helderberto/agent-skills

code-review

Review a GitHub PR for bugs, security, performance, and code quality.

ソースを見る

使い方

  1. インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
  2. 必要なツール、認証情報、対応環境を原文で確認します。
  3. 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/helderberto/agent-skills --skill code-review

開始前の確認

  • 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
  • スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文

見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。

Review Pull Request

Mode: $ARGUMENTS — BUGS, SECURITY, or PERFORMANCE narrows the review to that axis; otherwise apply all.

Approval standard

Approve when the change definitely improves overall code health, even if it isn't perfect. Don't block a change because it isn't how you would have written it. If it improves the codebase and follows its conventions, approve.

If the change is too large to review well (~1000+ lines), asking the author to split it is a valid outcome. Suggest a strategy: stack (small change, next one based on it), by file group, horizontal (shared code first, then consumers), or vertical (one end-to-end slice per PR).

Review criteria

Review every changed file, not just the latest commit.

  • Correctness: logic bugs, off-by-ones, race conditions, unhandled states, missing error paths
  • Readability: functions > 50 lines, nesting > 2 levels, dead code, unused imports
  • Security: exposed secrets, unvalidated external data
  • Type safety & immutability: any or unjustified assertions; in-place mutation of shared data
  • Patterns: consistent with codebase conventions, no reinvented wheels
  • Performance: unnecessary re-renders, O(n²) where O(n) works
  • Code smells: match the diff against the baseline in smells.md — always judgement calls; the repo's documented style overrides the baseline
  • Dependency upgrades (manifest/lockfile in the diff): one dependency per change — a bulk bump that breaks hides which package did it; verify against the changelog, not the version number; review the lockfile diff (one direct bump pulls dozens of transitive changes); flag hand-edited lockfiles

Output

Group by severity, file:line on every finding, a suggested fix for every Critical:

  • Critical — must fix before merge (bugs, vulnerabilities)
  • Suggestions — improvements worth considering
  • Nit — minor and optional; label true nitpicks as Nit rather than dropping or inflating them
  • FYI — informational
  • Positives — good patterns to call out

One structural problem and ten nits: the structural problem is the review — lead with it. Close with the verdict against the approval standard.

タスクに関連する項目

同じリポジトリから

関連する Skills

すべての Skills
helderberto
コミュニティ

codebase-design

Shared vocabulary for designing deep modules. Use when designing or improving a module's interface, placing a seam, making code more testable, or when another skill needs it. Don't use for codebase-wide audits (/architecture-audit) or UI components (/frontend-ui-engineering).

導入数
1
GitHub Stars
17
更新日
10月19日
helderberto
コミュニティ

debug

Disciplined diagnosis loop for hard bugs and performance regressions. Use when user says "diagnose" or "debug this", or reports something broken, throwing, failing, or slow. Don't use to build a feature or fix an understood bug test-first (/tdd).

導入数
1
GitHub Stars
17
更新日
10月19日
helderberto
コミュニティ

deps-audit

Check dependencies for known vulnerabilities and staleness. Use when asked to "audit dependencies", "check for vulnerabilities", or check dependency health. Don't use for code quality review.

導入数
1
GitHub Stars
17
更新日
10月19日
helderberto
コミュニティ

frontend-ui-engineering

Front-load UI construction decisions — component boundary and prop API, state placement, required states, responsiveness, accessibility. Use when creating or refactoring a component, page, or design-system primitive. Don't use for pure logic (/tdd), throwaway exploration (/prototype), or auditing finished UI (/a11y-audit).

導入数
1
GitHub Stars
17
更新日
10月19日