Review & quality
19,471 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
silkyland/jury-my-repo Skill
0★Agent skill: multi-agent adversarial code audit — run every installed AI coding agent CLI (Claude, Codex, Gemini, OpenCode, Kimi, Cursor…) in parallel on one brief, verify every claim against the code, score who was right/wrong/hallucinating
dekrezz/ultraloop/skills/ultraloop Skill
0★ repoAgent skill: a task is done only when verified and actually works. Triages scale, recons your repo, ships verified code or code + an honest run plan. For Claude Code, Codex, Cursor & other agents.
adeilsonrbrito/cross-model-consult/consult-codex Skill
0★ repoCross-model second opinions for coding agents — skills that let Claude Code consult rival-model CLIs (Codex, Grok, OpenCode), solo or as a blind three-model panel.
finnfotschki/mindful-agent-collaboration/skills/mindful-conduction Skill
0★ repoInstallable skills, gates, hooks and templates for deliberate human-agent work — drops into your existing Claude Code or Codex setup.
bman654/audio-forge/skills/audio-lens Skill
0★ repoLocal, on-device audio toolbox for AI agents: voice-clone TTS, instrumental music, and audio verification — three installable Agent Skills.
IcodeNet/agent-skills/skills/address-pr-feedback Skill
0★ repo40 portable full-SDLC agent skills for Claude Code, Cursor, Codex, and GitHub Copilot — deep-work autonomy, contract-guard for external interfaces, TDD, code review, PR babysitting. Install: npx github:IcodeNet/agent-skills
scottconverse/visitor-audit Skill
0★Claude skill: audit your project's public pages the way a first-time visitor experiences them — every page read fully, every link clicked and counted.
shinzoxD/knackbox/skills/coding/accessibility-review Skill
0★ repoCurated, auditable, benchmark-ready Agent Skills library for Claude Code, Codex, OpenCode, Cursor, and more.
CongBao/skill-steward/packages/engine/tests/fixtures/native-inventory/claude-code/cache/team/review/1.0.0/skills/review Skill
0★ repoCross-Harness operations for Agent Skills: task preflight, missing-Skill discovery, local evidence, and reversible governance.
mauromedda/ccctx/skills/ccctx-review Skill
0★ repoLLM-first Go CLI for managing multiple Claude Code OAuth sessions
VitorLudke/skillsync/skills/hello-world Skill
0★ repoOne canonical Agent Skills tree, symlinked into every agent CLI — edit a skill once, Claude Code, Codex and friends all see it
takeshijuan/create-public-pr/skills/create-public-pr Skill
0★ repoAgent Skill for creating privacy-safe public pull requests with redacted history and worktree audits.
ecfromthedc/ec-rt-skills/checker Skill
no license0★ repoAgent skills, Rust CLIs, and Python jobs for a content-marketing ops fleet — maker/checker gates, curation metric, workload ledger, ops-exhaust content machine, skill-tuner.
goonobu-dot/dev-skills-library/skills/ai-code-verification Skill
0★ repo15 auto-selectable Claude Code skills distilling engineering best practices (Kent Beck, Fowler, Google SRE, OWASP, Anthropic, Netflix…), with a bilingual offline learning site. Make Claude Code write better code — and learn the practices yourself.
MasashiFukuzawa/agent-toolbox/plugins/done/skills/done Skill
0★ repoReusable engineering skills for Claude Code and Codex
StaryMoon/review-response-matrix-skill/skills/review-response-matrix Skill
0★ repoAgent Skill for traceable peer-review response and revision matrices.
ProfesseurHaipeng/ai-research-preflight/skills/check-formulation-readiness Skill
0★ repoDeterministic, local-first preflights for research compute and declared experiment readiness.
runsagents/airlocks Skill
0★Uses black-box, read-after-write verification against the system of record before accepting a completion claim.
annost/skill-reviewer Skill
0★Claude Code skill that reviews other skills and slash commands for research-backed authoring anti-patterns (skill smells)
Kofiloski/ios-release-quality-toolkit/plugins/ios-release-quality-toolkit/skills/app-store-review-risk Skill
0★ repoAgent skills for App Store review risk, XCUITest testability repairs, and evidence-rich iOS Simulator checks.
kaustin923/agent-fitness-coach/.claude/skills/daily-checkin Skill
0★ repoGive this repo to Claude and it becomes your training coach: real periodized plans, Strava + Apple Health data, progress tracking and grading — files are the database, skills are the features, the agent is the app.
runsagents/second-opinion Skill
0★Second-opinion code review: a different model reviews each diff, and disagreements go to a human. Multi-model deliberation.
Thecsiz/agentic-principles/skills/agentic-critique Skill
no license0★ repoA practical framework and AI skill for critiquing agentic experiences, oversight, trust, and consent.
WdBlink/token-firewall-team/skills/token-firewall-team Skill
0★ repoLower LLM costs for coding agents: delegate implementation to cheaper models and reserve frontier-model tokens for evidence-backed final review.
eric-lim/skills/skills/code-review Skill
0★ repoMy curated repository of agent skills
warpdotdev/client-release-agent-oss/.warp/skills/cherrypick-to-release Skill
0★ repoWarp agent skills for release engineering automation — cherry-picking fixes, cutting release candidates, tracking PR status, and posting Sentry/Slack digests.
Wu030616/quest3-unity-codex-skills/skills/quest3-verify-first Skill
0★ repoQuest 3 Unity XR/MR Agent Skills for verification, spatial UI design, and read-only project audits
deployhq/reply-pr/skills/reply-pr Skill
no license0★ repoTriage and reply to a PR's unresolved review comments — reply-only, on each reviewer's channel, with you approving every reply.
4bdurehman56382/ghl-browser-audit-tool/grill-me-code Skill
0★ repoAI-importable browser audit tool repo with separated audit tooling and client materials.
bigpowert25-del/render-remotion-review/skill/render-remotion-review Skill
0★ repo有证据的复盘数据转为可验证的 Remotion 竖屏视频
tejask0/agent-skills/article-improve Skill
0★ repoA collection of reusable AI agent skills for everyday use.
takeshijuan/validating-prs-with-evidence/skills/validating-prs-with-evidence Skill
0★ repoAgent Skill for evidence-backed pull request and branch behavior QA.
okht/grill-powers/skills/grill-powers Skill
0★ repoCombines grill-me + superpowers: expand a rough idea into full product decisions, then converge into an approved product spec and verified delivery.
JoaoAlavarse/cursor-config/skills/architecture-review Skill
0★ repoConfiguração global do Cursor: user rules, agent skills, slash commands e hooks com scripts de instalação.
rogerchappel/agent-runbook-lint-skill Skill
0★Local-first lint checks for agent automation runbooks
prikotov/become-role/examples/skills/deep-review Skill
0★ repoResolve an agent role and declare its lazily-loaded skills as a standard catalog. Convention + tiny fail-fast CLI for role-based agent skills (pi/codex/Claude Code/any).
uizze/uizze/plugins/claude-directory/skills/anti-ui-slop Skill
0★ repoStop coding agents from shipping generic UI with 800,000+ real web and iOS screens and a hard finish gate.
TopicalitySummit/summit-decision-assurance/skills/check-governed-output Skill
no license0★ repoPublic-safe agent skills for Summit Decision Assurance
nikhilkyn-png/app-verify Skill
0★Claude Code skill: exploratory smoke-sweep + deploy verification for running/deployed web apps. Catches bugs that pass typecheck and return 200 but are wrong (dead DB columns, silent query failures, fake stats).
The-DevOps-Daily/devops-daily-skills/plugins/devops-daily-skills/skills/kubernetes-manifest-auditor Skill
0★ repoOpen-source Claude Agent Skills for DevOps engineers, by DevOps Daily — https://devops-daily.com
ahtishamshahzad/agent_dev_flow/.ai/skills/ai-output-review Skill
0★ repoTool-neutral AI Engineering System: 174 reusable skills (installable as Claude Code plugins) for planning and building software with AI agents. Classify → plan → approve → build under quality gates. Works with Claude Code, Codex, Cursor, Windsurf, Copilot & Antigravity. Canonical in .ai/.
coldsolutionz/grill-me-code Skill
0★Codex skill for adversarial code review and implementation-plan grilling
kocieusz/memex/.claude/skills/verify Skill
0★ repoManage Agent Skills across harnesses; Claude Code, Codex, pi, all with symlinks from selected library
YangsonHung/ui-ux-interaction-review/skills/en/ui-ux-interaction-review Skill
0★ repo基于状态机的 UI/UX 交互审查 Agent 技能。
lzx-Bill/Project-Factory-Core/.agents/skills/acceptance-design Skill
0★ repoDocs-first project incubation with 34 composable AI Agent skills—from idea and requirements to architecture, acceptance, and implementation handoff.
coldsolutionz/ghl-browser-audit-tool/grill-me-code Skill
0★ repoRead-only GoHighLevel browser audit tool with AI-agent friendly docs, safety checks, and offline tests
Amal-David/india-itr-filing-skill/skills/india-itr-filing Skill
0★ repoPrivacy-safe Agent Skill for preparing and reviewing Indian income-tax returns
dm1681/skills/skills/orchestrate-olympus Skill
no license0★ repoVersion-controlled agent skills and cross-platform installers
h8nc4y/isolated-worktree-pr-flow Skill
0★Agent skill for Claude Code and Codex: create PRs from a temporary git worktree off origin's default branch when the main checkout is dirty, behind, or shared with other agents - with merge-mode-aware cleanup guards.
control-decks/reality-check/plugins/reality-check/skills/check-assumptions Skill
0★ repoA verification deck for checking sources, assumptions, and concrete targets without replacing the result.
takeshijuan/bounded-review-loop/skills/bounded-review-loop Skill
0★ repoBudget-controlled, evidence-based review and repair for PRs, local diffs, and implementation plans.
CodeByVibes/agents-extras/skills/conventional-commits Skill
no license0★ repoReusable agent skills for automated coding workflows across languages and frameworks.
h8nc4y/gh-stacked-pr-merge-order Skill
0★Agent skill for Claude Code and Codex: merge stacked PRs safely with the gh CLI - retarget children before deleting base branches, confirm MERGED state before branch deletion, and recover auto-closed PRs with supersedes PRs.
Windows git stale lock recovery
h8nc4y/windows-git-stale-lock-recovery Skill
0★Agent skill for Claude Code and Codex: safely recover from stale 0-byte .git/index.lock files left by sandboxed git on Windows - a five-point pre-delete check, TOCTOU-aware bulk cleanup, and --no-optional-locks prevention.
keykovar/skill-fe-code-review/skills/fe-code-review Skill
0★ repoReusable frontend code review skill with Quick, Deep, and Fix Review modes for Codex, Claude Code, and Cursor.
junit/module-quality-reviewer Skill
0★An evidence-driven, platform-independent Agent Skill for reviewing substantial code modules and cross-file features.
zzjiho/espresso/skills/espresso-check Skill
0★ repoMakes your AI agent answer like a briefing to a busy, skeptical boss. Conclusion first, no padding, no agreement it doesn't mean.
hijabcantic-dotcom/app-review-opportunity-research-template/app-review-evidence-research Skill
no license0★ repoAn evidence-led template for turning app reviews into product research hypotheses.
InitusNovus/pcan-validation-skill Skill
0★Agent skill and executable suite for PCAN Classic CAN/CAN-FD functional, stress, recovery, and soak validation.
Gusen1453/creed/skills/commit-and-push Skill
0★ repoA software engineering creed for coding agents — discipline skills for tests, design, and evidence over claims.