Review & quality
19,040 rows, by stacks then stars
1,766 of these skill files have been read, by 1,273 distinct authors, and what they tell an agent counted. What Review & quality authors agree on, and what they forbid
lc-rezende/AI-Custom-Skills/skills/git-pr-helper Skill
1★ repoDraft pull request titles and bodies based on branch changes. Use when preparing a PR or when the user asks for a PR title/body.
lijinnair/claude-code-skillforge/examples/formatting-commits Skill
1★ repoGenerates a well-structured, conventional Git commit message from the user's staged changes or a description of what they did. Use when the user says "write a commit message", "format my commit", or "help me commit this". Outputs a ready-to-paste commit message following the Conventional Commits specification.
nainishshafi/developer-productivity-skills/.github/skills/github-security-scanner-hook Skill
1★ repoUse when the user asks to "scan for security vulnerabilities", "check for secrets in code", "set up a pre-commit security hook", "install security scanning", "scan staged files for secrets", "check for hardcoded credentials", "run a security scan before commit", "detect leaked API keys", "add a git commit hook for security", "security check before push", "scan for SQL injection", "check for XSS vulnerabilities", "detect injection flaws", or wants to prevent committing security issues to git.
nainishshafi/developer-productivity-skills/.github/skills/python-linter Skill
1★ repoUse when the user asks to "lint python", "run the linter", "fix linting errors", "check python code style", "run ruff", "format python code", "fix imports", "check types", "run mypy", or wants to find and fix Python code quality issues using ruff and mypy.
nainishshafi/developer-productivity-skills/.github/skills/scan-halucinated-tests Skill
1★ repoUse when the user asks to "scan for hallucinated tests", "check if my tests are hallucinated", "validate tests against source", "verify test accuracy", "find fake test assertions", "audit tests for hallucinations", "test hallucination scan", "verify tests match source code", "check java tests", "validate c# tests", or "check javascript tests for hallucinations". Also use when the user wants to cross-check a test file against real source code to detect phantom symbols, wrong imports, bad mock targets, or fabricated constants — in any supported language.
RockaRhymeLLC/claude-code-skills/skills/smart-commit Skill
1★ repoGenerates clear, conventional commit messages from staged changes. Analyzes diffs to produce focused commit messages that explain WHY, not just WHAT. Supports conventional commits, multi-file changes, and interactive refinement. Use when committing code or when the user says /smart-commit.
RockaRhymeLLC/claude-code-skills/skills/smart-pr Skill
1★ repoGenerates well-structured pull request descriptions from git history. Analyzes commits, diffs, and branch context to produce clear summaries with categorized changes, testing notes, and reviewer guidance. Use when creating a PR, writing a PR description, or when the user says /smart-pr.
RockaRhymeLLC/claude-code-skills/skills/smart-review Skill
1★ repoPerforms thorough code review on git changes. Analyzes diffs for bugs, security issues, performance problems, and design concerns. Produces actionable feedback organized by severity. Use when reviewing code, checking a PR, or when the user says /smart-review.
shubham0704/claude-skills/rigorous-paper-reviewer Skill
1★ repoReview a LaTeX research paper for mathematical rigor, notation consistency, proof obligations, numerical-analysis discipline, complexity claims, convergence/error bounds, figure quality, reader-state flow, cross-references, and global coherence. Use when the user wants a deep technical review or verification pass on a paper, supplement, or LaTeX project; also trigger when the user asks whether text sounds wasteful, machine-generated, clear, simple, readable, well-flowing, compressed, rhythmic, or wants to zoom in/out paragraph by paragraph. Do not use for initial drafting unless the user explicitly asks for review-first feedback.
shubham0704/claude-skills/tikz-figure-review Skill
1★ repoReview and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered figure visibly has overlap, clipping, or label collisions; when setting up a per-figure review workflow across a large document; or when the user shows a screenshot of a figure that looks wrong. Trigger proactively whenever the user mentions figure alignment, TikZ layout, pgfplots legends/axes, figure cleanup, or asks to fix a figure — even if they don't explicitly say 'review'. Covers a fast iteration loop: extract each tikzpicture into a standalone, compile to PNG, fix, sync back to the main file.
bjg4/bgskillz/bakeoff/fixtures/v4/grill-me-clone/grill-me Skill
1★ repoHelps with planning and design discussions.
bjg4/bgskillz/bakeoff/fixtures/v5/code-review/code-review Skill
1★ repoReview pull requests for bugs, security issues, and maintainability problems with structured findings. Use when reviewing PRs, diffs, or code changes. Do NOT use for writing new features from scratch.
bjg4/bgskillz/bakeoff/fixtures/v5/commit-message/commit-message Skill
1★ repoWrite clear conventional commit messages from git diffs or change descriptions. Use when committing, writing commit messages, or summarizing staged changes. Do NOT use for PR descriptions or release notes.
bjg4/bgskillz/bakeoff/fixtures/v5/grill-me-clone/grill-me Skill
1★ repoStress-test a plan or design through relentless Socratic questioning until shared understanding. Use when the user says "grill me", wants to stress-test a plan, or review a design decision. Do NOT use for implementation or code generation.
bjg4/bgskillz/bakeoff/live/v4/code-review/code-review Skill
1★ repoProvides comprehensive code review assistance for developers analyzing pull requests and code changes. Use when performing code reviews, examining diffs, or evaluating code quality before merge. Covers bugs, security vulnerabilities, performance concerns, and maintainability with structured feedback and severity levels.
bjg4/bgskillz/bakeoff/live/v4/commit-message/commit-message Skill
1★ repoAssists developers with writing high-quality commit messages for version control. Use when committing changes, summarizing staged diffs, or preparing changelog entries. Supports conventional commits and descriptive subject lines.
bjg4/bgskillz/bakeoff/live/v4/grill-me-clone/grill-me Skill
1★ repoHelps users stress-test plans and designs through detailed questioning. Use when discussing architecture, project plans, or design documents. Supports Socratic dialogue and recommended answers.
bjg4/bgskillz/bakeoff/live/v5/code-review/code-review Skill
1★ repoReview pull requests for bugs, security issues, and maintainability with severity-grouped findings. Use when reviewing PRs, diffs, or code changes before merge. Do NOT use for implementing features or writing new code.
bjg4/bgskillz/bakeoff/live/v5/commit-message/commit-message Skill
1★ repoWrite conventional commit messages from git diffs or change summaries. Use when committing, drafting commit messages, or summarizing staged changes. Do NOT use for PR bodies or release notes.
bjg4/bgskillz/bakeoff/live/v5/grill-me-clone/grill-me Skill
1★ repoStress-test a plan or design through Socratic questioning until shared understanding. Use when the user says "grill me", wants to stress-test a plan, or review a design. Do NOT use for implementation or code generation.
datamaker-kr/synapse-claude-marketplace/dist/opencode/speckit-helper/.opencode/skills/checklist-generation Skill
no license1★ repoExpertise in generating domain-specific quality checklists for specifications. Activates when user discusses quality validation or requirement testing. Trigger keywords: checklist, quality gate, requirement testing, validation, completeness check, review checklist
datamaker-kr/synapse-claude-marketplace/plugins/platform-dev-team-common/skills/commit-with-message Skill
no license1★ repo커밋 메시지 작성 가이드 (한글/영어). 커밋 생성 시 자동으로 활성화되어 규칙을 준수하도록 안내합니다.
The same file is in 2 other repositories
datamaker-kr/synapse-claude-marketplace/plugins/speckit-helper/agents/quality-gate Skill
no license1★ repoRuns consistency analysis and checklist validation as a quality checkpoint before implementation. Use when the user wants to validate their specification quality.
datamaker-kr/synapse-claude-marketplace/plugins/speckit-helper/skills/checklist-generation Skill
no license1★ repoExpertise in generating domain-specific quality checklists for specifications. Activates when user discusses quality validation or requirement testing. Trigger keywords: checklist, quality gate, requirement testing, validation, completeness check, review checklist
The same file is in 2 other repositories
lklimek/claudius/skills/check-pr-comments Skill
1★ repoPlugin with opinionated set of Claude Code agents nad skills
lklimek/claudius/skills/git-and-github Skill
1★ repoPlugin with opinionated set of Claude Code agents nad skills
lklimek/claudius/skills/grumpy-review Skill
1★ repoPlugin with opinionated set of Claude Code agents nad skills
lklimek/claudius/skills/push Skill
1★ repoPlugin with opinionated set of Claude Code agents nad skills
lklimek/claudius/skills/review-dependency Skill
1★ repoPlugin with opinionated set of Claude Code agents nad skills
lklimek/claudius/skills/review-loop Skill
1★ repoUse to autonomously handle peer review — request, wait, fix comments, push, repeat until resolved.
lklimek/claudius/skills/review-pr Skill
1★ repoPlugin with opinionated set of Claude Code agents nad skills
IamBiswajitSahoo/ClaudeSkills/plugins/bix-github/skills/github-pr-review Skill
1★ repoReview GitHub pull requests — drafts findings across 5 categories with severity labels, supports parallel agents for large PRs, and posts as a batched pending review after per-comment approval.
nicholashidalgo/claude-skillforge/data-engineering/report-output-validator Skill
1★ repoValidate report outputs with Python using row-count checks, subtotal tests, duplicate-grain checks, and comparison summaries.
nicholashidalgo/claude-skillforge/data-engineering/sql-join-risk-reviewer Skill
1★ repoReview SQL or report logic for many-to-many joins, duplicate-grain risk, unsafe aggregation, and filter side effects.
iabhisekbosepm/claude-god-setup/.claude/skills/pr-review Skill
no license1★ repoReview a GitHub pull request: fetch PR diff, run all review agents, post summary.
iabhisekbosepm/claude-god-setup/.claude/skills/review Skill
no license1★ repoRun the full code review pipeline on recent changes. Auto-selects reviewers based on file types.
wxxzy/Claude-Code-Software-Studios/.claude/skills/gate-check Skill
1★ repo发布前质量门控审计。当代码即将交付、需要 QA 按发布清单做最后质量验证时使用。
wxxzy/Claude-Code-Software-Studios/.claude/skills/review Skill
1★ repo技术评审与深度代码审计。当开发完成、发布前需要架构师从性能、可维护性与安全角度审查代码实现时使用。
wxxzy/Claude-Code-Software-Studios/.claude/skills/taste-review Skill
1★ repoVibe Mode 审美/体验维度评审。当原型功能已可跑但用户对"感觉不对"、视觉/交互氛围有疑虑时使用。产出 docs/reviews/taste-<date>.md。
wxxzy/Claude-Code-Software-Studios/.claude/skills/vibe-check Skill
1★ repo意图对齐校准。在原型迭代 3-5 轮后,或用户表达"感觉不对"时使用。对齐"最初想要什么 vs 现在做出了什么"。
DROOdotFOO/agent-skills/skills/code-review Skill
1★ repoStructured code review with blast radius analysis, security scanning, quality scoring, and a 30+ item checklist. TRIGGER when: user asks to review a PR, diff, changeset, or code for quality/security/breaking changes; user runs /review or /code-review; reviewing staged or committed changes. DO NOT TRIGGER when: writing new code from scratch, refactoring without review context, general debugging.
DROOdotFOO/agent-skills/skills/git-guardrails Skill
1★ repoSet up Claude Code hooks to block dangerous git commands before they execute. TRIGGER when: user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code. DO NOT TRIGGER when: user is asking about git workflow or branching strategy.
DROOdotFOO/agent-skills/skills/git-worktree-manager Skill
1★ repoParallel development with git worktrees and deterministic port isolation. TRIGGER when: user wants to work on multiple branches simultaneously, run parallel agent sessions, manage worktree-based dev environments, or asks about port conflicts between concurrent services. DO NOT TRIGGER when: simple branch switching (use git checkout), or single-branch development with no parallelism needed.
DROOdotFOO/agent-skills/skills/prd-to-plan Skill
1★ repoConvert a PRD into a phased implementation plan using tracer-bullet vertical slices, then optionally create GitHub issues from the plan. TRIGGER when: user has a PRD and wants an implementation plan, says "plan this", asks to break a feature into phases, wants to convert requirements into tasks, asks to break a PRD into issues, create issues from a plan, or says "prd to issues". Also when user wants to stress-test a plan, get grilled on their design, or says "grill me". DO NOT TRIGGER when: user wants to execute a plan (just code it), review existing code, or do general architecture discussion without a PRD.
DROOdotFOO/agent-skills/skills/release Skill
1★ repoRelease management with changelog generation, semantic versioning, and readiness checks. TRIGGER when: user asks to prepare a release, generate a changelog, bump version, check release readiness, or create a release tag; user runs /release or /changelog. DO NOT TRIGGER when: writing commit messages (use conventional commits directly), deploying to infrastructure, debugging production issues.
ajinkya-t/codebase-oracle/skills/oracle-review-spec Skill
1★ repoReview a product spec or PRD against the actual codebase behavior. Planned skill. See docs/architecture.md for the spec.
ladyiceberg/openclaw-memory-quality/skills/soul-check Skill
1★ repoAudit SOUL.md health for OpenClaw agents — detects boundary violations (injected code, URLs, shell commands, prompt injection), identity drift (action verb density, missing sections), and stability changes across runs. Optional LLM semantic conflict detection available. Use this skill whenever the user wants to check SOUL.md, mentions agent identity issues, soul drift, soul conflicts, or uses phrases like "check soul", "soul health", "SOUL.md", "agent identity", "soul drift", "soul conflict", "检查 SOUL", "SOUL 健康", "身份漂移", "语义冲突". Always use this skill for SOUL.md questions.
adrojis/tracecat-skills/skills/tracecat-validation-debug Skill
1★ repoActivate when users debug failed workflow executions, troubleshoot errors, or validate workflows before deployment
iwritec0de/conform/tests/empty-dirs-plugin/skills/valid-skill Skill
1★ repoUse this skill when the user asks to validate something. Trigger when the user mentions "validate", "check", or "verify inputs".
iwritec0de/conform/tests/malformed-plugin/skills/oversized-desc Skill
1★ repoThis is an extremely long description that exceeds the recommended 1024 character limit for skill descriptions. It goes on and on about all the things this skill can do, repeating itself unnecessarily to pad out the length. The skill handles data processing, file management, code generation, testing, deployment, monitoring, alerting, logging, debugging, profiling, benchmarking, optimization, refactoring, documentation, review, analysis, synthesis, transformation, validation, verification, certification, authentication, authorization, encryption, decryption, compression, decompression, serialization, deserialization, marshalling, unmarshalling, encoding, decoding, parsing, formatting, rendering, templating, caching, indexing, searching, filtering, sorting, grouping, aggregating, pivoting, joining, merging, splitting, chunking, batching, streaming, buffering, queuing, scheduling, dispatching, routing, balancing, scaling, sharding, replicating, synchronizing, reconciling, migrating, upgrading, patching, rolling, canary, blue-green, feature-flagging, circuit-breaking, rate-limiting, throttling, back-pressuring, retry-handling, timeout-managing, deadline-propagating, context-passing, span-tracing, metric-collecting, health-checking, readiness-probing, and liveness-monitoring across distributed systems.
iwritec0de/conform/tests/warning-plugin/skills/code-review Skill
1★ repoThis skill should be used when the user asks to "review code" or "check code quality". Provides code review guidance.
ryukyagamilight/terminal-skills/devops/git-advanced Skill
1★ repoGit 高级操作
The same file is in 1 other repository
Lu1sDV/skillsmd/skill-smell-checker Skill
no license1★ repoAudits Agent Skill SKILL.md files for the 26 skill smells defined in arXiv:2607.01456, separating five static checks from 21 semantic checks. It applies when reviewing, linting, authoring, or refactoring SKILL.md files; when a skill quality audit is requested; or when terms such as skill smell, SSD, static skill check, context bloat, missing guardrails, or vague skill description appear.
n1ddeh/fantastic-skills/review-graphite-stack-chomper Skill
no license1★ repoReviews all open non-draft PRs in a Graphite stack in parallel. Use when the user provides a PR number or URL and wants the entire stack reviewed. Runs review-pr-chomper on each branch and auto-posts GitHub comments and Linear updates without user confirmation. Supports --include-drafts to review draft PRs as well (e.g. for self-review).
n1ddeh/fantastic-skills/review-pr-chomper Skill
no license1★ repoDeep code review with a skeptic agent. Chomper is a ruthless but fair shark reviewer who catches bugs, evaluates existing PR comments, and filters false positives. Triggers on "review my changes", "check this code", "review the diff", or "find bugs in my changes".
ytubecoder/ticket-takeaway/src/skills/review Skill
no license1★ repoReview features in the For Review column — walk through tickets in batches, collect feedback or acceptance, create bug sub-tickets, and manage the acceptance flow.
swathidbhat/Claude-Skills/non-fiction-book-review Skill
1★ repoDocument a reader's experience with a non-fiction book through active recall and guided reflection. Triggers when user wants a book review/summary/notes AND provides their highlights, annotations, or reading data (JSON, HTML, CSV, export, copy-paste). Interviews the user with four reflection questions before evaluating their recall against their own highlights, checking factual accuracy, and flagging missed themes. Produces a one-page summary in the user's voice. Do not trigger for fiction, or requests without the user's own reading data.
tjhils/cx-plugins/writing-check/skills/writing-check Skill
1★ repoScan writing for AI-generated patterns and drift from the user's own voice. Use when the user says "writing check", "slop check", "check for AI writing", "de-slop this", "does this sound like AI", "review for AI tells", "scan my draft", "clean up AI writing", or asks to review a draft for robotic or formulaic language.
shivae372/claude-bootstrap/.claude/skills/code-review Skill
1★ repoStructured code review. Invoke before committing, before opening a PR, or when you want feedback on changes. Auto-activates on "review this code", "check my changes", "look for issues", "review before I push". Routes to code-reviewer sub-agent to keep main context clean.
shivae372/claude-bootstrap/.claude/skills/context-guard Skill
1★ repoContext window protection. Auto-activates when the conversation is getting long, when the user is about to do a large file read or exploration task, or when the context is approaching its limit. Helps route expensive operations to sub-agents to protect the main session.