agentleFS
Sign inStart free
illinigirlillinigirl/claude-code-toolkit/skills/public-ready/SKILL.md

public-ready

Skill0 starsChanged 5 months agoMITView on GitHub

Audit a repo for public release and, on approval, publish it. Scans tracked files for secrets, PII, and interview/hiring/portfolio framing; verifies tests + lint are green; checks LICENSE / README / .gitignore / CI; then (only when you say so) runs gh repo create --public --push. Use when the user wants to make a repo public, open-source it, ship it, or run a pre-publish / public-readiness check.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run the publish-readiness audit, fix or surface findings, then publish only on explicit approval.

    line 10
  2. Distinctive:

    Run the bundled scanner over the repo's *tracked* files and read its output:

    line 19
  3. Very specific:

    No secrets, tokens, .env, or personal data in tracked files — ever.

    line 59
  4. Distinctive:

    Prefer fixing in place; surface anything you can't safely auto-fix rather than publishing around it.

    line 60
  5. Distinctive:

    If something you find contradicts how the repo was described, stop and say so.

    line 62

≈ “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

Make a repo public-ready

Run the publish-readiness audit, fix or surface findings, then publish only on explicit approval. Publishing is outward-facing and hard to undo — never run the gh repo create / push step without a clear "yes".

1. Scope the target

Target repo = $1 (a path) or the current working directory. Confirm it's a git repo before proceeding.

2. Run the deterministic scan

Run the bundled scanner over the repo's tracked files and read its output:

bash "${CLAUDE_SKILL_DIR}/audit.sh" "$1"

It flags: secrets/keys/.env/state files tracked in git, high-entropy token patterns, personal email addresses, and interview/hiring/portfolio framing, plus a hygiene checklist (LICENSE / README / .gitignore / CI / clean tree). Treat any flag as a blocker until resolved.

3. Verify green (language-aware)

Detect the project type and run what applies — report real output, never claim green without running:

  • Python: ruff check . and python -m pytest -q (or the project's configured commands).
  • Node: the configured lint + npm test.
  • Other: the project's documented test/lint commands.

4. Hygiene + framing review

  • LICENSE present? README accurate (no stale scaffold/boilerplate text)?
  • .gitignore covers state, secrets, and build artifacts?
  • A CI workflow under .github/workflows/? Offer to add a minimal one if missing.
  • Working tree clean — is everything intended actually committed?
  • Framing: strip interview / hiring / portfolio / "for reviewers" language from anything public. This is a hard rule; suggest neutral wording ("Try it yourself").

5. Report, then publish on approval

Summarize: blockers found (and fixed), green status, hygiene gaps. Offer to fix small issues in place. Then, only if the user explicitly approves, publish — confirming the authenticated account first so it lands in the right place:

gh api user --jq .login          # confirm the target account
gh repo create <name> --public --source . --remote origin --push --description "<one-liner>"

For a private-first workflow, use --private and tell the user how to flip it public later. After pushing, confirm CI is green (gh run list).

Notes

  • No secrets, tokens, .env, or personal data in tracked files — ever.
  • Prefer fixing in place; surface anything you can't safely auto-fix rather than publishing around it.
  • If something you find contradicts how the repo was described, stop and say so.

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