skill authoring

Documentation Community

Skill notes

Goal

Transform noisy step traces or draft markdown into a strict SKILL.md that is: deterministic to execute explicit about when to trigger explicit about failure handling valid against strict skill validation rules

Required Structure

Frontmatter: name (kebab-case, matches directory) description (one concise sentence) optional metadata JSON for triggers/requirements Body sections:

Refinement Rules

Replace fragile coordinates with semantic UI targets whenever possible. Keep each procedure step one atomic action. Add at least one fallback path for common blockers (auth wall, empty state, loading timeout). If personal data is required, add request_human_auth guidance before UI actions. Keep language concise and executable.

Validation Gate

Before promotion: Run strict skill validation. If validation fails, keep as draft and report issues. Promote only validated output.

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Documentation
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@pockebot · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
Unspecified (assume cross-platform)
Runtime requirements
No explicit requirements detected
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Author source file SKILL.md

# skill-authoring

Use this skill when converting a rough draft into a production-ready skill document.

## Goal

Transform noisy step traces or draft markdown into a strict `SKILL.md` that is:

1. deterministic to execute
2. explicit about when to trigger
3. explicit about failure handling
4. valid against strict skill validation rules

## Required Structure

1. Frontmatter:
   - `name` (kebab-case, matches directory)
   - `description` (one concise sentence)
   - optional `metadata` JSON for triggers/requirements
2. Body sections:
   - `When To Use`
   - `Preconditions`
   - `Procedure`
   - `Failure Handling`
   - `Completion Criteria`

## Refinement Rules

1. Replace fragile coordinates with semantic UI targets whenever possible.
2. Keep each procedure step one atomic action.
3. Add at least one fallback path for common blockers (auth wall, empty state, loading timeout).
4. If personal data is required, add `request_human_auth` guidance before UI actions.
5. Keep language concise and executable.

## Validation Gate

Before promotion:

1. Run strict skill validation.
2. If validation fails, keep as draft and report issues.
3. Promote only validated output.

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.