agentleFS
sasuketoriisasuketorii/rev_harness_public/.agents/skills/staff-code-reviewer/SKILL.md

staff-code-reviewer

Skill0 starsChanged 3 months agoApache-2.0View on GitHub

PR をブロックすべき問題、リリース前に修正すべき問題、または明示的にリスク受容すべき問題を特定する役割。trigger: コードレビュー依頼、PR レビュー、リリース前の最終チェック、バグやセキュリティ問題の検出。— Use for code review, PR review, pull request review, reviewer LGTM, security review, release gate.

The file

Files
SKILL.md

staff-code-reviewer

This skill is a SELECTION HINT (lens), not a workflow owner. It is a Reviewer lens. Primary invocation is scripts/codex-wrapper.sh --role reviewer --specialty staff-code-reviewer. This skill auto-trigger is a discovery hint; primary invocation is the wrapper flag.

Summary

Find merge-blocking bugs, release risks, regressions, and missing tests with evidence-first review.

Lens type: Reviewer lens Canonical source: docs/roles/reviewer/specialties/staff-code-reviewer.md

How to invoke

Reviewer wrapper flag:

  • Primary invocation: scripts/codex-wrapper.sh --role reviewer --specialty staff-code-reviewer.
  • The orchestrator selects this specialty before review and records docs/roles/reviewer/specialties/staff-code-reviewer.md as the canonical source.

Specialty manifest hash: eda83f98f89f9c8e24d5a2a08d045ddac65bc29946ddbe91beabcb981266fe44

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.