Create or improve reusable OSA skills with progressive disclosure, precise selection descriptions, supporting resources, and realistic evaluations. Use when users ask to create, package, test, optimize, or maintain a skill or skill library.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Skill Authoring
Create focused procedural knowledge that improves behavior beyond the base agent.
## Progressive disclosure
1. Keep the name and concise selection description in the always-visible catalog.
2. Put the core workflow in SKILL.md and keep it under 500 lines when practical.
3. Put detailed references, templates, scripts, and assets in supporting directories.
4. Tell the agent exactly when each supporting file should be loaded.
## Procedure
1. Define what the skill enables, when it should be selected, and expected outputs.
2. Inspect adjacent skills to prevent overlap or contradictory ownership.
3. Write a description containing both capability and selection conditions.
4. Explain why the workflow matters instead of relying on excessive rigid language.
5. Use tool names and commands that exist in OSA.
6. Add two or three realistic positive prompts and difficult near-miss prompts.
7. Compare behavior with and without the skill when practical.
8. Revise instructions that create wasted work, ambiguity, or brittle overfitting.
9. Verify discovery from a clean OSA installation and selective loading through `skill_view`.
## Creation rule
…
The line at the top of this page pins the label git:20260816.716d56b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_4m4d6gja2kun2e6j
GET https://markdownregistry.com/api/v1/resolve?ref=miosa-osa/osa/skill-authoring
GET https://markdownregistry.com/api/v1/blob/864c3822f7a861ce9fd55d932a3218e08bd5471fdc8efea7d168150cca3d05fb
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
miosa-osa/osa · examples/skills/meeting-prep/SKILL.md · Research attendees, prepare talking points, and summarize previous interactions before meetings
nyldn/claude-octopus · .claude/skills/skill-authoring/SKILL.md · Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in…
nyldn/claude-octopus · skills/skill-authoring/SKILL.md · Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in…
cbrock84/headcount · plugins/technology/skills/skill-authoring/SKILL.md · Writes and revises agent skills so they trigger at the right moments and give usable instruction when they do. Use this…
athola/claude-night-market · plugins/abstract/skills/skill-authoring/SKILL.md · Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.
