agentsclimarketplace

Code review

Skill IcodeNet/agent-skills/skills/code-review

40 portable full-SDLC agent skills for Claude Code, Cursor, Codex, and GitHub Copilot — deep-work autonomy, contract-guard for external interfaces, TDD, code review, PR babysitting. Install: npx github:IcodeNet/agent-skills

Install
npx -y skills add IcodeNet/agent-skills --skill code-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 26 days oldThe repository was created 26 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Multi-axis review of diffs before merge. Use when reviewing a PR, branch, or local changes; when asking if a change is safe; or before marking code tasks complete. Do not use for CI babysitting loops or live incidents.

SKILL.md

1.7 KB, as published. Nobody here has run it

Code Review

Review for correctness, readability, architecture fit, security, and performance. Approve when the change improves code health — not only when it is perfect.

Workflow

  1. Context — intent, acceptance criteria, git diff <base>...HEAD (three-dot).
  2. Tests first — do tests exist, assert behavior, cover the risk?
  3. Five axes — correctness, readability, architecture, security, performance. Details: references/review-axes.md.
  4. Contract surface — does the diff touch anything consumed outside this repo (public APIs, endpoints, schemas, events, package exports)? If yes, apply the contract-guard skill: classify the change, require a compatibility strategy for breaking changes, demand contract evidence. An unflagged breaking change is always Critical:.
  5. Scope — ticket-sized? refactor mixed with feature? secrets? verification story present?
  6. Severity labels — Critical: / required / Nit: / Optional: / FYI.
  7. Verdict — Approve | Request changes. List blockers only.

Constraints

  • Do not rubber-stamp. Do not bury Critical under nits.
  • Prefer structural remedies (extract, reuse canonical helper, explicit types) over vague “make it cleaner”.
  • Split advice: large mixed refactor+feature PRs should be split when review needs unrelated context.

Verification

  • Intent understood
  • Tests reviewed for the change
  • Findings severity-labeled
  • Verdict + required follow-ups stated

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.