agentleFS
Sign inStart free
iansteitz1-engiansteitz1-eng/aria-skills/aria-skill-test/SKILL.md

aria-skill-test

Skill0 starsChanged 2 months agoApache-2.0View on GitHub

Regression harness for the aria-skills repo. Runs every shipped skill in dry-run mode + asserts clean output (no traceback, no credential leaks, valid SKILL.md frontmatter, README.md present). Text report by default; --junit-xml flag for CI integration. Use when the user says "test the skills", "regression check", "before push", "run the test harness", or any time before opening a PR or pushing to main.

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:

    Before pushing changes to the public repo

    line 12
  2. Very specific:

    After running aria-skill-template to confirm the generated stub passes

    line 14
  3. Distinctive:

    After editing any skill script — quick sanity check

    line 15
  4. Distinctive:

    No Python traceback in stderr

    line 26
  5. Distinctive:

    No credential leak patterns in output (Anthropic / Stripe / Resend / Twilio / Cloudflare / EL / AWS / GitHub PAT)

    line 27

≈ “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

aria-skill-test

Regression harness. Pythonic + zero-dependency. Tests structural correctness across every skill in the repo without making any real API calls.

When to use

  • Before pushing changes to the public repo
  • In CI on every PR (use --junit-xml flag)
  • After running aria-skill-template to confirm the generated stub passes
  • After editing any skill script — quick sanity check

What gets checked

Per skill directory:

  • SKILL.md frontmatter parses (YAML between --- markers)
  • name field in frontmatter matches directory name
  • description field is 40-600 chars
  • README.md exists
  • Executable script found (snake_case or kebab-case .py / .sh)
  • Dry-run exits 0 (clean) or 2 (needs creds with clear FATAL message)
  • No Python traceback in stderr
  • No credential leak patterns in output (Anthropic / Stripe / Resend / Twilio / Cloudflare / EL / AWS / GitHub PAT)

CLI

python3 aria_skill_test.py                              # all skills
python3 aria_skill_test.py --skill <name>               # one skill
python3 aria_skill_test.py --skip <name> --skip <name>  # exclude
python3 aria_skill_test.py --junit-xml results.xml      # CI mode
python3 aria_skill_test.py --repo-root /path/to/repo    # alternate

See also

  • BUILDER_GUIDE.md — the patterns enforced
  • aria-skill-template — generator paired with this harness

License

Apache 2.0

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