oleg-lukasonokandClaude Fable 5
6042272ccc
- 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>
69 lines
2.2 KiB
Markdown
69 lines
2.2 KiB
Markdown
---
|
||
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.
|