Defame1297
672fd25890
Rewrote the skill authoring factory skill from scratch against the agentskills.io specification. Renamed write-skill → skill-write (name now matches directory per spec). skill-write: - Full scaffold via new-skill.sh (annotated templates for SKILL.md, README.md, scripts/, references/, assets/) - validate.sh checks all spec constraints deterministically (name format/length, description length, placeholder detection, line count, script rules) - SKILL.md body includes description rules, body discipline, patterns, and scripts guidance with "why" rationale throughout - Templates usable standalone by agents and humans skill-audit: - Structural validation (via validate.sh) + seven qualitative dimensions - Produces PASS/FAIL/SUGGESTION punch list with per-FAIL fix proposals - Report-only: does not apply fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
references/
Additional documentation agents load on demand. Files here extend SKILL.md without bloating its core context.
When to add a reference file
Move content here when SKILL.md is approaching 500 lines, or when a topic is only relevant in specific circumstances (error handling, edge cases, domain-specific sub-procedures).
How to reference from SKILL.md
Load conditionally — tell the agent exactly when to read each file:
If the API returns a non-200 status, read `references/api-errors.md`.
Avoid generic "see references/ for details" — the agent loads context on demand, so give it a precise trigger condition.
File conventions
- One topic per file — focused files mean less unnecessary context loaded
- Kebab-case filenames (e.g.
api-errors.md,output-formats.md) - Keep files under 200 lines where possible
If no reference files are needed
Delete this README and the references/ directory entirely.