Skip to content

secondsky/claude-skills / plugins/code-review/skills/code-review

code-review

Unverified

Code review practices with technical rigor and verification gates. Use for receiving feedback, requesting code-reviewer subagent reviews, or preventing false completion claims in pull requests.

Code Review

Guide proper code review practices emphasizing technical rigor, evidence-based claims, and verification over performative responses.

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

Each practice has specific triggers and protocols detailed in reference files.

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
  • External reviewer lacks full context
  • Suggestion conflicts with existing decisions

Reference: references/code-review-reception.md

Requesting Review

Trigger when:

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

Reference: references/requesting-code-review.md

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
  • Expressing satisfaction with work

Reference: references/verification-before-completion.md

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? → Request code-reviewer subagent review
│  └─ Before merge? → Request code-reviewer subagent review
│
└─ 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: grep for usage before implementing suggested "proper" features

Source Handling

  • Human partner: Trusted - implement after understanding, no performative agreement
  • External reviewers: Verify technically correct, check for breakage, push back if wrong

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

Requesting Review Protocol

When to Request

  • After each task in subagent-driven development
  • After major feature completion
  • Before merge to main

Process

  1. Get git SHAs: BASE_SHA=$(git rev-parse HEAD~1) and HEAD_SHA=$(git rev-parse HEAD)
  2. Dispatch code-reviewer subagent via Task tool with: WHAT_WAS_IMPLEMENTED, PLAN_OR_REQUIREMENTS, BASE_SHA, HEAD_SHA, DESCRIPTION
  3. Act on feedback: Fix Critical immediately, Important before proceeding, note Minor for later

Full protocol: references/requesting-code-review.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

Skip any step = lying, not verifying

Requirements

  • Tests pass: Test output shows 0 failures
  • Build succeeds: Build command exit 0
  • Bug fixed: Test original symptom passes
  • Requirements met: Line-by-line checklist verified

Verification Commands

# Tests (prefer bun)
bun test  # or: npm test

# Build
bun run build  # or: npm run build

# Lint
bun run lint  # or: npm run lint

# Type check
bun run typecheck  # or: bunx tsc --noEmit

Red Flags - STOP

Using "should"/"probably"/"seems to", expressing satisfaction before verification, committing without verification, trusting agent reports, ANY wording implying success without running verification

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

Integration with Workflows

  • Subagent-Driven: Review after EACH task, verify before moving to next
  • Pull Requests: Verify tests pass, request code-reviewer review before merge
  • General: Apply verification gates before any status claims, push back on invalid feedback

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.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 463kUpdated Claude CodeCodexVerifiedInstall
discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.Stars: 195kUpdated Claude CodeCodexVerifiedInstall
internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).Stars: 195kUpdated Claude CodeCodexVerifiedInstall