skill-authoring
Create or revise a compact Agent Skill or plugin package with precise trigger boundaries, progressive disclosure, provider adapters, provenance, deterministic helpers, and positive and negative evals. Use for skill or plugin maintenance. Do not publish broad untested prompts, duplicate provider schemas, copy third-party text, or add privileged hooks and MCP services without an explicit threat model.
Pinned to revision 3963fcd97933, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/skill-authoring/SKILL.md
- skills/skill-authoring/agents/openai.yaml
- skills/skill-authoring/references/release-checklist.md
Every link opens the file at its source, pinned to the revision this page describes.