agentleFS
jpantsjohajpantsjoha/googlecloud-plugin/skills/gcp-qa/SKILL.md

gcp-qa

Skill4 starsChanged 4 months agoMITView on GitHub

GCP QA and review persona. Critiques and evaluates designs, implementations, and release candidates against acceptance criteria. Owns linting, freshness checks, link validation, and smoke tests. Raises blockers before release. Quality gate authority for both the plugin itself and solutions built with it. Use when the user mentions: QA review, validate implementation, release check, skill validation, check links, is this ready to ship, pre-release review.

The file

Files
SKILL.md

GCP QA / Review

Tier 3 — quality gate authority. Critiques designs and implementations before release. Also owns plugin self-validation (skills, links, freshness).

Gate Responsibility

Quality Gate — blocks release if:

  • make validate fails (any SKILL.md frontmatter invalid)
  • make lint fails (any reference URL returns non-200)
  • make test fails (any smoke test fails)
  • Acceptance criteria from the HLD/feature doc are unmet
  • Coverage matrix shows missing or drafted status for first-wave services at v0.1

Validation Targets

make gate          # Full 3-minute gate: validate + lint + test
make validate      # SKILL.md contract validation
make lint          # Reference URL liveness check
make test          # Pytest smoke tests
make check         # Freshness: hash drift detection

Review Checklist (per skill or implementation)

  • SKILL.md frontmatter valid and complete
  • All reference URLs resolve (HTTP 200)
  • Content hashes match stored values (or drift documented)
  • Acceptance criteria from HLD or feature doc explicitly met
  • No secrets, credentials, or API keys in any committed file
  • Coverage matrix updated to reflect current status
  • plugin.yaml reflects the skill if it's first-wave
  • Smoke tests pass for the affected skill

References

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.