Skills for Real Engineers. Straight from my .agents directory.
structured-code-review
Agent skill fromrohitg00/skillkit
Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR feedback, pull request review, or wants their code checked for bugs, style issues, or vulnerabilities — triggered by phrases like "review my code", "check this PR", "review my changes", "pull request review", or "code feedback".
How to install structured-code-review
npx skills add rohitg00/skillkit# or add only this skill to Claude Code: copy the folder
packages/core/src/methodology/packs/collaboration/structured-review/
# into
~/.claude/skills/structured-review/ (all projects)
.claude/skills/structured-review/ (one project)
1# Structured Code Review23You are performing a structured, multi-stage code review. This methodology ensures thorough review while providing actionable, constructive feedback.45## Core Principle67**Review in stages. Each stage has a specific focus. Don't mix concerns.**89A structured review catches more issues and provides better feedback than an unstructured scan.1011## Review Stages1213### Stage 1: Requirements Compliance1415First, verify the code meets its requirements.1617**Checklist:**18- [ ] Implements stated requirements19- [ ] Handles specified edge cases20- [ ] No scope creep (unexpected additions)21- [ ] No missing functionality2223**Feedback at this stage:**24- "This doesn't appear to handle the case when X is empty"25- "The requirement specified Y, but this implements Z"26- "This adds feature F which wasn't requested - is that intentional?"2728### Stage 2: Correctness2930Next, verify the code works correctly.3132**Checklist:**33- [ ] Logic is sound34- [ ] No obvious bugs35- [ ] Error paths are handled36- [ ] No unfinished code (TODOs without tickets)3738**Feedback at this stage:**39- "This will throw if `user` is null"40- "The loop exits early before processing all items"41- "What happens when the API call fails?"4243### Stage 3: Code Quality4445Then, evaluate code quality and maintainability.4647**Checklist:**48- [ ] Clear naming49- [ ] Reasonable function/method length50- [ ] No unnecessary complexity51- [ ] Follows project conventions52- [ ] Appropriate abstractions5354**Feedback at this stage:**55…
Excerpt shown under the repository's Apache-2.0 license.
More skills in skillkit
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
