agentleFS
Sign inStart free
LangChainKnown publisherlangchain-ai/design-agent/.agents/skills/release-check/SKILL.md

release-check

Skill2 starsChanged 14 days agoApache-2.0View on GitHub

Run the release gates before tagging a Design Agent release: hygiene, secrets, licenses, docs, tests, and the human reviews.

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Stop at the first failure and report it.

    line 8

“Common” is measured: kept by at least 6 in 10 of the 12 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

Release check

Stop at the first failure and report it; do not tag or publish. Tagging and publishing are the maintainers' call.

  1. uv sync --all-extras --dev, uv run ruff check ., uv run ruff format --check ., uv run mypy src, uv run pytest -q, uv run pytest -q -m render (Docker), uv run design-agent demo, uv run design-agent skills verify.
  2. DESIGN_AGENT_RELEASE_CHECK=1 uv run pytest -q tests/unit/test_public_hygiene.py: no internal identifiers, licensed fonts, third-party media or build notes; the pre-release paths (docs/prep/, IMPLEMENTATION_PROMPT.md, scripts/import_from_reference.py) are deleted first.
  3. gitleaks detect --no-banner (config .gitleaks.toml) on the full history.
  4. Licenses: fonts/LICENSES.md matches fonts/, licenses/ covers every vendored or bundled component, NOTICE.md is current, and skills-lock.json names each upstream license.
  5. Docs: every link resolves (uv run pytest -q tests/unit/test_docs_links.py), README quick start works from a clean clone, CHANGELOG.md has the release.
  6. uv run mda build from a clean checkout; inspect .mda/build and .mda/__contexthub__.
  7. Human gates (SPEC §24): partner reviews (HyperFrames, Paper), legal review, sample-brand and gallery review. Record who signed off outside the repository.

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