agentleFS
lbednerlbedner/aegis-stack/.claude/skills/example-skill/SKILL.md

example-skill

Skill144 starsChanged 15 months agoMITView on GitHub

Use when you need the canonical shape of an Aegis Stack skill, or as the copy-from starting point for a new skill. Demonstrates every required section; not a real workflow.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 38 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Use when starting a new skill and you want a known-good skeleton to fill in, or when you need to see how the required sections fit together.

    line 14
  2. Distinctive:

    Do NOT use for real work. This skill performs no framework change.

    line 17
  3. Very specific:

    Write the failing test first (TDD): add the case to the relevant tests/...

    line 34
  4. Distinctive:

    Update docs and i18n keys touched by the change.

    line 39
  5. Distinctive:

    Run the gates below and fix anything red.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 38 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

Example skill

This skill exists to validate and demonstrate the house format defined in .claude/skills/README.md. It is a template, not a real workflow. Copy this directory, rename it, and replace the placeholder content.

When to use

Use when starting a new skill and you want a known-good skeleton to fill in, or when you need to see how the required sections fit together.

Do NOT use for real work. This skill performs no framework change; it only shows the format.

Files that change

Grouped by role. A real skill lists exact repo-relative paths here so an agent opens them without searching. Placeholder example:

  • Registry: aegis/services/registry.py
  • CLI: aegis/cli/<command>.py
  • Template: aegis/templates/copier-aegis-project/{{ project_slug }}/...
  • Tests: tests/<area>/test_<thing>.py
  • Docs: docs/<page>.md
  • i18n: aegis/i18n/en.py

Procedure

  1. Write the failing test first (TDD): add the case to the relevant tests/... file and confirm it fails for the right reason.
  2. Make the change in the registry, CLI, and template files listed above.
  3. Backport any change made in a generated project into its template under aegis/templates/, so it survives the next aegis init.
  4. Update docs and i18n keys touched by the change.
  5. Run the gates below and fix anything red.

Gates

  • make check (lint, typecheck, test) must pass.
  • make test-template must pass when the change touches templates.

Pitfalls

  • Template changes read from the committed git state, not the working tree, so an uncommitted template edit will not show up in a freshly generated project.
  • A vague frontmatter description means the skill never loads, because the description is the only thing an agent reads when deciding to use it.

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.