps\nNo invented baseline",
"pos": [
1450,
595
],
"size": [
440,
290
],
"icon": "none"
},
{
"id": "comparison",
"type": "backend",
"label": "Later comparison",
"tag": "05 / Evaluate",
"sublabel": "Comparable rules\nContext + uncertainty\nNot causal ROI",
"pos": [
1920,
775
],
"size": [
440,
290
],
"icon": "none"
}
],
"connections": [
{
"id": "workflow-selection",
"from": "workflow",
"to": "selection",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
495.0,
200.0
],
[
495.0,
380.0
]
]
},
{
"id": "selection-evidence",
"from": "selection",
"to": "evidence",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
965.0,
380.0
],
[
965.0,
560.0
]
]
},
{
"id": "evidence-position",
"from": "evidence",
"to": "position",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
1435.0,
560.0
],
[
1435.0,
740.0
]
]
},
{
"id": "position-comparison",
"from": "position",
"to": "comparison",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
1905.0,
740.0
],
[
1905.0,
920.0
]
]
}
]
}
@@ -19,7 +19,7 @@
"type": "external",
"label": "Observe use",
"tag": "Owner + Data & AI",
"sublabel": "Feedback, drift + review due",
"sublabel": "Selected evidence + drift",
"pos": [
60,
120
@@ -19,7 +19,7 @@
"type": "external",
"label": "Observe use",
"tag": "Owner + Data & AI",
"sublabel": "Feedback, drift + review due",
"sublabel": "Selected evidence + drift",
"pos": [
670,
60
@@ -1,314 +1,20 @@
{
"schema_version": 1,
"diagram_type": "architecture",
"meta": {
"title": "TO-BE: Measurement",
"output": "static/diagrams/strategy-measurement-mobile/index.html",
"quality_profile": "showcase",
"legend": {
"mode": "hidden"
},
"viewBox": [
880,
3630
]
},
"meta": {"title": "Two connected measurement tracks", "output": "static/diagrams/strategy-measurement-mobile/index.html", "quality_profile": "showcase", "legend": {"mode": "hidden"}, "viewBox": [880, 2450]},
"components": [
{
"id": "success-source",
"type": "external",
"label": "Tracker + acceptance",
"tag": "Matured task starts",
"sublabel": "Join evidence to the workflow",
"pos": [
60,
120
],
"size": [
740,
220
],
"icon": "none"
},
{
"id": "success",
"type": "frontend",
"label": "Accepted / eligible starts \u00d7 100",
"tag": "Task success (%)",
"sublabel": "Failures + unresolved retained",
"pos": [
60,
490
],
"size": [
740,
220
],
"icon": "none"
},
{
"id": "quality-source",
"type": "external",
"label": "Changes + defects",
"tag": "Completed follow-up",
"sublabel": "Join evidence to the workflow",
"pos": [
60,
860
],
"size": [
740,
220
],
"icon": "none"
},
{
"id": "quality",
"type": "frontend",
"label": "Affected / accepted changes \u00d7 100",
"tag": "Escaped quality (%)",
"sublabel": "Count each affected change once",
"pos": [
60,
1230
],
"size": [
740,
220
],
"icon": "none"
},
{
"id": "cost-source",
"type": "external",
"label": "Invoices + review minutes",
"tag": "Include failed attempts",
"sublabel": "Join evidence to the workflow",
"pos": [
60,
1600
],
"size": [
740,
220
],
"icon": "none"
},
{
"id": "cost",
"type": "frontend",
"label": "Allocated cost / accepted tasks",
"tag": "Cost per accepted outcome",
"sublabel": "Missing buckets = partial",
"pos": [
60,
1970
],
"size": [
740,
220
],
"icon": "none"
},
{
"id": "confidence-source",
"type": "external",
"label": "Anonymous 1\u20135 survey",
"tag": "Protect small groups",
"sublabel": "Join evidence to the workflow",
"pos": [
60,
2340
],
"size": [
740,
220
],
"icon": "none"
},
{
"id": "confidence",
"type": "frontend",
"label": "Confidence sum / valid responses",
"tag": "Verification confidence (1\u20135)",
"sublabel": "Show distribution + response rate",
"pos": [
60,
2710
],
"size": [
740,
220
],
"icon": "none"
},
{
"id": "interpret",
"type": "backend",
"label": "Compare with baseline",
"tag": "Interpret, then act",
"sublabel": "Like workflows + source coverage\nZero denominator = N/A\nTrends are not causal ROI\nFix gaps; improve the workflow",
"pos": [
60,
3080
],
"size": [
740,
400
],
"icon": "none"
}
{"id": "workflow", "type": "backend", "label": "Workflow effectiveness", "tag": "01 / Baseline current work", "sublabel": "Accepted work, time, failures\nCost, effort + experience\nSelect relevant contracts only\nSkills need not exist yet", "pos": [90, 50], "size": [700, 350], "icon": "none"},
{"id": "compare", "type": "backend", "label": "Compare the same outcomes", "tag": "02 / After introducing skills", "sublabel": "Same workflow + acceptance\nSame follow-up + source coverage\nKeep gaps and task mix visible\nBefore / after is not causality", "pos": [90, 450], "size": [700, 350], "icon": "none"},
{"id": "interpret", "type": "external", "label": "Is work getting better?", "tag": "03 / Interpret workflow evidence", "sublabel": "Balance value, quality and risk\nMore adoption is not better work\nKeep live outcomes separate\nfrom skill evaluation cases", "pos": [90, 850], "size": [700, 350], "icon": "none"},
{"id": "skills", "type": "frontend", "label": "Skills effectiveness & health", "tag": "01 / Qualify named skill versions", "sublabel": "Selection precision + recall\nSeparate evaluation evidence\nNo applicable skills: N/A\nNot a zero workflow baseline", "pos": [90, 1250], "size": [700, 350], "icon": "none"},
{"id": "observe", "type": "frontend", "label": "Observe use + upkeep", "tag": "02 / Adoption and maintenance", "sublabel": "Supported bundle coverage\nApproved-workflow adoption\nSubstantive review evidence\nMissing observations: unknown", "pos": [90, 1650], "size": [700, 350], "icon": "none"},
{"id": "improve", "type": "external", "label": "Improve, retain or retire", "tag": "03 / Use both tracks together", "sublabel": "16 optional candidate contracts\n9 prototype / 7 unimplemented\nNo mandatory collection\nNo installed telemetry claimed", "pos": [90, 2050], "size": [700, 350], "icon": "none"}
],
"connections": [
{
"id": "success-source-success",
"from": "success-source",
"to": "success",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default",
"labelAt": [
610,
395
]
},
{
"id": "quality-source-quality",
"from": "quality-source",
"to": "quality",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default",
"labelAt": [
610,
1135
]
},
{
"id": "cost-source-cost",
"from": "cost-source",
"to": "cost",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default",
"labelAt": [
610,
1875
]
},
{
"id": "confidence-source-confidence",
"from": "confidence-source",
"to": "confidence",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default",
"labelAt": [
610,
2615
]
},
{
"id": "success-interpret",
"from": "success",
"to": "interpret",
"label": "",
"fromSide": "right",
"toSide": "right",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
850,
600.0
],
[
850,
3280.0
]
],
"labelAt": [
620,
3040
]
},
{
"id": "quality-interpret",
"from": "quality",
"to": "interpret",
"label": "",
"fromSide": "right",
"toSide": "right",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
850,
1340.0
],
[
850,
3280.0
]
],
"labelAt": [
620,
3040
]
},
{
"id": "cost-interpret",
"from": "cost",
"to": "interpret",
"label": "",
"fromSide": "right",
"toSide": "right",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
850,
2080.0
],
[
850,
3280.0
]
],
"labelAt": [
620,
3040
]
},
{
"id": "confidence-interpret",
"from": "confidence",
"to": "interpret",
"label": "",
"fromSide": "bottom",
"toSide": "top",
"route": "straight",
"width": 4,
"variant": "default",
"labelAt": [
610,
2985
]
}
{"id": "workflow-compare", "from": "workflow", "to": "compare", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"},
{"id": "compare-interpret", "from": "compare", "to": "interpret", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"},
{"id": "skills-observe", "from": "skills", "to": "observe", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"},
{"id": "observe-improve", "from": "observe", "to": "improve", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"},
{"id": "interpret-improve", "from": "interpret", "to": "improve", "label": "", "fromSide": "right", "toSide": "right", "route": "straight", "width": 4, "variant": "default", "via": [[835, 1025], [835, 2225]]}
]
}
}
+13 -285
View File
@@ -1,292 +1,20 @@
{
"schema_version": 1,
"diagram_type": "architecture",
"meta": {
"title": "TO-BE: Measurement",
"output": "static/diagrams/strategy-measurement/index.html",
"quality_profile": "showcase",
"legend": {
"mode": "hidden"
},
"viewBox": [
2400,
1120
]
},
"meta": {"title": "Two connected measurement tracks", "output": "static/diagrams/strategy-measurement/index.html", "quality_profile": "showcase", "legend": {"mode": "hidden"}, "viewBox": [2400, 960]},
"components": [
{
"id": "success-source",
"type": "external",
"label": "Tracker + acceptance",
"tag": "Matured task starts",
"sublabel": "Join evidence to the workflow",
"pos": [
50,
70
],
"size": [
580,
180
],
"icon": "none"
},
{
"id": "success",
"type": "frontend",
"label": "Accepted / eligible starts \u00d7 100",
"tag": "Task success (%)",
"sublabel": "Failures + unresolved retained",
"pos": [
770,
70
],
"size": [
700,
180
],
"icon": "none"
},
{
"id": "quality-source",
"type": "external",
"label": "Changes + defects",
"tag": "Completed follow-up",
"sublabel": "Join evidence to the workflow",
"pos": [
50,
320
],
"size": [
580,
180
],
"icon": "none"
},
{
"id": "quality",
"type": "frontend",
"label": "Affected / accepted changes \u00d7 100",
"tag": "Escaped quality (%)",
"sublabel": "Count each affected change once",
"pos": [
770,
320
],
"size": [
700,
180
],
"icon": "none"
},
{
"id": "cost-source",
"type": "external",
"label": "Invoices + review minutes",
"tag": "Include failed attempts",
"sublabel": "Join evidence to the workflow",
"pos": [
50,
570
],
"size": [
580,
180
],
"icon": "none"
},
{
"id": "cost",
"type": "frontend",
"label": "Allocated cost / accepted tasks",
"tag": "Cost per accepted outcome",
"sublabel": "Missing buckets = partial",
"pos": [
770,
570
],
"size": [
700,
180
],
"icon": "none"
},
{
"id": "confidence-source",
"type": "external",
"label": "Anonymous 1\u20135 survey",
"tag": "Protect small groups",
"sublabel": "Join evidence to the workflow",
"pos": [
50,
820
],
"size": [
580,
180
],
"icon": "none"
},
{
"id": "confidence",
"type": "frontend",
"label": "Confidence sum / valid responses",
"tag": "Verification confidence (1\u20135)",
"sublabel": "Show distribution + response rate",
"pos": [
770,
820
],
"size": [
700,
180
],
"icon": "none"
},
{
"id": "interpret",
"type": "backend",
"label": "Compare with baseline",
"tag": "Interpret, then act",
"sublabel": "Like workflows + source coverage\nZero denominator = N/A\nTrends are not causal ROI\nFix gaps; improve the workflow",
"pos": [
1650,
325
],
"size": [
680,
400
],
"icon": "none"
}
{"id": "workflow", "type": "backend", "label": "Workflow effectiveness", "tag": "01 / Baseline current work", "sublabel": "Accepted work, time, failures\nCost, effort + experience\nSelect relevant contracts only\nSkills need not exist yet", "pos": [40, 40], "size": [720, 310], "icon": "none"},
{"id": "compare", "type": "backend", "label": "Compare the same outcomes", "tag": "02 / After introducing skills", "sublabel": "Same workflow + acceptance\nSame follow-up + source coverage\nKeep gaps and task mix visible\nBefore / after is not causality", "pos": [840, 40], "size": [720, 310], "icon": "none"},
{"id": "interpret", "type": "external", "label": "Is work getting better?", "tag": "03 / Interpret workflow evidence", "sublabel": "Balance value, quality and risk\nMore adoption is not better work\nKeep live outcomes separate\nfrom skill evaluation cases", "pos": [1640, 40], "size": [720, 310], "icon": "none"},
{"id": "skills", "type": "frontend", "label": "Skills effectiveness & health", "tag": "01 / Qualify named skill versions", "sublabel": "Selection precision + recall\nSeparate evaluation evidence\nNo applicable skills: N/A\nNot a zero workflow baseline", "pos": [40, 590], "size": [720, 310], "icon": "none"},
{"id": "observe", "type": "frontend", "label": "Observe use + upkeep", "tag": "02 / Adoption and maintenance", "sublabel": "Supported bundle coverage\nApproved-workflow adoption\nSubstantive review evidence\nMissing observations: unknown", "pos": [840, 590], "size": [720, 310], "icon": "none"},
{"id": "improve", "type": "external", "label": "Improve, retain or retire", "tag": "03 / Use both tracks together", "sublabel": "16 optional candidate contracts\n9 prototype / 7 unimplemented\nNo mandatory collection\nNo installed telemetry claimed", "pos": [1640, 590], "size": [720, 310], "icon": "none"}
],
"connections": [
{
"id": "success-source-success",
"from": "success-source",
"to": "success",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default"
},
{
"id": "quality-source-quality",
"from": "quality-source",
"to": "quality",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default"
},
{
"id": "cost-source-cost",
"from": "cost-source",
"to": "cost",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default"
},
{
"id": "confidence-source-confidence",
"from": "confidence-source",
"to": "confidence",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default"
},
{
"id": "success-interpret",
"from": "success",
"to": "interpret",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
1550,
160
],
[
1550,
525
]
]
},
{
"id": "quality-interpret",
"from": "quality",
"to": "interpret",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
1550,
410
],
[
1550,
525
]
]
},
{
"id": "cost-interpret",
"from": "cost",
"to": "interpret",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
1550,
660
],
[
1550,
525
]
]
},
{
"id": "confidence-interpret",
"from": "confidence",
"to": "interpret",
"label": "",
"fromSide": "right",
"toSide": "left",
"route": "straight",
"width": 4,
"variant": "default",
"via": [
[
1550,
910
],
[
1550,
525
]
]
}
{"id": "workflow-compare", "from": "workflow", "to": "compare", "label": "", "fromSide": "right", "toSide": "left", "route": "straight", "width": 4, "variant": "default"},
{"id": "compare-interpret", "from": "compare", "to": "interpret", "label": "", "fromSide": "right", "toSide": "left", "route": "straight", "width": 4, "variant": "default"},
{"id": "skills-observe", "from": "skills", "to": "observe", "label": "", "fromSide": "right", "toSide": "left", "route": "straight", "width": 4, "variant": "default"},
{"id": "observe-improve", "from": "observe", "to": "improve", "label": "", "fromSide": "right", "toSide": "left", "route": "straight", "width": 4, "variant": "default"},
{"id": "interpret-improve", "from": "interpret", "to": "improve", "label": "", "fromSide": "bottom", "toSide": "top", "route": "straight", "width": 4, "variant": "default"}
]
}
}
+58
View File
@@ -0,0 +1,58 @@
---
id: baseline
title: Baseline
sidebar_label: Baseline
description: Understand a workflow, select relevant candidate metrics and establish feasible starting evidence for later comparison.
pagination_prev: measurement/index
pagination_next: skills-governance
hide_table_of_contents: true
---
import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
<div className="strategy-content">
Establish a starting position for one workflow as adoption reaches it. This is not a mandatory company-wide baseline of every metric in the [Measurement registry](./measurement/index.mdx).
<ArchifyDiagram name="strategy-baseline" title="From current workflow through relevant selection and feasible evidence to a starting position and later comparison" story />
**Target operating model — no actual baseline values or approved thresholds are established here.** Missing evidence remains an explicit gap, not an invented starting value.
## Understand the current workflow
Describe the task, team or service, intended outcome, current tools, handoffs, controls and known friction. Bound what is in and out of scope. For Delivery, start with codebase structure and existing principles, system-logic sources, tests, builds and packaging, then deployments. Record current practice, including any existing AI use; do not label it “no-skill” unless that is true.
## Select relevant metrics, with reasons
Start with **Workflow effectiveness**: select relevant current-workflow outcomes before standardized skills adoption—accepted work, delivery time, failures/rework, cost, human effort/experience or business acceptance where the contracts apply. Choose the registry entries that answer this workflow's questions. Record why each selected metric applies, what decision it can inform, and why other candidates are irrelevant or deferred. There is no required universal subset. A service-level DORA metric, a qualification test and a people survey have different populations; they are not interchangeable.
Keep **Skills effectiveness & health** separate. If no applicable skills exist, selection, bundle, adoption and review measures may be N/A, not zero; they are not prerequisites for baselining current work. If skills already exist, record that starting context and qualify named revisions separately. Do not mix sandbox skill evaluations into validated workflow task success or live policy-effect rates.
Agree what counts as a started task, independent acceptance and completed follow-up before counting outcomes. Freeze eligibility and acceptance rules and verify event joins. Select a complete comparable workflow cycle and a predeclared precision/sample requirement appropriate to the decision. Do not select a convenient end date after seeing results. Where those requirements cannot be met, record the resulting evidence limitation.
## Agree feasible evidence
Confirm collection feasibility, period, sources, owner, independent reviewer, access, lawful basis, privacy and retention before collecting. Use the [shared safeguards](./measurement/collection-and-safeguards.mdx) and each selected contract's input requirements. Proposed owner/cadence entries are not already assigned responsibilities.
Start with a controlled worksheet or export if automation is unavailable. Join task IDs to acceptance records, PR/commit IDs, CI results and later defects where relevant; test source coverage and permissions. Repository and CI evidence support verification, but a green build alone is not task acceptance. Record exact skill revisions and client/model configurations when present; keep missing versions unknown.
## Record the starting position
Collect prospective current-practice evidence over the agreed period. Record actual starting values only when supported by traceable evidence. Include units, population, observation period, counts, exclusions, source coverage, calculation version, uncertainty and limitations. Zero denominators mean “not available,” not zero performance.
For each selected metric, keep one of these explicit records:
- **Available:** evidenced starting value, source links, calculation, owner and limits.
- **Unavailable:** missing input or permission, affected comparison, responsible owner and proposed next action or review point. Never fill the gap with the synthetic example or an assumed industry value.
Record deferred and non-applicable candidates separately from selected-but-unavailable metrics. This page is the recording method, not an Eldorado baseline report or a set of approved targets.
## Keep later evaluation comparable
Retain task class, service, skill, client/model configuration and concurrent changes. In [Adoption](./skills-adoption.mdx), use the same agreed eligibility, acceptance and observation rules; in [Maintenance](./skills-maintenance.mdx), record any changes and breaks in comparability rather than silently replacing the starting position.
A matched or randomized comparison may be used when practical and ethical. Label observational trends as descriptive, not causal ROI; report confounding, selection and uncertainty. Missing or small samples limit conclusions. Baseline values describe current practice; they do not establish acceptable risk or authorize expansion.
**Next:** [Govern skill ownership and authority →](./skills-governance.mdx)
</div>
@@ -2,12 +2,12 @@
id: collection-and-safeguards
slug: /measurement/collection-and-safeguards
title: Collection and safeguards
description: Collection rules, baseline interpretation, event contracts and privacy safeguards.
description: Shared interpretation rules, event contracts and privacy safeguards for selected metrics.
---
<div className="strategy-content">
**Target operating model — recommended contracts, not installed collection.** All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
**Target operating model — recommended contracts, not installed collection.** Registry inclusion does not require use, collection or baselining. All owner and cadence entries are proposals to confirm for selected metrics, not assigned responsibilities or approved schedules.
{/* preserved:start */}
Introduction depends on the [roadmap gates](../roadmap.mdx); these pages do not describe installed controls or measured company results.
@@ -20,11 +20,11 @@ Begin with task acceptance, repository, CI, deployment and incident systems beca
Validated success uses all eligible initiated tasks whose predeclared observation window has matured. Failed and abandoned tasks remain nonsuccess. Unresolved or unobserved outcomes remain in the denominator, with known-outcome coverage shown alongside the conservative confirmed-success share. They are not relabeled as observed failure. A task cancelled before start is excluded; cancellation after start remains visible. Count a task once across retries and multiple skills. For timeliness, also show unfinished work and age; accepted-only lead-time distributions have survivorship limitations.
Track all five service-level DORA measures: commit-to-production lead time, deployment frequency, change fail rate, failed deployment recovery time and deployment rework rate. Do not substitute PR-open-to-merge time or all-incident MTTR. Pair them with matured escaped-quality rates, policy effects, total cost per accepted outcome, support coverage, adoption, human experience and catalog maintenance. Keep customer/business outcomes linked to their departmental hypotheses; do not infer conversion, trust or revenue improvement from delivery telemetry.
The registry includes five service-level DORA measures: commit-to-production lead time, deployment frequency, change fail rate, failed deployment recovery time and deployment rework rate. Select them only where applicable; do not substitute PR-open-to-merge time or all-incident MTTR. Where relevant, interpret them alongside selected quality, policy, cost, support, adoption, experience or maintenance evidence. Keep customer/business outcomes linked to their departmental hypotheses; do not infer conversion, trust or revenue improvement from delivery telemetry.
### Baseline and interpretation
### Interpretation limits {#baseline-and-interpretation}
Before a pilot, freeze eligibility and acceptance rules and verify event joins. Collect prospective no-skill/current-practice evidence over a complete comparable workflow cycle and until the preregistered precision/sample requirement is met. Do not select a convenient end date after seeing results. Retain task class, service, skill, client/model configuration and concurrent changes. A matched or randomized comparison may be used when practical and ethical; label observational trends as descriptive and report confounding, selection and uncertainty.
See [Baseline](../baseline.mdx) for selecting relevant metrics and establishing comparable current-practice evidence. Pilot application belongs to [Adoption](../skills-adoption.mdx); ongoing reporting belongs to [Maintenance](../skills-maintenance.mdx).
Elapsed time and human effort are different quantities. Parallel agents may reduce waiting while increasing review or compute. Include failed attempts and human review/rework in cost, do not multiply a multi-skill task's value across every invocation, and do not convert survey perceptions into proven time savings. Small or incomplete populations yield evidence limits, not an ROI percentage.
+42 -69
View File
@@ -3,7 +3,9 @@ id: index
slug: /measurement
title: Skills Measurement
sidebar_label: Measurement
description: Which KPIs to collect during skills adoption, where the evidence comes from, how to calculate them and when to report.
description: Optional contracts for workflow effectiveness and skills effectiveness and health, with distinct populations and honest implementation limits.
pagination_prev: stage-01-skills-adoption
pagination_next: baseline
hide_table_of_contents: true
---
@@ -11,59 +13,17 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
<div className="strategy-content">
Measure adoption in stages: first establish today’s performance, then follow the pilot, extend coverage and keep skills current. Count use separately from outcomes—more use does not by itself mean better work.
Start with how work performs today; compare relevant outcomes after introducing skills. Separately assess whether the skills are effective, supported, used and maintained. Registry inclusion does not require a metric to be used, collected or baselined. More adoption does not prove improved work.
<ArchifyDiagram name="strategy-measurement" title="Skills adoption measurement: baseline, pilot, broader adoption and monitoring" story />
<ArchifyDiagram name="strategy-measurement" title="Workflow effectiveness / Skills effectiveness & health" story />
**Recommended collection plan · Target operating model, not installed telemetry.** Confirm the proposed roles and reporting cadence below before collecting data.
**Target operating model — candidate definitions, not installed telemetry or a collection plan.** Proposed owners and cadences in the contracts apply only if selected and agreed for a workflow.
## 1. Establish the baseline
## Read a candidate contract
Choose one workflow, such as reviewing a code change with a review skill. Agree what counts as a started task, independent acceptance and the follow-up period before counting outcomes. Collect current-practice evidence over a complete comparable workflow cycle and until the agreed sample requirement is met; use the same rules in the pilot.
Each entry explains meaning and applicability, calculation, required inputs and evidence, exclusions, missing-evidence behavior, limitations and implementation status. The two groups below classify every contract by its primary question; conditional reuse never merges populations. A delivery metric need not fit a non-delivery workflow.
Start with a controlled worksheet or export. Join task IDs to acceptance records, PR/commit IDs, CI results and later defects. Record the exact skill revision and client configuration for pilot work; keep missing versions unknown. Repository and CI evidence support verification, but a green build alone is not task acceptance.
## 2. Measure the pilot
Start with these four questions. Capture inputs as work happens; do not reconstruct review effort from elapsed PR time.
### Are tasks reaching acceptance?
**Collect:** task starts and independent acceptance, failure or abandonment records from the work tracker. **Calculate:** accepted tasks / all eligible starts whose observation period has ended × 100. Failed, abandoned and unresolved tasks stay in the denominator; show unknown outcomes and coverage separately. This is [validated task success](./validated-task-success.mdx), not a count of agent completions. **Weekly:** Quality Engineering reviews the pilot cohort.
### Is quality holding up?
**Collect:** accepted change IDs, linked confirmed defects, severity and follow-up dates from review and defect records; retain PR/CI evidence. **Calculate:** changes with at least one confirmed defect / accepted changes with completed follow-up × 100. Count each affected change once, not each defect. Missing links do not mean clean work. **Monthly:** Quality Engineering reviews [escaped quality](./changes-with-escaped-quality-issues.mdx) after follow-up, alongside severe incident counts.
### What does an accepted outcome cost?
**Collect:** invoices and usage costs plus sampled human review/rework minutes at approved rates, including unsuccessful attempts and allocated licenses/tooling. **Calculate:** total allocated workflow cost / independently accepted tasks in the same matured start cohort. Keep effort separate from waiting time. Missing buckets make this a partial estimate, not total cost. **Monthly:** Finance & Accounting reconciles [cost per accepted outcome](./cost-per-accepted-outcome.mdx), restating late invoices.
### Can people confidently verify the work?
**Collect:** an anonymous 1–5 survey after a pilot workflow cycle: verification confidence, manageable workload and usefulness as separate items. **Calculate:** sum of valid confidence scores / valid responses; also show the distribution and responses / invitations × 100. This guides enablement, not claims of saved time. **After each pilot cycle:** People & Administration reviews [confidence and cognitive load](./verification-confidence-and-cognitive-load.mdx); protect small groups.
### What a pilot report looks like
**Illustrative arithmetic, not company results or targets.** The bundled synthetic fixture shows four matured starts: one accepted, one failed, one abandoned and one unresolved. Confirmed success is **1 / 4 × 100 = 25%**, with **75%** known-outcome coverage. A newer start has not finished its observation period and is shown separately.
Recorded compute spend is **EUR 60 / 1 = EUR 60** per accepted outcome—a **partial estimate** because licenses, tooling, review and rework are missing. Five survey responses total 20 points: **20 / 5 = 4** out of 5; response rate is **5 / 10 × 100 = 50%**. The report calls for reconciling the unknown task and missing costs, not claiming a skills benefit. Reproduce it with `node scripts/ai-kpi.mjs`; [fixture and limits](./synthetic-example.mdx).
## 3. Extend collection as adoption grows
Keep those outcome measures, then add reach. An adoption percentage is meaningless without a known eligible population.
**Are supported skills available?** Freeze the expected active installation inventory; compare observed bundle/adapter revisions with the approved support and revocation records. [Supported bundle coverage](./supported-bundle-coverage.mdx) = fresh, verified supported installations / all expected active installations × 100. Offline or stale entries stay in the denominator. **Weekly and at revocation:** Platform & IT reconciles coverage.
**Are approved workflows being used?** Freeze the lawfully enrolled participant cohort; collect workflow-linked use of an approved revision through a qualified adapter or a separately labeled declaration. [Approved-workflow adoption](./approved-workflow-adoption.mdx) = eligible participants with at least one observed approved use / eligible invited participants × 100. Report this as an observed lower bound with source coverage: missing use is unknown. Installation and loading are not use. **Monthly:** Data & AI reviews reach without invocation quotas or employee rankings.
## 4. Keep the collection running
**Are skills still maintained?** From the versioned catalog, join each active approved revision to its owner, substantive review evidence and due date. [Review coverage](./skills-within-substantive-review-window.mdx) = revisions with all three current / all active approved revisions × 100. **Monthly and each release:** Data & AI reports overdue/ownerless revisions and deprecated or revoked versions still in use—not just a percentage.
At each report, compare like workflows with the baseline and publish the period, counts, exclusions and source coverage. Zero denominators mean “not available.” Trends are descriptive, not causal ROI. Act on critical policy effects immediately; add selection precision/recall at qualification and service-level delivery or departmental outcome measures when their source links are ready.
Agree purpose, lawful basis, access and retention first. No raw prompts, code or secrets by default; suppress people cohorts below five and prevent identifying drill-downs.
To select a relevant subset and establish actual starting evidence, use [Baseline](../baseline.mdx). Pilot application belongs to [Adoption](../skills-adoption.mdx); ongoing interpretation belongs to [Maintenance](../skills-maintenance.mdx).
## Metric definitions
@@ -71,29 +31,42 @@ There are **16 contracts: 9 prototype calculations and 7 unimplemented metrics**
The nine calculations cover task success, selection precision and recall, change fail rate, deployment rework, escaped quality, policy effects, cost and the primary human-experience item. The seven omissions are supported bundle coverage, approved-workflow adoption, change lead time, deployment frequency, failed deployment recovery time, substantive-review coverage and workflow-specific business acceptance.
Each contract is a prospective collection design. No live source or observed baseline is established. N and D refer to the numerator and denominator shown for that metric.
Each contract is a prospective definition, not a rollout obligation. No live source or observed baseline is established. N and D refer to the numerator and denominator shown for that metric.
Selection measures concern qualification; coverage and adoption concern reach; DORA measures concern service delivery. Outcome, safety, cost, experience and maintenance measures retain their distinct populations.
### Workflow effectiveness
1. [Validated task success](./validated-task-success.mdx) — prototype calculation
2. [Skill selection precision](./skill-selection-precision.mdx) — prototype calculation
3. [Skill selection recall](./skill-selection-recall.mdx) — prototype calculation
4. [Supported bundle coverage](./supported-bundle-coverage.mdx) — unimplemented metric
5. [Approved-workflow adoption](./approved-workflow-adoption.mdx) — unimplemented metric
6. [Change lead time](./change-lead-time.mdx) — unimplemented metric
7. [Deployment frequency](./deployment-frequency.mdx) — unimplemented metric
8. [Change fail rate](./change-fail-rate.mdx) — prototype calculation
9. [Failed deployment recovery time](./failed-deployment-recovery-time.mdx) — unimplemented metric
10. [Deployment rework rate](./deployment-rework-rate.mdx) — prototype calculation
11. [Changes with escaped quality issues](./changes-with-escaped-quality-issues.mdx) — prototype calculation
12. [Confirmed policy effects](./confirmed-policy-effects.mdx) — prototype calculation
13. [Cost per accepted outcome](./cost-per-accepted-outcome.mdx) — prototype calculation
14. [Verification confidence and cognitive load](./verification-confidence-and-cognitive-load.mdx) — prototype calculation
15. [Skills within substantive review window](./skills-within-substantive-review-window.mdx) — unimplemented metric
16. [Workflow-specific business acceptance](./workflow-specific-business-acceptance.mdx) — unimplemented metric
**Is the work getting better?** Baseline relevant current-workflow outcomes even before standardized skills exist, then compare the same outcomes during adoption and maintenance. Use comparable task mix, acceptance rules, follow-up periods and source coverage. Before/after trends alone are not causal evidence of a skills benefit.
Read [Collection and safeguards](./collection-and-safeguards.mdx) for shared baseline, event and privacy rules. [Run the synthetic measurement example](./synthetic-example.mdx) for reproducible arithmetic and limits.
1. [Validated task success](./validated-task-success.mdx) — **Prototype calculation.** Independently accepted outcomes among matured workflow starts; failures, abandonment and unresolved outcomes remain in the denominator.
2. [Change lead time](./change-lead-time.mdx) — **Unimplemented metric.** Delivery time for production changes in one service, not general task duration.
3. [Deployment frequency](./deployment-frequency.mdx) — **Unimplemented metric.** Production delivery frequency for one service; frequency alone is not value.
4. [Change fail rate](./change-fail-rate.mdx) — **Prototype calculation.** Production deployments causing failures; requires joined change/incident evidence.
5. [Failed deployment recovery time](./failed-deployment-recovery-time.mdx) — **Unimplemented metric.** Recovery from failed production deployments; conditional on eligible incidents.
6. [Deployment rework rate](./deployment-rework-rate.mdx) — **Prototype calculation.** Unplanned corrective production deployments, not all forms of task rework.
7. [Changes with escaped quality issues](./changes-with-escaped-quality-issues.mdx) — **Prototype calculation.** Accepted changes with confirmed downstream issues after follow-up.
8. [Confirmed policy effects](./confirmed-policy-effects.mdx) — **Prototype calculation.** Safety of supported workflow attempts; governed skill trials are a separate evaluation population, never pooled with live work.
9. [Cost per accepted outcome](./cost-per-accepted-outcome.mdx) — **Prototype calculation.** Cost of the matured workflow cohort, including unsuccessful attempts and recorded review/rework effort. Missing cost buckets remain partial.
10. [Verification confidence and cognitive load](./verification-confidence-and-cognitive-load.mdx) — **Prototype calculation.** Anonymous cohort experience: confidence, workload and usefulness separately, not measured time savings.
11. [Workflow-specific business acceptance](./workflow-specific-business-acceptance.mdx) — **Unimplemented metric.** Acceptance against an agreed departmental rubric; requires a defined workflow and independent evidence.
**Next:** [Maintain skills using the evidence →](../skills-maintenance.mdx)
Human effort is recorded as review/rework inputs where the cost contract supports it; the experience survey describes perception. Neither elapsed delivery time nor token counts establish effort saved. If the current workflow lacks the event semantics required by a contract (for example, governed attempts), record it as not applicable or unavailable with a reason; do not relabel unrelated records to manufacture a baseline.
### Skills effectiveness & health
**Are the skills fit for use and kept fit?** Qualify named skills and versions, observe supported use during adoption, and review or retire them in maintenance. Without applicable skills, bundles or enrolled use, skill-specific measures may be **N/A, not zero**. Once a population exists, missing observations are unknown, not evidence of non-use or good health.
1. [Skill selection precision](./skill-selection-precision.mdx) — **Prototype calculation.** Did the evaluated selection choose an applicable skill? Requires labeled qualification cases.
2. [Skill selection recall](./skill-selection-recall.mdx) — **Prototype calculation.** Were expected skills selected? Requires the same labeled qualification population.
3. [Supported bundle coverage](./supported-bundle-coverage.mdx) — **Unimplemented metric.** Are expected active installations on supported, non-revoked bundles/adapters?
4. [Approved-workflow adoption](./approved-workflow-adoption.mdx) — **Unimplemented metric.** Is the enrolled cohort using approved skills in eligible workflows? Installation/loading is not use.
5. [Skills within substantive review window](./skills-within-substantive-review-window.mdx) — **Unimplemented metric.** Do active approved revisions have current owners and substantive review evidence?
**Task-success population matters.** The canonical validated-task-success contract above measures workflow outcomes, not an evaluation benchmark. A named skill/version can be examined as a predeclared live-workflow slice under that same contract, without counting retries or multiple skills as extra tasks or attributing causality. Sandbox/evaluation cases remain excluded: a named skill/version evaluation must be reported separately with its own declared cases, acceptance evidence and limits. It is not an additional implemented calculation or a second conflicting task-success formula. The canonical page explains this boundary. Likewise, keep policy-effect evaluation trials separate from live attempts.
Use both tracks together to decide whether to improve, retain or retire a skill. Higher selection scores, wider adoption or current reviews cannot substitute for accepted work, safety, cost and human experience.
Read [Collection and safeguards](./collection-and-safeguards.mdx) for shared interpretation, event and privacy rules. [Run the synthetic measurement example](./synthetic-example.mdx) for reproducible arithmetic and limits.
**Next:** [Establish a relevant workflow baseline →](../baseline.mdx)
</div>
@@ -29,6 +29,14 @@ Confirmed independently accepted tasks as a share of all eligible initiated task
| Gaming and limits | Split easy tasks or omit starts; reconcile starts to approved backlog and audit acceptance rubrics. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Maturation horizon is workflow-specific and must be approved; no automatic abandonment on timeout. |
{/* contract:end */}
## Workflow outcomes versus skill/version evaluation
This contract belongs to **Workflow effectiveness**. Use the same matured-start population and independent acceptance rules before and after introducing skills; skills are not required for a workflow outcome to exist. Do not narrow the later denominator to successful skill invocations.
For **Skills effectiveness & health**, a predeclared slice of live workflow tasks using a named skill/version may reuse this contract unchanged. Keep the parent cohort visible, report exact versions and selection limits, and count each task once across retries, skills and clients. Overlapping skill slices must not be summed. This is descriptive evidence, not proof that the skill caused success.
A sandbox or qualification evaluation of a named skill/version is a different population and remains excluded by this contract. Declare its cases, skill/version, client/model configuration, acceptance rubric and observed results separately; never combine those cases with live workflow starts or present their results as this prototype's workflow rate. This page does not introduce an implemented skill-evaluation metric or an alternative formula. No applicable skill means that skill-specific evaluation is N/A, not a zero workflow success rate.
Read the shared [collection and safeguards](./collection-and-safeguards.mdx) before collecting data; see the [synthetic example and limits](./synthetic-example.mdx).
Return to [Skills Measurement](./index.mdx).
+34 -2
View File
@@ -13,7 +13,7 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
## When should a pilot become a team workflow?
Expand only when a bounded canary produces independently accepted work and useful feedback. Teach people to verify artifacts and recover without AI, not merely invoke a skill.
Expand only when a bounded canary produces independently accepted work and useful feedback. Teach people to verify artifacts and recover without AI, not merely invoke a skill. Compare **Workflow effectiveness** with the current-workflow baseline; observe **Skills effectiveness & health** separately as skills enter use. More adoption does not prove improved work, and before/after trends alone are not causal evidence.
<ArchifyDiagram name="strategy-adoption" title="Choose a workflow, coach a canary, verify outcomes and improve before expansion" story />
@@ -36,6 +36,38 @@ No developer rankings, individual productivity scores, minimum invocation quotas
</details>
**Next:** [Measure accepted outcomes, not activity →](./measurement/index.mdx)
<details>
<summary>Pilot evidence, illustrative report and expansion</summary>
## Apply the selected measures in the pilot
Use the relevant subset agreed in [Baseline](./baseline.mdx), not every entry in the [Measurement registry](./measurement/index.mdx). Keep its eligibility, independent acceptance and follow-up rules. Capture inputs as work happens; record exact skill revision and client configuration, leaving missing versions unknown. Do not reconstruct review effort from elapsed PR time.
The following questions are candidates, not a mandatory pilot bundle. Proposed owners and cadences need agreement before collection:
| If this question is selected | Evidence and pilot review |
| --- | --- |
| Are tasks reaching acceptance? | Join tracker starts to independent acceptance, failure and abandonment. Apply [validated task success](./measurement/validated-task-success.mdx) to matured starts; retain failed, abandoned and unresolved tasks in the denominator and show unknown outcomes and coverage. Proposed weekly reviewer: Quality Engineering. |
| Is quality holding up? | Link accepted changes to confirmed defects, severity and follow-up dates; retain PR/CI evidence. Apply [escaped quality](./measurement/changes-with-escaped-quality-issues.mdx) after follow-up, counting each affected change once, alongside severe incidents. Missing links are not clean work. Proposed monthly reviewer: Quality Engineering. |
| What does an accepted outcome cost? | Reconcile invoices and usage, sampled review/rework minutes at approved rates, unsuccessful attempts and allocated licenses/tooling. Apply [cost per accepted outcome](./measurement/cost-per-accepted-outcome.mdx) to the same matured start cohort; distinguish effort from waiting. Missing buckets make the estimate partial. Proposed monthly reviewer: Finance & Accounting; restate late invoices. |
| Can people confidently verify the work? | Use the anonymous 1–5 survey for confidence, manageable workload and usefulness as separate items. Report the [confidence measure](./measurement/verification-confidence-and-cognitive-load.mdx), distribution and response rate; protect small groups. Proposed reviewer after each pilot cycle: People & Administration. This is enablement evidence, not proven saved time. |
### What a pilot report looks like
**Illustrative arithmetic, not company results or targets.** The bundled synthetic fixture shows four matured starts: one accepted, one failed, one abandoned and one unresolved. Confirmed success is **1 / 4 × 100 = 25%**, with **75%** known-outcome coverage. A newer start has not finished its observation period and is shown separately.
Recorded compute spend is **EUR 60 / 1 = EUR 60** per accepted outcome—a **partial estimate** because licenses, tooling, review and rework are missing. Five survey responses total 20 points: **20 / 5 = 4** out of 5; response rate is **5 / 10 × 100 = 50%**. Reconcile the unknown task and missing costs instead of claiming a skills benefit. Reproduce it with `node scripts/ai-kpi.mjs`; [fixture and limits](./measurement/synthetic-example.mdx).
### Revisit selection as adoption expands
Selection precision/recall qualify named skill versions against labeled cases; they do not measure real-workflow acceptance. Keep any skill/version evaluation separate from the live task-success cohort. Skill-specific measures with no applicable population are N/A, not zero; missing evidence for an existing population remains unknown.
Keep relevant outcome evidence comparable; add reach measures only if they answer the expanded workflow's questions. For [supported bundle coverage](./measurement/supported-bundle-coverage.mdx), freeze the expected active installation inventory and compare observed bundle/adapter revisions to support and revocation records. Offline or stale entries stay in the denominator. Platform & IT is the proposed weekly and at-revocation reviewer.
For [approved-workflow adoption](./measurement/approved-workflow-adoption.mdx), freeze the lawfully enrolled participant cohort and distinguish qualified-adapter observations from labeled declarations. Report the observed lower bound with source coverage: missing use is unknown; installation and loading are not use. Data & AI is the proposed monthly reviewer. No invocation quotas or employee rankings. Return to Baseline for a new workflow rather than treating rollout as company-wide metric collection.
</details>
**Next:** [Maintain skills using the agreed evidence →](./skills-maintenance.mdx)
</div>
+16 -1
View File
@@ -13,7 +13,7 @@ import ArchifyDiagram from '@site/src/components/ArchifyDiagram';
## What happens when a skill drifts or causes harm?
Monitor usefulness and safety throughout a revision's life. Unsafe behavior triggers containment; a correction returns through independent tests and approval, never automatic reinstatement.
Monitor both **Workflow effectiveness** (comparable outcomes, safety, cost and human experience) and **Skills effectiveness & health** (selection, supported use and substantive review) throughout a revision's life. Use the evidence to improve, retain or retire skills; adoption or current review dates alone do not prove better work. Unsafe behavior triggers containment; a correction returns through independent tests and approval, never automatic reinstatement.
<ArchifyDiagram name="strategy-maintenance" title="Monitor, triage and test corrections; promote safely or contain and roll back" story />
@@ -44,6 +44,21 @@ Owner ratification is required before adoption. Review earlier after incidents o
</details>
<details>
<summary>Ongoing reporting and comparison</summary>
## Keep selected evidence useful
Continue the measures agreed for the workflow in [Baseline](./baseline.mdx) and applied during [Adoption](./skills-adoption.mdx). Revisit relevance when scope changes; the [registry](./measurement/index.mdx) is a source of choices, not a requirement to collect every metric. Preserve current-workflow comparisons separately from named skill/version evaluations. No applicable skill population is N/A, not zero; missing evidence for existing revisions is unknown and must not improve reported health.
If substantive-review coverage is selected, join each active approved catalog revision to its owner, substantive review evidence and due date. Apply [review coverage](./measurement/skills-within-substantive-review-window.mdx): revisions with all three current / all active approved revisions × 100. The proposed Data & AI review is monthly and at each release, subject to agreement. Report overdue/ownerless revisions and deprecated or revoked versions still in use—not just a percentage.
At each agreed report, compare like workflows with their recorded starting position. Publish period, counts, exclusions, source coverage and changes in calculation or scope. Zero denominators mean “not available”; unresolved gaps remain visible. Trends are descriptive, not causal ROI. Reconcile late evidence using versioned corrections and distinguish changed practice from changed measurement.
Act on critical policy effects immediately; do not wait for a reporting cycle. Use selection precision/recall at qualification, or service-level delivery and departmental outcome measures, only where relevant and their source links are feasible. Confirm purpose, lawful basis, access and retention before changing collection, following the [shared safeguards](./measurement/collection-and-safeguards.mdx).
</details>
**Next:** [Stage - 02 - Autonomous Agent →](./stage-02-autonomous-agent.mdx)
</div>
+9 -4
View File
@@ -19,18 +19,23 @@ Adoption then extends to other SDLC phases; their order is not yet decided. Deli
## Repeat within each phase
**Understand the current situation → establish KPIs and a baseline → engineer skills topology → use skills in real work → collect metrics and feedback → understand the new current situation → repeat.**
**Understand the current situation → select relevant KPIs and establish a workflow baseline → engineer skills topology → use skills in real work → collect agreed metrics and feedback → understand the new current situation → repeat.**
Skills topology connects what skills exist, how they relate, when they are used and how they work together. Compare accepted outcomes, quality, cost and review effort with the baseline; use friction and feedback to revise the skills and working practices. These are repeating steps within each phase, not additional roadmap stages.
## Put the foundation into practice
- [Measurement](./measurement/index.mdx) — distinguish Workflow effectiveness from Skills effectiveness & health; candidate inclusion does not require collection or baselining.
- [Baseline](./baseline.mdx) — understand current workflow outcomes first, select relevant metrics and record feasible starting evidence or explicit gaps; absent skills are not zero performance.
- [Governance](./skills-governance.mdx) — define ownership, authority and approval of skills.
- [Quality](./skills-quality.mdx) — qualify skills and verify their outcomes before wider use.
- [Adoption](./skills-adoption.mdx) — coach bounded workflows with a supported client and a manual path.
- [Measurement](./measurement/index.mdx) — establish KPIs, collect evidence and compare outcomes with the baseline.
- [Maintenance](./skills-maintenance.mdx) — review feedback, control versions and recover from unsafe updates.
- [Adoption](./skills-adoption.mdx) — compare workflow outcomes and observe skill use separately, with a supported client and a manual path.
- [Maintenance](./skills-maintenance.mdx) — monitor both tracks to improve or retire skills, control versions and recover from unsafe updates.
Proven skills, measurements and working practices support [Stage - 02 - Autonomous Agent](./stage-02-autonomous-agent.mdx); adoption alone does not grant autonomous execution authority.
These six topics belong to Stage 01, not six additional roadmap stages. Establish a baseline per workflow as adoption reaches it—not a mandatory company-wide baseline of every registry metric.
**Next:** [Browse the Measurement registry →](./measurement/index.mdx)
</div>
@@ -150,7 +150,9 @@
"shared": [
{
"slug": "collection-and-safeguards",
"sha256": "8610ed8df6a24cf138f9e6e2c09060db2aab4c0b1259ca0168e581e3fb964e52"
"sha256": "37709cf9978a698026492b29f2095996c462e098a74f082a6b3c3a3a7b38ecab",
"previousSha256": "8610ed8df6a24cf138f9e6e2c09060db2aab4c0b1259ca0168e581e3fb964e52",
"revisionNote": "Stage 01 separation: baseline establishment moved to baseline.mdx; DORA candidates are optional. Event/privacy and outcome safeguards retained."
},
{
"slug": "synthetic-example",
+34
View File
@@ -0,0 +1,34 @@
import test from 'node:test';
import assert from 'node:assert/strict';
import {readFileSync} from 'node:fs';
const read = path => readFileSync(path, 'utf8');
test('Baseline is workflow-scoped, evidence-bound and distinct from the optional registry', () => {
const page = read('docs/strategy/baseline.mdx');
for (const heading of ['Understand the current workflow','Select relevant metrics, with reasons','Agree feasible evidence','Record the starting position','Keep later evaluation comparable']) assert(page.includes(`## ${heading}`));
for (const text of ['not a mandatory company-wide baseline','no actual baseline values or approved thresholds','lawful basis','privacy','retention','source coverage','**Available:**','**Unavailable:**','not causal ROI','selected-but-unavailable']) assert(page.includes(text), text);
assert(page.indexOf('<ArchifyDiagram') < page.indexOf('## Understand'));
assert(!page.includes('25%'));
for (const doc of ['measurement/index','measurement/collection-and-safeguards','skills-adoption','skills-maintenance','skills-governance']) assert(page.includes(`./${doc}.mdx`));
const registry = read('docs/strategy/measurement/index.mdx');
assert(registry.includes('pagination_next: baseline'));
assert(page.includes('pagination_prev: measurement/index'));
assert(page.includes('pagination_next: skills-governance'));
});
test('workflow application has one home and shared safety remains explicit', () => {
const registry = read('docs/strategy/measurement/index.mdx');
const shared = read('docs/strategy/measurement/collection-and-safeguards.mdx');
const adoption = read('docs/strategy/skills-adoption.mdx');
const maintenance = read('docs/strategy/skills-maintenance.mdx');
assert(!registry.includes('Measure the pilot'));
assert(!shared.includes('Track all five'));
assert(!shared.includes('Before a pilot, freeze'));
assert(shared.includes('id') && shared.includes('{#baseline-and-interpretation}')); // Existing inbound anchor survives relocation.
for (const marker of ['transport retries','quarantined','Late arrivals','Unknown version stays null','30 days','12 months','below five people','No raw prompts','Consent is not presumed']) assert(shared.includes(marker),marker);
assert(adoption.includes('not a mandatory pilot bundle'));
assert(adoption.includes('What a pilot report looks like'));
assert(maintenance.includes('Keep selected evidence useful'));
assert(maintenance.includes('versioned corrections'));
assert(adoption.includes('**Next:** [Maintain skills using the agreed evidence →](./skills-maintenance.mdx)'));
});
+5 -2
View File
@@ -7,7 +7,7 @@ const assert=require('node:assert/strict');
const browser=await chromium.launch({executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE,args:['--no-sandbox']});
const results=[];
try {
for(const topic of ['governance','quality','adoption','measurement','maintenance']) for(const width of [1440,1024,390,320]){
for(const topic of ['measurement','baseline','governance','quality','adoption','maintenance']) for(const width of [1440,1024,390,320]){
const spec=JSON.parse(fs.readFileSync(`diagrams/strategy-${topic}${width<=1100?'-mobile':''}.architecture.json`));
const page=await browser.newPage({viewport:{width:1200,height:1000}});
await page.goto('file://'+path.resolve(`${dir}/${topic}-${width}.svg`));
@@ -33,7 +33,10 @@ const assert=require('node:assert/strict');
assert.deepEqual(measured.labelOverlaps,[],`${topic}-${width}: rendered edge labels overlap`);
for(const n of spec.components){assert(measured.text.includes(n.label));assert(measured.text.includes(n.tag));for(const line of n.sublabel.split('\n'))assert(measured.text.includes(line));}
for(const e of spec.connections)if(e.label)assert(measured.text.includes(e.label));
if(width===1440)await page.screenshot({path:`${dir}/${topic}-standalone-export.png`});
if(width===1440){
await page.setViewportSize({width:spec.meta.viewBox[0],height:spec.meta.viewBox[1]});
await page.screenshot({path:`${dir}/${topic}-standalone-export.png`});
}
results.push({topic,width,nodes:measured.nodes.length,edges:measured.edges.length,complete:true});await page.close();
}
fs.writeFileSync(`${dir}/export-results.json`,JSON.stringify(results,null,2));
+32 -6
View File
@@ -18,12 +18,15 @@ const fs = require('node:fs');
assert.equal(await page.locator('h1').innerText(), 'Skills Measurement');
assert((await page.title()).startsWith('Skills Measurement |'));
assert.equal(await page.locator('.strategy-content details').count(), 0);
assert.equal(await page.locator('.strategy-content h2').count(), 5);
assert.equal(await page.locator('.strategy-content h2').count(), 2);
assert.deepEqual((await page.locator('.strategy-content h3').allTextContents()).map(text => text.replaceAll('\u200b', '')), ['Workflow effectiveness', 'Skills effectiveness & health']);
assert.equal(await page.locator('.strategy-content ol').count(), 2);
assert.equal(await page.locator('.strategy-content ol > li').count(), 16);
if (width < 700) await page.getByRole('button', {name:'Toggle navigation bar'}).click();
const menu = page.locator('.theme-doc-sidebar-menu .menu__link').filter({visible:true});
await menu.first().waitFor({state:'visible'});
const metrics = JSON.parse(fs.readFileSync('research/ai-adoption/measurement-migration.json','utf8')).metrics;
assert.deepEqual(await menu.allTextContents(), ['Target','Roadmap','Stage - 01 - Skills Adoption','Governance','Quality','Adoption','Measurement',...metrics.map(m => m.title),'Collection and safeguards','Run the synthetic measurement example','Maintenance','Stage - 02 - Autonomous Agent']);
assert.deepEqual(await menu.allTextContents(), ['Target','Roadmap','Stage - 01 - Skills Adoption','Measurement',...metrics.map(m => m.title),'Collection and safeguards','Run the synthetic measurement example','Baseline','Governance','Quality','Adoption','Maintenance','Stage - 02 - Autonomous Agent']);
if (width < 700) await page.getByRole('button', {name:'Close navigation bar'}).click();
const panel = page.locator('.archify-panel--story');
const iframe = panel.locator(width > 700 ? '.story-desktop' : '.story-mobile');
@@ -41,7 +44,7 @@ const fs = require('node:fs');
await page.waitForFunction(() => document.documentElement.dataset.theme === 'dark');
await frame.locator('#btn-theme').click();
await page.waitForFunction(() => document.documentElement.dataset.theme === 'light');
for (const preset of ['blueprint','classic']) {
for (const preset of ['signal-flow','blueprint','editorial','classic']) {
await frame.locator('#btn-preset').click();
await frame.locator(`[data-preset-value="${preset}"]`).click();
assert.equal(await frame.locator('html').getAttribute('data-preset'), preset);
@@ -51,7 +54,30 @@ const fs = require('node:fs');
assert.equal(await download.failure(), null);
const path = `${output}/${width}.svg`; await download.saveAs(path);
const svg = fs.readFileSync(path, 'utf8');
assert(svg.includes('Compare with baseline') && svg.includes('Zero denominator = N/A'));
assert(svg.includes('Workflow effectiveness') && svg.includes('Skills effectiveness &amp; health') && svg.includes('No mandatory collection'));
const exports = ['svg'];
for (const format of ['png','jpeg','webp','svg-light','svg-dark','webm']) {
await frame.locator('#btn-export').click();
const option = frame.locator(`[data-format="${format}"]`);
if (await option.isDisabled()) { exports.push(`${format}:unsupported`); await frame.locator('#btn-export').click(); continue; }
const [file] = await Promise.all([page.waitForEvent('download', {timeout:60000}), option.click()]);
assert.equal(await file.failure(), null);
const target = `${output}/${width}-${format}-${file.suggestedFilename()}`;
await file.saveAs(target);
const bytes = fs.readFileSync(target); assert(bytes.length > 1000);
if (format.startsWith('svg')) assert(bytes.toString().includes('eldorado-skills-typography'));
else {
const mime = {png:'image/png', jpeg:'image/jpeg', webp:'image/webp', webm:'video/webm'}[format];
const dimensions = await page.evaluate(async ({mime,data}) => {
const media = document.createElement(mime.startsWith('video') ? 'video' : 'img');
const ready = new Promise((resolve,reject) => {media[mime.startsWith('video') ? 'onloadedmetadata' : 'onload'] = resolve; media.onerror = reject;});
media.src = `data:${mime};base64,${data}`; await ready;
return [media.videoWidth || media.naturalWidth, media.videoHeight || media.naturalHeight];
}, {mime, data:bytes.toString('base64')});
assert(dimensions.every(n => n > 0));
}
exports.push(format);
}
const opener = panel.getByRole('button', {name:/^Expand /});
await opener.click();
const close = panel.getByRole('button', {name:'Close full-screen diagram', exact:true});
@@ -76,10 +102,10 @@ const fs = require('node:fs');
assert.equal(new Set(links.map(h => new URL(h).pathname)).size, 18);
assert(!await page.evaluate(() => document.documentElement.scrollWidth > innerWidth));
assert.deepEqual(errors, []);
results.push({width, geometry, links:links.length, title:true, sidebar:true, controls:true, export:true, reference:true});
results.push({width, geometry, links:links.length, title:true, sidebar:true, controls:true, exports, reference:true});
fs.writeFileSync(`${output}/results.json`, JSON.stringify(results,null,2));
await context.close();
}
console.log(`PASS ${results.length} Skills Measurement viewports: title/sidebar, open plan, diagram geometry/controls/export, all reference links and no page errors`);
console.log(`PASS ${results.length} Skills Measurement viewports: title/sidebar, optional registry, diagram geometry/controls/export, all reference links and no page errors`);
} finally {await browser.close();}
})().catch(error => {console.error(error); process.exitCode = 1;});
+17 -3
View File
@@ -6,13 +6,23 @@ const assert=require('node:assert/strict');
const out=`.cache/skills-${process.argv[3]||'candidate'}`;fs.mkdirSync(out,{recursive:true});
const browser=await chromium.launch({executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE,args:['--no-sandbox']}); const results=[];
try {
for(const topic of ['governance','quality','adoption','measurement','maintenance']) for(const width of [1440,1024,390,320]) {
for(const topic of ['measurement','baseline','governance','quality','adoption','maintenance']) for(const width of [1440,1024,390,320]) {
console.log(`Checking ${topic} at ${width}px`);
const page=await browser.newPage({viewport:{width,height:900},colorScheme:'light'});const errors=[];page.on('pageerror',e=>errors.push(e.message));
const route=topic==='measurement'?topic:`skills-${topic}`;
const route=['measurement','baseline'].includes(topic)?topic:`skills-${topic}`;
assert.equal((await page.goto(`${base}/eldorado-v1/documentation/strategy/${route}/`,{waitUntil:'networkidle'})).status(),200);
const panel=page.locator('.archify-panel--skills');assert.equal(await panel.count(),1);
const iframe=panel.locator(width>1100?'.story-desktop':'.story-mobile');await iframe.scrollIntoViewIfNeeded();
const frame=await(await iframe.elementHandle()).contentFrame();await frame.locator('svg[role="img"]').waitFor();
// Keep iframe controls below the fixed portal header. Frame-local click
// actionability cannot detect an overlay in the parent document.
const showControls=async()=>{
await panel.locator('dialog iframe').waitFor({state:'detached'});
await panel.evaluate(n=>{
scrollTo({top:n.getBoundingClientRect().top+scrollY-100,behavior:'instant'});
return new Promise(resolve=>requestAnimationFrame(()=>requestAnimationFrame(resolve)));
});
};
const geometry=await frame.locator('svg[role="img"]').evaluate(svg=>{
const nodes=[...svg.querySelectorAll('g[data-node-id]')];const issues=[];let min=Infinity;
for(const n of nodes){const rect=n.querySelector('rect').getBBox();for(const t of n.querySelectorAll('text')){
@@ -24,16 +34,20 @@ const assert=require('node:assert/strict');
const source=JSON.parse(fs.readFileSync(`diagrams/strategy-${topic}.architecture.json`));
assert.equal(geometry.nodes,source.components.length);assert.deepEqual(geometry.issues,[]);assert(geometry.min>=10,JSON.stringify(geometry));
for(const theme of ['light','dark']){
await showControls();
if(await frame.locator('html').getAttribute('data-theme')!==theme)await frame.locator('#btn-theme').click();
await page.waitForFunction(t=>document.documentElement.dataset.theme===t,theme);
await page.waitForFunction(t=>document.documentElement.dataset.theme===t,theme).catch(error=>{throw new Error(`${topic}/${width}/${theme}: theme synchronization failed`,{cause:error});});
await panel.scrollIntoViewIfNeeded();await page.screenshot({path:`${out}/${topic}-${width}-${theme}-inline.png`});
const open=panel.getByRole('button',{name:/^Expand /});await open.click();const close=panel.getByRole('button',{name:'Close full-screen diagram',exact:true});await close.waitFor({state:'visible'});
const expanded=await(await panel.locator('dialog iframe').elementHandle()).contentFrame();await expanded.locator('svg[role="img"]').waitFor();
await expanded.waitForFunction(t=>document.documentElement.dataset.theme===t,theme);
await panel.locator('dialog').evaluate(n=>n.scrollTop=0);
assert((await expanded.url()).includes(width<=1100?`${topic}-mobile/`:`${topic}/`));
await page.screenshot({path:`${out}/${topic}-${width}-${theme}-fullscreen.png`});
if(width<=700){await page.setViewportSize({width,height:480});assert(await panel.locator('dialog').evaluate(n=>n.scrollHeight>n.clientHeight));await panel.locator('dialog').evaluate(n=>n.scrollTop=n.scrollHeight);await page.screenshot({path:`${out}/${topic}-${width}-${theme}-short-bottom.png`});await page.setViewportSize({width,height:900});}
await close.focus();await page.keyboard.press('Escape');assert(await open.evaluate(n=>n===document.activeElement));
}
await showControls();
await frame.locator('#btn-preset').click();await frame.locator('[data-preset-value="blueprint"]').click();
await frame.locator('#btn-preset').click();await frame.locator('[data-preset-value="classic"]').click();
await frame.locator('#btn-export').click();const [download]=await Promise.all([page.waitForEvent('download'),frame.locator('[data-format="svg"]').click()]);assert.equal(await download.failure(),null);
+7 -7
View File
@@ -8,12 +8,12 @@ const fs = require('node:fs');
const prefix = '/eldorado-v1/documentation/strategy/';
const first = 'Stage - 01 - Skills Adoption';
const second = 'Stage - 02 - Autonomous Agent';
const topics = ['Governance','Quality','Adoption','Measurement','Maintenance'];
const topics = ['Measurement','Baseline','Governance','Quality','Adoption','Maintenance'];
const metrics = JSON.parse(fs.readFileSync('research/ai-adoption/measurement-migration.json','utf8')).metrics;
const childIds = [...metrics.map(m => m.docId),'measurement/collection-and-safeguards','measurement/synthetic-example'];
const childTitles = [...metrics.map(m => m.title),'Collection and safeguards','Run the synthetic measurement example'];
const ids = ['target-operating-model','roadmap','stage-01-skills-adoption','skills-governance','skills-quality','skills-adoption','measurement',...childIds,'skills-maintenance','stage-02-autonomous-agent'];
const titles = ['Target','Roadmap',first,'Skills governance','Skills quality','Skills adoption','Skills Measurement',...childTitles,'Skills maintenance',second];
const ids = ['target-operating-model','roadmap','stage-01-skills-adoption','measurement',...childIds,'baseline','skills-governance','skills-quality','skills-adoption','skills-maintenance','stage-02-autonomous-agent'];
const titles = ['Target','Roadmap',first,'Skills Measurement',...childTitles,'Baseline','Skills governance','Skills quality','Skills adoption','Skills maintenance',second];
const browser = await chromium.launch({headless:true, executablePath:process.env.PLAYWRIGHT_CHROMIUM_EXECUTABLE, args:['--no-sandbox']});
const results = [];
try {
@@ -47,7 +47,7 @@ const fs = require('node:fs');
await reference.focus();
await page.keyboard.press('Enter');
await category.getByRole('link', {name:'Validated task success', exact:true}).waitFor({state:'visible'});
assert.deepEqual(await visibleLabels(), ['Target','Roadmap',first,...topics.slice(0,4),...childTitles,'Maintenance',second]);
assert.deepEqual(await visibleLabels(), ['Target','Roadmap',first,topics[0],...childTitles,...topics.slice(1),second]);
await reference.click();
await page.screenshot({path:`${output}/${width}-expanded.png`, animations:'disabled'});
await caret.click();
@@ -68,14 +68,14 @@ const fs = require('node:fs');
else assert((await page.locator('h1').innerText()).includes('Target'));
const prev = page.locator('.pagination-nav__link--prev');
const next = page.locator('.pagination-nav__link--next');
if (index) assert.equal(await prev.getAttribute('href'), `${prefix}${ids[index-1]}/`);
if (index) assert.equal(await prev.getAttribute('href'), `${prefix}${id === 'baseline' ? 'measurement' : ids[index-1]}/`);
else assert.equal(await prev.count(), 0);
if (index < ids.length-1) assert.equal(await next.getAttribute('href'), `${prefix}${ids[index+1]}/`);
if (index < ids.length-1) assert.equal(await next.getAttribute('href'), `${prefix}${id === 'measurement' ? 'baseline' : ids[index+1]}/`);
else assert.equal(await next.count(), 0);
if (index >= 3 && index < ids.length - 1) {
assert.equal(await page.locator('.breadcrumbs a').filter({hasText:first}).getAttribute('href'), `${prefix}stage-01-skills-adoption/`);
menu = await openMenu();
const expectedTopics = id === 'measurement' || id.startsWith('measurement/') ? [...topics.slice(0,4),...childTitles,'Maintenance'] : topics;
const expectedTopics = id === 'measurement' || id.startsWith('measurement/') ? [topics[0],...childTitles,...topics.slice(1)] : topics;
assert.deepEqual(await visibleLabels(), ['Target','Roadmap',first,...expectedTopics,second]);
if (id.startsWith('measurement/')) assert.equal(await page.locator('.breadcrumbs a').filter({hasText:'Measurement'}).getAttribute('href'), `${prefix}measurement/`);
await closeMenu();
+34 -4
View File
@@ -4,14 +4,16 @@ import {readFileSync} from 'node:fs';
import {calculate} from './ai-kpi.mjs';
const read = path => readFileSync(path, 'utf8');
test('Skills Measurement is an open adoption collection plan, not a hidden catalogue', () => {
test('Skills Measurement is a visible optional registry, separate from workflow application', () => {
const page = read('docs/strategy/measurement/index.mdx');
assert.match(page, /title: Skills Measurement\nsidebar_label: Measurement/);
for (const heading of ['Establish the baseline', 'Measure the pilot', 'Extend collection as adoption grows', 'Keep the collection running']) assert(page.includes(heading), heading);
for (const heading of ['Establish the baseline', 'Measure the pilot', 'Extend collection as adoption grows', 'Keep the collection running']) assert(!page.includes(heading), heading);
assert(page.includes('Registry inclusion does not require a metric to be used, collected or baselined'));
assert(page.includes('../baseline.mdx'));
assert(!page.includes('<details>'));
assert(page.includes('./collection-and-safeguards.mdx'));
assert(!page.includes('Is AI-assisted work worth continuing?'));
for (const word of ['Recommended', 'not installed', 'unknown', 'review', 'CI', 'revision', 'Monthly', 'Weekly']) assert(page.includes(word), word);
for (const word of ['candidate', 'not installed', 'applicability', 'calculation', 'inputs', 'limitations', 'implementation status']) assert(page.includes(word), word);
});
test('all sixteen metric definitions remain in the reference with explicit implementation limits', () => {
@@ -26,8 +28,36 @@ test('all sixteen metric definitions remain in the reference with explicit imple
for (const text of ['9 prototype calculations', '7 unimplemented metrics', 'no network collectors', '30 days', '12 months', 'below five people', 'Missing telemetry is unknown']) assert(page.includes(text), text);
});
test('published pilot arithmetic matches the executable fixture, including partial cost', () => {
test('two groups exhaustively classify the sixteen canonical contracts without duplication', () => {
const page = read('docs/strategy/measurement/index.mdx');
const manifest = JSON.parse(read('research/ai-adoption/measurement-migration.json'));
assert.deepEqual([...page.matchAll(/^### (.+)$/gm)].map(m => m[1]), ['Workflow effectiveness', 'Skills effectiveness & health']);
const rows = [...page.matchAll(/^\d+\. \[([^\]]+)\]\(\.\/([^/]+)\.mdx\) — \*\*(Prototype calculation|Unimplemented metric)\.\*\*/gm)];
assert.equal(rows.length, 16);
assert.equal(new Set(rows.map(m => m[2])).size, 16);
assert.deepEqual(rows.map(m => m[1]).sort(), manifest.metrics.map(m => m.title).sort());
assert.equal(rows.filter(m => m[3] === 'Prototype calculation').length, 9);
assert.equal(rows.filter(m => m[3] === 'Unimplemented metric').length, 7);
const [workflow, skills] = page.split('### Workflow effectiveness')[1].split('### Skills effectiveness & health');
assert.equal([...workflow.matchAll(/^\d+\. /gm)].length, 11);
assert.equal([...skills.matchAll(/^\d+\. /gm)].length, 5);
for (const slug of ['validated-task-success', 'confirmed-policy-effects', 'cost-per-accepted-outcome', 'workflow-specific-business-acceptance']) assert(workflow.includes(`./${slug}.mdx`));
for (const slug of ['skill-selection-precision', 'skill-selection-recall', 'supported-bundle-coverage', 'approved-workflow-adoption', 'skills-within-substantive-review-window']) assert(skills.includes(`./${slug}.mdx`));
for (const marker of ['N/A, not zero', 'More adoption does not prove improved work', 'Before/after trends alone are not causal evidence', 'Sandbox/evaluation cases remain excluded']) assert(page.includes(marker), marker);
});
test('workflow task-success contract retains evaluation exclusions and explains conditional skill slices', () => {
const page = read('docs/strategy/measurement/validated-task-success.mdx');
assert.equal((page.match(/\| Expression \|/g) || []).length, 1);
for (const marker of ['sandbox/evaluation tasks', 'Overlapping skill slices must not be summed', 'remains excluded by this contract', 'does not introduce an implemented skill-evaluation metric', 'N/A, not a zero workflow success rate']) assert(page.includes(marker), marker);
for (const name of ['baseline', 'skills-adoption', 'skills-maintenance', 'stage-01-skills-adoption']) {
const text = read(`docs/strategy/${name}.mdx`);
if (name !== 'stage-01-skills-adoption') for (const group of ['Workflow effectiveness', 'Skills effectiveness & health']) assert(text.includes(group), name);
}
});
test('published pilot arithmetic matches the executable fixture, including partial cost', () => {
const page = read('docs/strategy/skills-adoption.mdx');
const fixture = JSON.parse(read('scripts/fixtures/ai-kpi-synthetic.json'));
const report = calculate(fixture);
const success = report.kpis['validated-task-success'];
+7 -6
View File
@@ -6,15 +6,15 @@ import {join} from 'node:path';
import {execFileSync} from 'node:child_process';
import {skillsViewer,isSkillsStory} from './skills-viewer.mjs';
const read = p => readFileSync(p,'utf8');
const topics = ['governance','quality','adoption','measurement','maintenance'];
test('all six Skills Adoption pages account for exactly five diagrams and ten sources',()=>{
const topics = ['measurement','baseline','governance','quality','adoption','maintenance'];
test('all seven Skills Adoption pages account for six diagrams and twelve sources',()=>{
let count=0;
for(const route of ['stage-01-skills-adoption',...topics.map(t=>t==='measurement'?t:`skills-${t}`)]){
for(const route of ['stage-01-skills-adoption',...topics.map(t=>['measurement','baseline'].includes(t)?t:`skills-${t}`)]){
const diagrams=[...read(`docs/strategy/${route === 'measurement' ? 'measurement/index' : route}.mdx`).matchAll(/<ArchifyDiagram name="([^"]+)"/g)];
assert.equal(diagrams.length,route.startsWith('stage-')?0:1);
for(const [,name] of diagrams){assert(isSkillsStory(name));for(const suffix of ['','-mobile'])JSON.parse(read(`diagrams/${name}${suffix}.architecture.json`));count++;}
}
assert.equal(count,5);assert(!isSkillsStory('strategy-target'));assert(!isSkillsStory('strategy-roadmap'));
assert.equal(count,6);assert(!isSkillsStory('strategy-target'));assert(!isSkillsStory('strategy-roadmap'));
});
for(const topic of topics) test(`${topic}: rich native source, wide desktop, mobile parity and checked adapter`,()=>{
const name=`strategy-${topic}`;const desktop=JSON.parse(read(`diagrams/${name}.architecture.json`));
@@ -43,7 +43,7 @@ test('domain contracts retain human authority, honest measures and Delivery-firs
assert(text('quality').includes('Critical effect blocks'));
assert(text('adoption').includes('Delivery first')&&text('adoption').includes('Later order undecided'));
assert(text('adoption').includes('No quotas or rankings'));
for(const marker of ['Tracker + acceptance','Invoices + review minutes','Changes + defects','Anonymous 1–5 survey','Missing buckets = partial','Zero denominator = N/A'])assert(text('measurement').includes(marker),marker);
for(const marker of ['Workflow effectiveness','Skills effectiveness & health','16 optional candidate contracts','No mandatory collection','Before / after is not causality','9 prototype / 7 unimplemented'])assert(text('measurement').includes(marker),marker);
assert(text('maintenance').includes('No automatic reinstatement'));
});
test('topic compositions explain distinct relationships rather than a fixed card count',()=>{
@@ -55,6 +55,7 @@ test('topic compositions explain distinct relationships rather than a fixed card
has(g,'approve','owner');has(g,'distribute','withdraw');
const q=spec('quality');for(const id of ['selection','safety','artifact','outcome'])has(q,id,'gate');has(q,'gate','accept');has(q,'gate','rework');
const a=spec('adoption');for(const [x,y] of [['human','agent'],['agent','human'],['agent','learn'],['learn','delivery'],['learn','expand'],['human','expand']])has(a,x,y);
const m=spec('measurement');for(const id of ['success','quality','cost','confidence']){has(m,id+'-source',id);has(m,id,'interpret');}
const m=spec('measurement');for(const [x,y] of [['workflow','compare'],['compare','interpret'],['skills','observe'],['observe','improve'],['interpret','improve']])has(m,x,y);
const b=spec('baseline');for(const [x,y] of [['workflow','selection'],['selection','evidence'],['evidence','position'],['position','comparison']])has(b,x,y);
const c=spec('maintenance');for(const [x,y] of [['observe','triage'],['triage','change'],['change','validate'],['validate','release'],['release','observe'],['triage','safe'],['safe','observe'],['triage','retire'],['triage','contain'],['contain','change']])has(c,x,y);
});
+1 -1
View File
@@ -1,5 +1,5 @@
// Native editable geometry and edges; scoped editorial typography for Stage 01.
export const isSkillsStory = name => /^strategy-(governance|quality|adoption|measurement|maintenance)(-mobile)?$/.test(name);
export const isSkillsStory = name => /^strategy-(governance|quality|adoption|measurement|baseline|maintenance)(-mobile)?$/.test(name);
const escape = text => text.replaceAll('&', '&amp;').replaceAll('<', '&lt;').replaceAll('>', '&gt;').replaceAll('"', '&quot;');
export function skillsViewer(html, spec) {
if (spec.diagram_type !== 'architecture' || !spec.components.length) throw new Error('Skills story contract drift');
+5 -4
View File
@@ -14,13 +14,14 @@ test('Strategy has Target, Roadmap, a linked Skills Adoption category and Autono
type:'category', label:'Stage - 01 - Skills Adoption',
link:{type:'doc', id:'stage-01-skills-adoption'}, collapsed:true,
items:[
{type:'doc', id:'skills-governance', label:'Governance'},
{type:'doc', id:'skills-quality', label:'Quality'},
{type:'doc', id:'skills-adoption', label:'Adoption'},
{type:'category', label:'Measurement', collapsed:true, link:{type:'doc', id:'measurement/index'}, items:[
...JSON.parse(read('research/ai-adoption/measurement-migration.json')).metrics.map(m => m.docId),
'measurement/collection-and-safeguards','measurement/synthetic-example',
]},
{type:'doc', id:'baseline', label:'Baseline'},
{type:'doc', id:'skills-governance', label:'Governance'},
{type:'doc', id:'skills-quality', label:'Quality'},
{type:'doc', id:'skills-adoption', label:'Adoption'},
{type:'doc', id:'skills-maintenance', label:'Maintenance'},
],
@@ -39,7 +40,7 @@ test('stage overviews explain the foundation and future without replacing topic
assert(page.includes(`id: ${id}\ntitle: ${title}`));
for (const link of ['./roadmap.mdx', './target-operating-model.mdx']) assert(page.includes(link));
}
for (const id of ['skills-governance','skills-quality','skills-adoption','measurement/index','skills-maintenance']) assert(first.includes(`./${id}.mdx`));
for (const id of ['measurement/index','baseline','skills-governance','skills-quality','skills-adoption','skills-maintenance']) assert(first.includes(`./${id}.mdx`));
for (const marker of ['human + AI Agent','Delivery first','order is not yet decided','KPIs','baseline','topology','feedback','new current situation']) assert(first.includes(marker), marker);
for (const marker of ['future','proven skills','measurements','working practices','direction and review','not deployed autonomy','approved KPI thresholds']) assert(second.includes(marker), marker);
assert.match(read('docs/strategy/measurement/index.mdx'), /^title: Skills Measurement\nsidebar_label: Measurement$/m);
+1 -1
View File
@@ -13,7 +13,7 @@ test('every strategy page leads with a compact diagram story and closes its refe
assert(!page.includes('<details>') || page.indexOf(' story />') < page.indexOf('<details>'), id);
assert(!/<details\s+open/.test(page), id);
assert.equal((page.match(/<details>/g) || []).length, (page.match(/<\/details>/g) || []).length, id);
assert.equal((narrative.match(/^## /gm) || []).length, id === 'measurement' ? 5 : id === 'roadmap' ? 4 : 1, id);
assert.equal((narrative.match(/^## /gm) || []).length, id === 'measurement' ? 2 : id === 'roadmap' ? 4 : 1, id);
assert((narrative.match(/^- /gm) || []).length <= 3, id);
assert(narrative.includes('**Next:**'), id);
assert(!narrative.includes('| ---'), id);
+1 -1
View File
@@ -6,7 +6,7 @@ const model = JSON.parse(read('research/ai-adoption/strategy-model.json'));
test('seven existing strategy pages and two stage overviews preserve canonical routes', () => {
assert.equal(model.pages.length, 7);
assert.deepEqual(readdirSync('docs/strategy').filter(p => p.endsWith('.mdx')).sort(),
[...model.pages.filter(p => p.id !== 'measurement').map(({id}) => `${id}.mdx`), 'stage-01-skills-adoption.mdx', 'stage-02-autonomous-agent.mdx'].sort());
[...model.pages.filter(p => p.id !== 'measurement').map(({id}) => `${id}.mdx`), 'stage-01-skills-adoption.mdx', 'stage-02-autonomous-agent.mdx', 'baseline.mdx'].sort());
for (const {id} of model.pages) {
const page = read(`docs/strategy/${id === 'measurement' ? 'measurement/index' : id}.mdx`);
assert(page.includes(`id: ${id === 'measurement' ? 'index' : id}`));
+2
View File
@@ -22,11 +22,13 @@ if (process.argv.includes('--build')) {
verifyMeasurementPages();
const model = JSON.parse(read('research/ai-adoption/strategy-model.json'));
const indexes = readdirSync('build').filter(f => /^search-index.*\.json$/.test(f)).map(f => read(join('build',f))).join('\n');
assert(indexes.includes('/eldorado-v1/documentation/strategy/baseline/'), 'Missing indexed Baseline route');
const redirect = read('build/strategy/index.html');
assert(redirect.includes('/eldorado-v1/documentation/strategy/target-operating-model/'));
assert(redirect.includes('window.location.href') && redirect.includes('http-equiv="refresh"') && !redirect.includes('archify-panel'), 'Landing must redirect, not duplicate Target');
const strategyPages = [...model.pages,
{id:'stage-01-skills-adoption', title:'Stage - 01 - Skills Adoption'},
{id:'baseline', title:'Baseline'},
{id:'stage-02-autonomous-agent', title:'Stage - 02 - Autonomous Agent'},
];
for (const {id, title} of strategyPages) {
+4 -3
View File
@@ -9,9 +9,6 @@ export default {
link: {type: 'doc', id: 'stage-01-skills-adoption'},
collapsed: true,
items: [
{type: 'doc', id: 'skills-governance', label: 'Governance'},
{type: 'doc', id: 'skills-quality', label: 'Quality'},
{type: 'doc', id: 'skills-adoption', label: 'Adoption'},
{
type: 'category', label: 'Measurement', collapsed: true,
link: {type: 'doc', id: 'measurement/index'},
@@ -36,6 +33,10 @@ export default {
'measurement/synthetic-example',
],
},
{type: 'doc', id: 'baseline', label: 'Baseline'},
{type: 'doc', id: 'skills-governance', label: 'Governance'},
{type: 'doc', id: 'skills-quality', label: 'Quality'},
{type: 'doc', id: 'skills-adoption', label: 'Adoption'},
{type: 'doc', id: 'skills-maintenance', label: 'Maintenance'},
],
},
+1 -1
View File
@@ -12,7 +12,7 @@ export default function ArchifyDiagram({name, title, compact = false, story = fa
const headingId = useId();
const [expanded, setExpanded] = useState(false);
const [narrowRoadmap, setNarrowRoadmap] = useState(false);
const skillsStory = /^strategy-(governance|quality|adoption|measurement|maintenance)$/.test(name);
const skillsStory = /^strategy-(governance|quality|adoption|measurement|baseline|maintenance)$/.test(name);
useEffect(() => {
if (!name.startsWith('strategy-roadmap') && !skillsStory) return;
const media = window.matchMedia(skillsStory ? '(max-width: 1100px)' : '(max-width: 999px)');
+2 -1
View File
@@ -157,7 +157,8 @@ a:focus-visible, button:focus-visible {outline: 3px solid #b88719; outline-offse
.archify-panel--skills {--skills-wide: 2000 / 1200; --skills-narrow: 880 / 2900;}
.archify-panel--skills[data-diagram="strategy-governance"] {--skills-wide: 1760 / 1550;}
.archify-panel--skills[data-diagram="strategy-adoption"] {--skills-wide: 2040 / 1300; --skills-narrow: 880 / 2200;}
.archify-panel--skills[data-diagram="strategy-measurement"] {--skills-wide: 2400 / 1280; --skills-narrow: 880 / 3900;}
.archify-panel--skills[data-diagram="strategy-measurement"] {--skills-wide: 2400 / 1280; --skills-narrow: 880 / 2600;}
.archify-panel--skills[data-diagram="strategy-baseline"] {--skills-wide: 2400 / 1280; --skills-narrow: 880 / 2200;}
.archify-panel--skills[data-diagram="strategy-maintenance"] {--skills-wide: 2630 / 1480; --skills-narrow: 880 / 3250;}
.archify-panel--story.archify-panel--skills > .story-desktop {aspect-ratio: var(--skills-wide); height: auto;}
@media (max-width: 1100px) {