Add skill-manager skill (migrated from skill-creator) with deploy action

- Skill content moved from ~/.agents/skills/skill-creator, renamed to skill-manager - New deploy CLI action: installs any skill via absolute-path symlinks (or copies) into $HOME/.agents/skills, $HOME/.claude/skills and $HOME/.cline/skills - Taskfile + shell module wrappers (task deploy / cli:deploy) - SKILL.md: deploy docs, origin-repository/origin-path metadata Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-23 22:32:42 +03:00
parent cc30987dd2
commit 6042272ccc
62 changed files with 3474 additions and 1 deletions
@@ -0,0 +1,68 @@
+---
+name: skill-name
+description: >
+  [What the skill does — be specific about capabilities].
+  Use this skill when [specific trigger conditions — user intent, task type, domain],
+  even if the user doesn't explicitly mention [domain keywords].
+license: Proprietary
+metadata:
+  author: workspace-swiss-knife
+  version: "1.0"
+# compatibility: Designed for Cline, Claude Code, GitHub Copilot, OpenAI Codex, and other compatible agents (uncomment if needed)
+# allowed-tools: Bash Read Write (uncomment if needed)
+---
+
+# [Skill Title]
+
+[One-sentence summary of what this skill does and for whom.]
+
+## Overview
+
+[2–3 sentences of context. What problem does this skill solve? What domain does it operate in?]
+
+## Prerequisites
+
+[List any tools, packages, env vars, or conditions required. Remove section if none.]
+
+- Requires: `tool-name`
+- Environment: `ENV_VAR=value`
+
+## Available scripts
+
+[List scripts if any. Remove section if no scripts/ directory.
+Convention: Taskfile.yml is always required when scripts/ exists.
+Shell scripts → scripts/.scripts/<domain>/api/ (Taskfile → api → lib modules)
+Other languages → scripts/src/]
+
+Run via Taskfile (preferred):
+```bash
+cd scripts && task <action> -- --flag=value
+```
+
+- **`scripts/Taskfile.yml`** — Entry point; maps tasks to `.scripts/<domain>/` modules
+- **`scripts/.scripts/<domain>/api/<action>--<sub>.sh`** — [what it does]
+- **`scripts/src/process.py`** — [what it does]
+
+## Workflow
+
+[Step-by-step instructions. Be prescriptive for fragile steps; flexible for steps with valid alternatives.]
+
+1. [Step one]
+2. [Step two]
+3. [Step three]
+
+## Gotchas
+
+[Non-obvious facts the agent will get wrong without being told. This is the highest-value section.
+Delete this section if you have no gotchas yet — add them as you discover them.]
+
+- [Specific fact that defies reasonable assumptions]
+- [Another non-obvious environment-specific detail]
+
+## References
+
+[Tell the agent when to load each reference file. Use conditional loading, not generic "see references/".
+Delete this section if no references/ directory.]
+
+- Read `references/api-errors.md` if the API returns a non-200 status code.
+- Read `references/schema.md` before writing any database queries.
@@ -0,0 +1,46 @@
+{
+  "_comment": "Eval suite for skill output quality and trigger testing. See references/description-optimization.md for the full optimization loop.",
+  "skill_name": "my-skill",
+  "trigger_queries": {
+    "_comment": "~20 queries split 60/40 into train and validation sets. Each has should_trigger: true/false.",
+    "train": [
+      { "query": "I have a CSV of monthly sales data in ~/data/q4_results.csv — can you find the top 3 months by revenue?", "should_trigger": true },
+      { "query": "my boss wants a chart from this data file", "should_trigger": true },
+      { "query": "can you analyze this spreadsheet and tell me which rows have missing values?", "should_trigger": true },
+      { "query": "whats the quickest way to convert this json file to yaml", "should_trigger": false },
+      { "query": "write a fibonacci function in python", "should_trigger": false },
+      { "query": "can you write a python script that reads a csv and uploads each row to postgres", "should_trigger": false }
+    ],
+    "validation": [
+      { "query": "hey can you clean up this csv and remove duplicates?", "should_trigger": true },
+      { "query": "I need to update the formulas in my Excel budget spreadsheet", "should_trigger": false }
+    ]
+  },
+  "output_evals": {
+    "_comment": "Test cases for evaluating skill output quality. Store input files in evals/files/.",
+    "evals": [
+      {
+        "id": 1,
+        "prompt": "I have a CSV of monthly sales data in data/sales_2025.csv. Can you find the top 3 months by revenue and make a bar chart?",
+        "expected_output": "A bar chart image showing the top 3 months by revenue, with labeled axes and values.",
+        "files": ["evals/files/sales_2025.csv"],
+        "assertions": [
+          "The output includes a bar chart image file",
+          "The chart shows exactly 3 months",
+          "Both axes are labeled",
+          "The chart title or caption mentions revenue"
+        ]
+      },
+      {
+        "id": 2,
+        "prompt": "there's a csv in my downloads called customers.csv, some rows have missing emails — can you clean it up and tell me how many were missing?",
+        "expected_output": "A cleaned CSV with missing emails handled, plus a count of how many were missing.",
+        "files": ["evals/files/customers.csv"],
+        "assertions": [
+          "Output includes a cleaned CSV file",
+          "Output states the count of rows with missing emails"
+        ]
+      }
+    ]
+  }
+}