agentleFS
Sign inStart free
berntpoppberntpopp/gencc-link/.claude/skills/code-quality-review/SKILL.md

code-quality-review

Skill0 starsChanged 4 months agoMITView on GitHub

Use when reviewing a diff, PR, or change set for correctness and quality before merge or handoff. For a deep security-only pass, use security-review instead.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Follow AGENTS.md first. Run the mechanical pass first (make ci-local, and /code-review if available).

    line 8

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

Code-Quality Review

Follow AGENTS.md first. Run the mechanical pass first (make ci-local, and /code-review if available); this skill is the judgment layer on top.

Scan order (security-first)

Review in this order — don't rush past a step to get to style nits:

  1. Secrets — hardcoded tokens/keys/URLs that belong in runtime env.
  2. Input validation — untrusted args validated against Pydantic schemas/ranges before use.
  3. Trust boundary — no caller-token passthrough to upstreams; fixed upstream host (no SSRF); Origin validation intact. (For the full boundary review, use security-review.)
  4. Dependencies — new deps pinned in uv.lock, mainstream, no post-install hooks.
  5. Correctness — logic, error handling, edge cases, response-envelope shape (success + flat error_code/message/_meta).
  6. Efficiency — N+1 upstream calls, unbounded loops/inputs, missing size caps.
  7. Style / fleet rules — modern typing (X | None), the per-file line budget (scripts/check_file_size.py), thin handlers, no PII in logs.

Report each finding

Group by file. For each: severity (critical = bug/security · warning = fix before merge · suggestion = optional), the issue, and a concrete fix. Anchor to file:line.

Common mistakes

  • Reporting style nits while missing a token-passthrough or SSRF regression.
  • Vague findings ("improve error handling") with no location or fix.
  • Approving a diff that grows a module past the LOC budget with no split.

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.

Reviews can't be read right now.

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