plipowczanSkillcode-review
plipowczan/claude-piv-skeleton/.claude/skills/code-review/SKILL.md
Auto-activates during code reviews
Claude skills and agent skills
Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Best matches · from page 13Worked for most · soon
plipowczanSkill
ProviderProtocolSkillcode-review
ProviderProtocol/ai/.claude/skills/code-review/SKILL.md
Comprehensive multi-agent code review with parallel analysis. Use for thorough code reviews, finding bugs, checking regressions, or getting alternative implementation perspectives.
s1lver091Skillcode-review
s1lver091/pi-agent-config/skills/code-review/SKILL.md
Review code changes for bugs, security vulnerabilities, performance issues, and maintainability. Use when asked to review code, a PR, a diff, or recent changes.
saitarrunSkillcode-review
saitarrun/Devforge-ai/skills/code-review/SKILL.md
This skill should be used when the user mentions keywords related to code-review.
sdageltcSkillcode-review
sdageltc/letitloop/.github/skills/code-review/SKILL.md
Comprehensive code review agent skill for letitloop pull requests and diffs. Enforces deterministic contract contracts, typed exceptions, zero blind except Exception blocks, Bandit SAST security checks, and triple-OS test verification.
SebaBolerSkillcode-review
SebaBoler/vanguard/skills/code-review/SKILL.md
Use when reviewing a code change or diff for correctness, security, missing tests, and convention violations before opening or approving a PR. Review independently and adversarially, then fix high-confidence issues.
TerfynSkillcode-review
Terfyn/terfyn/.cursor/skills/code-review/SKILL.md
Review pull requests or diffs for defects, security, and project conventions. Use when reviewing a PR, examining a diff, or when the user asks for a code review.
thejordanleopoldSkillcode-review
thejordanleopold/claude-code-skills-distilled/code-review/SKILL.md
Use when reviewing code, giving feedback on a PR, auditing a codebase for quality problems, or evaluating code before submitting. Triggers: \"review this\", \"code review\", \"review this PR\", \"give me feedback on this code\", \"audit this code\", \"what's wrong with this\", \"is this implementation good\", \"critique this\", \"check this for issues\".
TTflyskySkillcode-review
TTflysky/sirenhuisuo/skills/code-review/SKILL.md
按严重程度检查代码缺陷、回归风险、边界条件和测试缺口。
xiaolongnkSkillcode-review
xiaolongnk/SuperHarness/skills/code-review/SKILL.md
Reviews a change against its plan — checks scope match, hunts correctness bugs, and reports findings by severity.
xiehuan123Skillcode-review
xiehuan123/coding-coach/skills/code-review/SKILL.md
评审：对照代码规范和需求文档两个维度，审查最近改动（某个提交/分支以来的差异），并行子代理分别评审后并排汇报。Review changes since a fixed point along Standards and Spec axes.
ADT109119Skillcode-review
ADT109119/code-review/SKILL.md
通用平行化 Code Review Agent。支持多文件/多目录并行审查、多维度分析（安全/性能/可读性/架构/测试）、可配置严重等级、结构化报告生成。触发词：code review, 代码审查, 评审代码, PR review, 检视, lint, 静态分析
bhaumikmaanSkillcode-review
bhaumikmaan/claude-code-master-skills/skills/code-review/SKILL.md
Three-pass code review covering reuse, quality, and efficiency. Starts from git diff and produces actionable findings with a consolidation step. Use when reviewing code changes, after implementation, when asked to simplify or clean up code, or before merging.
evelan-deSkillcode-review
evelan-de/claude-code-plugins/skills/code-review/SKILL.md
Evelan's code review. ALWAYS use this skill (never the built-in code-review) whenever the user asks for a code review in any wording: \"code review\", \"review this\", \"review the PR\", \"review the branch\", \"review my changes\", \"review since X\", German \"Code Review\", \"reviewe das\", \"mach ein Review\", \"schau dir den Diff an\". Reviews the changes since a fixed point along three axes: Standards, Spec, and Codex (cross-model, when the Codex CLI is installed).
FirzusSkillcode-review
Firzus/agent-skills/skills/engineering/code-review/SKILL.md
Review a scoped diff against requirements, project standards, and correctness using independent read-only reviewers. Use for branch, PR, or uncommitted-change review, and implementation review checkpoints.
francogalfreSkillcode-review
francogalfre/skills/code-review/SKILL.md
Reviews code for bugs, security vulnerabilities, performance issues, and readability problems. Use when the user says "review this code", "check my code", "what's wrong with this", "code review", "audit this file", or pastes code and asks for feedback. Works with any language but optimized for TypeScript, JavaScript, React, and Node.js.
fworks-techSkillcode-review
fworks-tech/agenthood/skills/code-review/SKILL.md
Deprecated alias for the-reviewer. Do not select directly; load skills/the-reviewer/SKILL.md instead.
gener8vSkillcode-review
gener8v/gener8v.claude-skills/skills/code-review/SKILL.md
Review one delivered ticket against the pipeline: acceptance criteria, requirement coverage, constraints, architecture decisions and @spec annotations, producing traceability tables, findings and a verdict. Use after a delivery, in parallel with quality-review and security-review, when asked to 'review TICKET-003', 'check the delivery against the spec' or 'did we build what the ticket asked for'. Not for readability or tests on their own (quality-review), vulnerabilities (security-review), or code with no ticket behind it (quality-review on the files).
hoangNguyenAngelhackSkillcode-review
hoangNguyenAngelhack/ai-agent-setup/.agents/skills/code-review/SKILL.md
Perform five-axis code reviews covering correctness, readability, architecture, security, and performance. Use when reviewing PRs, code changes, or evaluating code quality.
howar31Skillreview-code
howar31/magi-workflow/skills/review-code/SKILL.md
Review the current git diff and produce DRIFT.md when a sprint context exists. **Mandatory before /magi:commit in sprint mode** — DRIFT.md is required input for the commit step's drift backfill flow. Default behaviour is multi-CLI MAGI cross-review (orchestrator + magi-consensus). Use --single to fall back to a single Opus reviewer (the magi-reviewer subagent) — saves tokens but loses cross-validation. Supports --magi <mode> override and --reviewers override. Never auto-fixes; always presents findings for the user to decide.
About skills
What is a Claude skill?
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.