agentleFS
Sign inStart free
fiedlrobfiedlrob/agent-skills/skills/example-skill/SKILL.md

example-skill

Skill0 starsChanged 5 months agoMITView on GitHub

This is the tool-agnostic core for the example skill. Keep reusable workflow instructions here, and put tool-specific discovery metadata in adapter files under adapters/. example-skill A reference skill that demonstrates the structure, sections, and writing style expected of skills in this repository. Use it as a starting template when authoring a new skill. - You are creating a new skill and want a known-good layout to copy. - You want a concrete example of how the sections in CONTRIBUTING.md map…

50 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use handoff and code-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 37 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When an existing skill already covers your task.

    line 27
  2. Very specific:

    Write the Required workflow as ordered, concrete steps the agent can follow without guessing.

    line 35
  3. Very specific:

    Update adapters/codex/SKILL.md and adapters/claude/SKILL.md with the loader metadata and short entrypoint text for those tools.

    line 37
  4. Very specific:

    Add Safety notes for any destructive, external, or irreversible action.

    line 39
  5. Very specific:

    Delete references/ or scripts/ directories if your skill does not need them.

    line 40
  6. Distinctive:

    When adapting it, mark any step that deletes data, pushes to a remote, or calls an external API, and require confirmation before that step …

    line 46

“Common” is measured: kept by at least 6 in 10 of the 37 edited versions of this file we could read. “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

SKILL

This is the tool-agnostic core for the example skill. Keep reusable workflow instructions here, and put tool-specific discovery metadata in adapter files under adapters/.

Name

example-skill

Description

A reference skill that demonstrates the structure, sections, and writing style expected of skills in this repository. Use it as a starting template when authoring a new skill.

When to use

  • You are creating a new skill and want a known-good layout to copy.
  • You want a concrete example of how the sections in CONTRIBUTING.md map onto a real SKILL.md.

When not to use

  • For real agent work. This skill performs no task on its own; it only illustrates structure.
  • When an existing skill already covers your task. Improve that skill instead of duplicating it.

Required workflow

  1. Copy the skills/example-skill/ directory to skills/<your-skill-name>/.
  2. Replace the Name and Description with your skill's specifics.
  3. Fill in When to use and When not to use with concrete trigger rules.
  4. Write the Required workflow as ordered, concrete steps the agent can follow without guessing.
  5. Update adapters/codex/SKILL.md and adapters/claude/SKILL.md with the loader metadata and short entrypoint text for those tools.
  6. Add Safety notes for any destructive, external, or irreversible action.
  7. Delete references/ or scripts/ directories if your skill does not need them. Keep both adapter directories.

Safety notes

  • This skill does not run commands, write files, or contact external services.
  • When adapting it, mark any step that deletes data, pushes to a remote, or calls an external API, and require confirmation before that step runs.

Optional examples

To scaffold a new skill from this template:

cp -r skills/example-skill skills/my-new-skill

See references/optional-reference.md for a checklist, and scripts/optional-helper.sh for a small validation helper. The Codex and Claude adapter examples live under adapters/.

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