Skip to content

DangQuangSE/team-development-skills / .agents/skills/code-review

code-review

Verified

Always use this skill before claiming any work is done, fixed, passing, or complete — even if it seems obvious. Also use when receiving code review feedback from any source (human or automated), when finishing a task or major feature, before committing or creating a PR, or when about to express satisfaction with work. Covers three practices: receiving feedback with technical rigor (no performative agreement), triggering code review via /code-review command or cook/fix pipelines, and verification gates (run the command, read the output, then make the claim). Never skip — the cost of false completion claims is higher than the cost of verifying. References: code-review-reception.md, requesting-code-review.md, verification-before-completion.md.

Code Review

Apply code review practices with technical rigor, evidence-based claims, and verification over performative responses.

References

PracticeWhen to loadFile
Receiving feedbackUnclear/questionable feedback, conflict with reviewerreferences/code-review-reception.md
Requesting reviewAfter each task, before merge — use /code-reviewreferences/requesting-code-review.md
Verification gatesBefore any completion/success claimreferences/verification-before-completion.md

Overview

Code review requires three distinct practices:

  1. Receiving feedback — Technical evaluation over performative agreement
  2. Requesting reviews — Systematic review via code-reviewer subagent
  3. Verification gates — Evidence before any completion claims

Core Principle

Technical correctness over social comfort. Verify before implementing. Ask before assuming. Evidence before claims.

When to Use This Skill

Receiving Feedback

Trigger when:

  • Receiving code review comments from any source
  • Feedback seems unclear or technically questionable
  • Multiple review items need prioritization
  • Suggestion conflicts with existing decisions

Requesting Review

Trigger when:

  • Completing tasks in subagent-driven development (after EACH task)
  • Finishing major features or refactors
  • Before merging to main branch
  • After fixing complex bugs

Use /code-review (local) or /code-review <PR> (PR mode). ck:cook, ck:quality, and ck:test remain separate gates; run final code review after their required artifacts are current.

Verification Gates

Trigger when:

  • About to claim tests pass, build succeeds, or work is complete
  • Before committing, pushing, or creating PRs
  • Moving to next task
  • Any statement suggesting success/completion

Quick Decision Tree

SITUATION?
│
├─ Received feedback
│  ├─ Unclear items? → STOP, ask for clarification first
│  ├─ From human partner? → Understand, then implement
│  └─ From external reviewer? → Verify technically before implementing
│
├─ Completed work
│  ├─ Major feature/task? → Run /code-review (or it's automatic in cook/fix)
│  └─ Before merge? → Run /code-review <PR-number>
│
└─ About to claim status
   ├─ Have fresh verification? → State claim WITH evidence
   └─ No fresh verification? → RUN verification command first

Receiving Feedback Protocol

Response Pattern

READ → UNDERSTAND → VERIFY → EVALUATE → RESPOND → IMPLEMENT

Key Rules

  • No performative agreement: "You're absolutely right!", "Great point!", "Thanks for [anything]"
  • No implementation before verification
  • Restate requirement, ask questions, push back with technical reasoning, or just start working
  • If unclear: STOP and ask for clarification on ALL unclear items first
  • YAGNI check: search for usage before implementing suggested features

Full protocol: references/code-review-reception.md

Verification Gates Protocol

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

Gate Function

IDENTIFY command → RUN full command → READ output → VERIFY confirms claim → THEN claim

Red Flags — STOP

Using "should"/"probably"/"seems to", expressing satisfaction before verification, committing without verification, trusting agent reports.

Full protocol: references/verification-before-completion.md

Bottom Line

  1. Technical rigor over social performance — no performative agreement
  2. Systematic review processes — use code-reviewer subagent
  3. Evidence before claims — verification gates always

Verify. Question. Then implement. Evidence. Then claim.

writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 319kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall