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
shivae372/claude-bootstrap/.claude/skills/dep-check Skill
1★ repoDependency audit skill. Check for outdated packages and security vulnerabilities. Auto-activates on "check dependencies", "any vulnerable packages", "audit deps", "what's outdated", "npm audit". Routes to dep-checker sub-agent to keep main context clean.
shivae372/claude-bootstrap/.claude/skills/git-workflow Skill
1★ repoGit workflow assistant. Invoke when the user wants to commit, create a branch, write a PR description, or follow the project's git conventions. Auto-activates on: "commit this", "create a PR", "write a commit message", "what should I name this branch".
KKenny0/Taku/skills/guard Skill
no license1★ repoExecution reliability expert. ALWAYS invoke this skill after any coding skill completes its work. Do not accept completed work without running this guard first. Use this skill to audit step execution and catch silent omissions.
KKenny0/Taku/skills/reflect Skill
no license1★ repoUser-invoked reflection. Three modes: Learn (script-backed recording, searching, pruning, exporting, and optional bootstrap for user-approved patterns, pitfalls, preferences, discoveries), Retro (weekly engineering retrospective with git commit analysis, metrics, team breakdowns, trends), and Write Skill (codify recurring learnings into reusable skills). Triggers on "what have we learned", "add learning", "show learnings", "weekly retro", "what did we ship", "engineering retrospective", "write a skill", "create a skill", "codify this pattern", "总结一下", "学到了什么", "记录一下", "回顾这周", "做个retro", "写个技能", "把这个模式固化". Also invoke when the user expresses satisfaction or frustration after completing work — these are natural reflection moments.
KKenny0/Taku/skills/review Skill
no license1★ repoUse after implementation is complete. Triggers after /taku-build. Analyzes diffs for security issues, bugs, and code quality. Run when asked to "review this", "check my diff", "code review", "审查代码", "看看有什么问题", "检查一下", "准备合并", "代码质量", or before shipping. Proactively invoke when the user is about to merge or land code changes.
anotherben/claude-enterprise-skills/skills/enterprise-review Skill
1★ repoTwo-stage code review: spec compliance THEN code quality. Separate concerns prevent spec bugs hiding behind quality observations. Medium+ tier requires a separate agent — builder never reviews own work. Use after enterprise-build.
The same file is in 2 other repositories
anotherben/claude-enterprise-skills/skills/enterprise-verify Skill
1★ repoEvidence-based verification before any completion claim. No 'should work' or 'probably fine' — paste fresh test output or don't claim done. 7-check verification sequence. Use before committing or claiming work is complete.
The same file is in 2 other repositories
Uapi post sensitive word quick check
AxT-Team/uapi-agent-skills/skills/uapi-post-sensitive-word-quick-check Skill
1★ repo使用 UAPI 的“敏感词检测(快速)”单接口 skill,处理 敏感词检测(快速)、敏感词检测、快速审核 等请求。 Use when the user wants post sensitive word quick check, text profanitycheck, profanitycheck, sensitive word detection, text moderation, profanity check, or when you need to call POST /text/profanitycheck directly.
AxT-Team/uapi-agent-skills/skills/uapi-post-text-md5-verify Skill
1★ repo使用 UAPI 的“MD5 校验”单接口 skill,处理 MD5 校验、MD5 等请求。 Use when the user wants post text md5 verify, text md5 verify, verify, md5 hash, text analysis, text conversion, or when you need to call POST /text/md5/verify directly.
manastalukdar/ai-devstudio/skills/ai-system-review Skill
1★ repoReview LLM application code for context assembly quality, retrieval integration, prompt construction, output validation, cost controls, and failure handling
manastalukdar/ai-devstudio/skills/branch-finish Skill
1★ repoComplete branch workflow with squash, rebase, and cleanup
manastalukdar/ai-devstudio/skills/code-review-checklist Skill
1★ repoGenerate context-aware code review checklists for changes
manastalukdar/ai-devstudio/skills/commit Skill
1★ repoAnalyze changes and create meaningful conventional commits with pre-commit quality checks
manastalukdar/ai-devstudio/skills/context-restore Skill
1★ repoRestore work-in-progress context saved by /context-save — finds the most recent WIP commit on the current branch and unpacks it back to the working tree so you can resume exactly where you left off. Inspired by gstack's context-restore skill.
manastalukdar/ai-devstudio/skills/context-save Skill
1★ repoSave current work-in-progress context as a git WIP commit — captures all staged and unstaged changes with a timestamped stash message so you can switch contexts safely and restore later. Inspired by gstack's context-save skill.
manastalukdar/ai-devstudio/skills/cross-modal-review Skill
1★ repoRun a second-model quality gate on staged changes, a skill draft, or any generated output. A cheaper, independent model reviews the primary output for correctness, safety, and completeness before the user sees the final result.
manastalukdar/ai-devstudio/skills/devex-review Skill
1★ repoAudit the developer experience of your project — setup friction, onboarding clarity, local dev loop speed, tooling consistency, and documentation gaps. Produces a DX scorecard and prioritized improvement list. Inspired by gstack's devex-review skill.
manastalukdar/ai-devstudio/skills/git-bisect Skill
1★ repoAutomated git bisect for bug hunting with test script execution
manastalukdar/ai-devstudio/skills/git-guardrails Skill
1★ repoInstall a Claude Code PreToolUse hook that blocks dangerous git operations (force push, reset --hard, clean -f, branch -D, checkout ., restore .) before they execute. Use when setting up git safety hooks or preventing destructive git commands in Claude Code.
manastalukdar/ai-devstudio/skills/git-worktree Skill
1★ repoManage git worktrees for parallel feature development
manastalukdar/ai-devstudio/skills/grill-me Skill
1★ repoRelentlessly interview the user about a plan or design, walking down every branch of the decision tree one question at a time until reaching shared understanding. Use when user wants to stress-test a plan, get challenged on their design, or says "grill me".
manastalukdar/ai-devstudio/skills/incremental-implementation Skill
1★ repoEnforce vertical-slice discipline — implement one thin slice (~100 lines max), test it, verify it works, commit it, then repeat. Never write more than can be tested in a single step.
manastalukdar/ai-devstudio/skills/license-check Skill
1★ repoLicense compliance checking and conflict detection
manastalukdar/ai-devstudio/skills/loop-verify Skill
1★ repoIndependent verification agent for loop-produced changes — runs tests, confirms diff scope, and issues APPROVE / REJECT / ESCALATE_HUMAN. Use after any implementer agent. Never in the same role as the implementer.
manastalukdar/ai-devstudio/skills/owasp-check Skill
1★ repoOWASP Top 10 vulnerability scanning and remediation
manastalukdar/ai-devstudio/skills/review Skill
1★ repoMulti-agent code analysis covering security, performance, quality, and architecture
manastalukdar/ai-devstudio/skills/setup-pre-commit Skill
1★ repoInstall Husky pre-commit hooks with lint-staged (Prettier), type checking, and test automation. Auto-detects package manager. Use when adding pre-commit hooks, setting up Husky, configuring lint-staged, or adding commit-time formatting and type checking.
manastalukdar/ai-devstudio/skills/sre-review Skill
1★ repoReview code and configuration for SRE concerns — SLO/SLA coverage, observability gaps, toil, alerting blind spots, and reliability anti-patterns
manastalukdar/ai-devstudio/skills/ui-critique Skill
1★ repoDual-agent UX design review — Assessment A runs design-director heuristics while Assessment B runs visual pattern analysis; results synthesized into a prioritized critique snapshot
thattimc/skills/skills/okf-lint Skill
1★ repoValidate an Open Knowledge Format (OKF) knowledge base (a wiki/ bundle of Markdown + YAML frontmatter) for spec conformance and house rules. Use when the user wants to check, validate, or lint their wiki / knowledge base, or after editing KB pages. Triggers: "lint my wiki", "validate the knowledge base", "check the OKF bundle", "is my wiki conformant", "run the okf linter". Reports errors (must fix) and warnings (review), with a non-zero exit on failure.
thattimc/skills/skills/okf-new-kb Skill
1★ repoScaffold a brand-new personal wiki / knowledge base in the Open Knowledge Format (OKF). Use when the user wants to start a new knowledge base, personal wiki, "second brain", or notes repo from scratch — especially an OKF / agent-managed / Obsidian-friendly one. Triggers: "new knowledge base", "start a wiki", "scaffold an OKF kb", "set up a personal wiki", "create a notes vault", "bootstrap a knowledge base". Stamps a complete, lint-clean OKF bundle plus the agent operating manual, templates, validator, and Obsidian config.
hparamore/essential-claude-skills-hparamore/fable-toolkit/skills/release-readiness Skill
no license1★ repoRun a pre-ship gate that verifies a build is actually ready to deploy RIGHT NOW — build passes, core flows work, no regressions or debug residue, docs and version notes updated — and give a clear GO / NO-GO with evidence. Use whenever the user says "ready to ship?", "can I deploy this", "pre-launch check", "release checklist", "is this good to go", or asks to verify a change before deploying. Verify, don't assume — a NO-GO with reasons beats a GO that breaks prod. Not for planning which features go in a release (use project planning), writing release notes or changelogs, or executing the deploy itself — this is the go/no-go safety check that runs just before shipping.
kreek/consult/agents/.agents/skills/code-review Skill
1★ repoUse to review diffs and PRs for bugs, regressions, edge cases, proof, and merge readiness.
kreek/consult/agents/.agents/skills/commit Skill
1★ repoUse for staging reviewed work, commit splits, and messages.
kreek/consult/agents/.agents/skills/git-workflow Skill
1★ repoUse for branches, history edits, conflicts, rebases, recovery, force-push, and gh.
kreek/consult/agents/.agents/skills/official-source-check Skill
1★ repoUse when external behavior must be checked against official sources.
kreek/consult/consult/skills/code-review Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/consult/skills/commit Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/consult/skills/git-workflow Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/consult/skills/official-source-check Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/plugin/skills/code-review Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/plugin/skills/commit Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/plugin/skills/git-workflow Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/plugin/skills/official-source-check Skill
1★ repoUse when external behavior must be checked against official sources.
Methasit-Pun/data_engineer_claude_skills/06-reliability/data-contracts Skill
no license1★ repoDefine and enforce schema contracts between producer and consumer teams — field types, nullability, allowed values, versioning, breaking vs. non-breaking changes, and change detection patterns. Use this skill whenever two teams or services share a dataset and upstream changes keep breaking the downstream silently, when a team wants to formalize what a dataset "promises" to its consumers, or when setting up schema validation at pipeline boundaries. Also trigger when the user asks about schema evolution, backward/forward compatibility, schema registries, Great Expectations for inter-team contracts, or when a producer is about to make a "small" schema change and you want to assess its downstream impact. If upstream and downstream are owned by different people, this skill should be active.
vikast908/agent-repo-card/skills/product-review Skill
1★ repoUse when the user wants a product / PM / product-market-fit review of what their repo actually does — evaluating the customer problem, target users, jobs-to-be-done, core functionality, value & differentiation, scope, adoption/usability, positioning, and gaps. Triggers on "is this useful", "review my product", "PMF check", "who is this for", "what's missing", "product critique".
t0ddharris/compound-marketing/.claude/skills/devils-advocate Skill
no license1★ repoGet an outside-Anthropic second opinion on any piece of work by sending it to Google Gemini with an adversarial critique prompt. Use when the user wants to pressure-test a decision, plan, assumption, blog draft, landing page, positioning statement, campaign, or chunk of code with a non-Claude model. Trigger when the user says 'devil's advocate,' 'play devil's advocate,' 'poke holes,' 'stress test this,' 'second opinion,' 'outside perspective,' 'non-Anthropic read,' 'sanity check from another model,' 'challenge this,' 'critique this from outside,' or '/devils-advocate.' This is explicitly a cross-model sanity check — do NOT substitute your own critique; the whole point is to surface blind spots Claude might share.
t0ddharris/compound-marketing/.claude/skills/impeccable Skill
no license1★ repoUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
The same file is in 1 other repository
iamjosuho/memOrb/skills/core/memorb-lint Skill
no license1★ repoWiki Lint 工作流:memory 健檢,找出矛盾、過期、孤兒頁、缺頁、缺連結。觸發詞:整理 memory、檢查第二大腦、健檢、memory 有沒有要更新的。跑 dream-studio 之前主動建議執行。
SkillMedev/vercel-platform/skills/vercel-firewall-and-botid Skill
1★ repoHarden a Vercel app at the platform edge - the Vercel WAF (custom rules, IP blocking, managed rulesets like OWASP CRS + bot_protection + ai_bots, rate limiting), Attack Challenge Mode, system bypass rules, automatic DDoS mitigation, and BotID bot verification on sensitive routes. Use when someone says "protect my Vercel app", "add a WAF rule", "rate limit my API", "block this IP / country / user-agent", "I'm getting DDoSed", "stop bots / scrapers / AI crawlers", "turn on Attack Mode", "verify human vs bot on checkout/signup/login", or "set up BotID". Do NOT use for app-level auth/session logic - that is application code; do NOT use for env vars or secrets - use vercel-env-management; do NOT use for the deploy/promote/rollback flow - use vercel-deploy-pipeline.
The same file is in 1 other repository
christophecapel/claude-mechanisms-tools/skills/press1-check Skill
1★ repoAudit which Bash commands required manual approval ("press 1") in Claude Code sessions. Use when the user says "press1-check", "press 1 check", "permission audit", or wants to review which commands need allow-listing.
MalamaLabs/Carbon-Market-Skills-Pack/skills/carbon-project-timeline Skill
1★ repoBuild project timelines, milestone trackers, and Gantt-style dependency maps for carbon credit projects, covering the validation, monitoring, verification, and issuance cycle. Use whenever the user wants a carbon project timeline, milestone tracker, registry submission schedule, crediting period roadmap, or wants to map dependencies between PDD completion, validation, first monitoring period, and credit issuance. Trigger on "project timeline," "milestone tracker," "when do we submit," "validation timeline," or "crediting period schedule."
Finishing a development branch
NafisRayan/100x-Agent-Toolkit/skills/finishing-a-development-branch Skill
no license1★ repoUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
The same file is in 10 other repositories
NafisRayan/100x-Agent-Toolkit/skills/full-code-review Skill
no license1★ repoRun a deep multi-agent code review across one or more codebases. Covers security, code quality, and business logic. Outputs structured markdown with file paths, line numbers, severity ratings, and fix instructions. Triggers on "full code review", "comprehensive review", "code audit", "review entire codebase", "review all code".
NafisRayan/100x-Agent-Toolkit/skills/grill-me Skill
no license1★ repoInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
The same file is in 23 other repositories
NafisRayan/100x-Agent-Toolkit/skills/impeccable Skill
no license1★ repoUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
NafisRayan/100x-Agent-Toolkit/skills/receiving-code-review Skill
no license1★ repoUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
The same file is in 28 other repositories
NafisRayan/100x-Agent-Toolkit/skills/requesting-code-review Skill
no license1★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
The same file is in 11 other repositories
NafisRayan/100x-Agent-Toolkit/skills/syntax-rules Skill
no license1★ repoApply language-specific coding standards, conventions, and syntax rules across 18 languages plus universal common rules. Use when writing, reviewing, or refactoring code in any language — enforces coding style, testing patterns, security practices, error handling, naming conventions, immutability principles, and project structure. Triggers on "coding standards", "code style", "syntax rules", "coding conventions", "apply rules", "follow conventions", "enforce style", "lint rules", or when writing code in any supported language. Covers TypeScript, JavaScript, Python, Rust, Go, Java, Kotlin, Swift, C++, C#, PHP, Dart, Angular, ArkTS, F#, Perl, web/frontend, and Chinese-language rules.
NafisRayan/100x-Agent-Toolkit/skills/ultrareview Skill
no license1★ repoMulti-agent parallel code review system inspired by Claude Code's /ultrareview. Spawn 5-20 specialized agents (security, logic, performance, edge cases, architecture) to review code simultaneously, cross-validate findings, and produce a consolidated bug report. Use when asked to do deep code review, ultrareview, multi-agent review, comprehensive bug hunting, security audit, or thorough pre-merge code inspection.