agentleFS
Sign inStart free
nassaj2011nassaj2011/claude-skills-for-chatgpt/skills/skill-authoring-toolkit/SKILL.md

skill-authoring-toolkit

Skill0 starsChanged 24 days agoMITView on GitHub

Create and maintain reusable Agent Skills in SKILL.md format, with precise triggers, testable workflows, safe tool permissions and validation.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write a concise frontmatter name (lowercase kebab-case) and description explaining *when* to use the skill, plus relevant exclusions.

    line 8
  2. Very specific:

    Place essential decision rules, required evidence, safety boundaries and expected outputs in SKILL.md.

    line 9
  3. Distinctive:

    Add references/ only for substantial task-specific details and scripts/ only for deterministic repeatable work.

    line 10
  4. Distinctive:

    Create example triggers and counterexamples to test routing.

    line 12
  5. Distinctive:

    Run the repository validator and tests.

    line 13

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Author reliable Agent Skills

  1. Identify one specialized recurring task and examples where existing agent instructions underperform. Avoid a general-purpose catchall skill.
  2. Write a concise frontmatter name (lowercase kebab-case) and description explaining when to use the skill, plus relevant exclusions.
  3. Place essential decision rules, required evidence, safety boundaries and expected outputs in SKILL.md. Keep instructions short enough to be selectively loaded.
  4. Add references/ only for substantial task-specific details and scripts/ only for deterministic repeatable work. No placeholder dependencies.
  5. Separate planning from execution; never use a skill to expand user authorization or bypass platform restrictions.
  6. Create example triggers and counterexamples to test routing; include a success/failure rubric and compare against a baseline without the skill.
  7. Run the repository validator and tests; update documentation and examples. Review any third-party borrowed content and its specific license.

Output: installable folder, trigger cases, expected outputs, validation evidence and update notes. A SKILL.md file cannot confer permissions, network access, native ChatGPT installation or tool availability.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free