Review & quality
19,016 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
LuisHiluy/claude-code-pipeline-skills/go-loop Skill
0★ repoClose the AI media iteration loop autonomously. Generate → verify via quality gate → auto-regen items below threshold → build composite → commit → notify. Use whenever the user finishes a generation batch, says "go", "go loop", "ship it", "close the loop", "run the loop", or asks to automate the generate-verify-regen-commit cycle for AI images or video. Even when the user just says "finish this batch", "we're done generating", or appends /go-loop to any prompt, trigger this skill to close the loop properly without babysitting. Applies Boris Cherny's /go pattern to AI media pipelines.
LuisHiluy/claude-code-pipeline-skills/verify Skill
0★ repoRun CLIP-based quality scoring on AI-generated image frames against configurable thresholds. Returns a GOOD / PASS / FAIL verdict with per-metric breakdown (prompt match, character similarity, palette match, composite). Use whenever the user generates an AI frame and needs objective quality feedback, says "verify", "check quality", "CLIP score", "does this pass", "score this frame", "is this good enough", or is iterating on an AI image pipeline. Trigger this skill as the quality gate between generation and the next step in any AI media loop.
r-bart/scribetronic/packages/cli/templates/claude-code/.claude/skills/ai-slop-check Skill
0★ repoDetection pass for AI-generated patterns and clichés. Final check before publishing. Returns a list of detected issues with severity and fix suggestions.
The same file is in 1 other repository
r-bart/scribetronic/packages/cli/templates/claude-code/.claude/skills/review Skill
0★ repoParallel review of a draft along multiple focuses (voice, structure, slop, hook, closer, optional factual). Spawns N subagents concurrently — each with a single focus and the user's writing-style — then aggregates findings into one severity-grouped report. Use full mode mid-draft or as a pre-publish gate; use delta mode (--since-last / --since <ref>) to review only what changed since the last snapshot or git ref — 3 focuses instead of 5, ~5s instead of ~10s, ~80% fewer tokens.
The same file is in 1 other repository
rodrijuarez/mtg-argentina-skills/mtg-sealed-price-check Skill
0★ repoVerify whether an Argentine sealed MTG product (Collector Booster Box, Play Booster Box, Bundle, etc.) is fairly priced by comparing against current US market price. Use when the user shares a price list from an Argentine MTG store or asks "is X a good price?".
y-a-v-a/skills/grill-me Skill
0★ 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".
y-a-v-a/skills/stern-code-review Skill
0★ repoUse this skill when the user asks for a rigorous, blunt, senior-level code review focused on correctness, maintainability, production risk, unnecessary abstraction, weak tests, security issues, and operational failure modes. Do not use it for brainstorming, greenfield implementation, or purely stylistic feedback.
y-a-v-a/codex-executor/skills/codex-review Skill
0★ repoCross-model code review with OpenAI Codex. A different model reviews the diff, findings are triaged by severity, and contested findings are reconciled with Codex before you act — so Claude-authored changes get reviewed without self-review bias.
nakane1chome/claude-skills/skills/review-skill Skill
0★ repoReviews a SKILL.md file or skill directory for quality, correctness, and alignment with Claude Code skill conventions. Use when you've written a new skill and want to check it before committing, or when evaluating an existing skill for improvements.
nakane1chome/claude-skills/skills/review-steps Skill
0★ repoStructured review for polishing documents. Fixes language, improves clarity, checks structural consistency, and compares against best practice. Use when a draft has structure but needs a thorough review pass.
The same file is in 1 other repository
nakane1chome/claude-skills/skills/sdlc-cross-review Skill
0★ repoReview a document against its SDLC lifecycle context — assess completeness and check consistency with parent documents in the document hierarchy.
The same file is in 2 other repositories
Finishing a development branch
zjy1020/claude-code-skills/skills/finishing-a-development-branch Skill
0★ 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
zjy1020/claude-code-skills/skills/using-git-worktrees Skill
0★ repoUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
The same file is in 13 other repositories
Verification before completion
zjy1020/claude-code-skills/skills/verification-before-completion Skill
0★ repoUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
The same file is in 40 other repositories
Clinical-Quality-Artifical-Intelligence/nhs-clinical-safety-skills/skills/plan-clinical-review Skill
no license0★ repoClinical product direction review from a UK nursing perspective. The CQAI equivalent of /plan-ceo-review — asks the hard clinical questions before any technical planning. Reviews NMC Standards alignment, patient safety classification, health equity impact, and the "Ward Test". Use this INSTEAD of /plan-ceo-review for any nursing or clinical tool.
Clinical-Quality-Artifical-Intelligence/nhs-clinical-safety-skills/skills/review-clinical-safety Skill
no license0★ repoClinical safety code review against DCB0129/DCB0160 and NHS Digital standards. This is NOT a general code review — it is a clinical safety audit for tools handling clinical data, calculations, decision support, or patient-facing information. Produces a hazard register, required mitigations, and a release recommendation.
Clinical-Quality-Artifical-Intelligence/nhs-clinical-safety-skills/skills/review-fhir Skill
no license0★ repoFHIR Implementation Guide and resource review — terminology, profiling, and compliance audit for UK NHS FHIR projects. Covers FHIR R4 conformance, UK SNOMED/dm+d/LOINC terminology binding, UKCore/CareConnect compatibility, nursing-specific profiling (NEWS2, Waterlow, ADPIE), and IG structure. Produces a scored compliance report.
alexe-ev/product-plugins/product-ops/skills/run-cross-functional-review Skill
0★ repoDesign and facilitate a cross-functional product review that builds alignment across teams. Use this skill when a product decision or initiative needs structured review and input from multiple functions.
deokjinlog/intent-locked-workflow/skills/auto-executing-plans Skill
0★ repoauto-flow 4단계 (마지막) — implementation-plan.md 읽기 + Entry Guard (preflight.subagent_task_entry_check) + DAG 자동 build + 무조건 wave-parallel subagent 강제 (Gate #14 override) + failure isolation 그대로 + End-of-run consolidator 자동 + finishing-a-development-branch 자동 호출. AskUserQuestion 호출 X — clarifying Q 는 prose 질의다 (본문 Anti-Patterns 와 CLAUDE.md 정본). generating-html 은 Step 4.5 fire-and-forget dispatch (v2.3.2+ — v1.1.17 '호출 부재' 룰이 반전됨).
deokjinlog/intent-locked-workflow/skills/executing-plans Skill
0★ repoUse when you have a written implementation plan (<slug>-implementation-plan.md) to execute in a separate session with review checkpoints. intent-locked-workflow extension — picks git-fast mode (default, uses `git diff HEAD` against working tree pre-commit for before/after extraction so per-edit Read snapshot is skipped; commits code per task; the plan log is appended once at end-of-run, Phase 3) or memory-fallback mode (when no git or commits forbidden). Per-edit: risk-annotation 3-checklist + RISK comments. Per-task: ONE consolidated change-history [코드-수정] entry, drastically reducing 구현계획서.md Read/Edit cost.
Finishing a development branch
deokjinlog/intent-locked-workflow/skills/finishing-a-development-branch Skill
0★ repoUse when implementation is complete and tests pass. Runs the test gate one final time and emits a single termination message; user manually decides merge / PR / keep / discard. (v1.1.14 슬림화 — AskUserQuestion 게이트 + boilerplate 제거)
deokjinlog/intent-locked-workflow/skills/receiving-code-review Skill
0★ 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
deokjinlog/intent-locked-workflow/skills/requesting-code-review Skill
0★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
Verification before completion
deokjinlog/intent-locked-workflow/skills/verification-before-completion Skill
0★ repoUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
The same file is in 40 other repositories
deokjinlog/intent-locked-workflow/skills/verifying-spec Skill
0★ repoUse immediately after writing <slug>-tech-design.md (via tech-design) or <slug>-implementation-plan.md (via writing-plans), before final user handoff. Performs main-agent self-verification — A) consistency cross-check between target MD and all upstream MDs, plus C) code impact analysis (file existence, callers, side-effect candidates) — and produces a structured 4-axis report for user decision.
clever-cc-plugins/cc-concept/plugins/cc-concept/skills/cc-concept-performance-review Skill
0★ repoUse this skill to review whether a strategic concept's bets actually played out — a positioning claim, a channel allocation, a content-strategy pillar mix, a GTM milestone, or a campaign's stated goals. Invoke when the user says "review our strategy performance", "did our positioning hold up", "how did the campaign perform against plan", "review the channel mix results", or "strategic performance review". Works from whatever performance data the owner pastes in — there is no analytics API integration. Do NOT use it to analyze how an individual content piece performed structurally or tonally — that is cc-content-performance-review's job, a different plugin's skill at the content-piece altitude, not the strategy altitude.
azadmotala/claude-code-team-builder/examples/saas-dashboard/.claude/skills/review Skill
0★ repoCode review for TenantFlow. Checks security, correctness, and quality. Focuses on tenant isolation, Stripe webhooks, and Clerk auth.
telefrek/vallorcine/skills/spec-verify Skill
0★ repoVerify a spec against its implementation and repair violations
bokuwalily/claude-code-skills/skills/autonomous-build-verify Skill
0★ repo自律ビルドセッション(大規模な機能実装・スクレイパー構築・フルスタックアプリ生成など)の完了宣言前に実行する出力検証チェックリスト。「完成」と報告した後にダミーデータや未デプロイ変更が発覚するパターンを防ぐ。
bokuwalily/claude-code-skills/skills/git-commit-helper Skill
0★ repoConventional Commits 形式(feat/fix/docs/style/refactor/perf/test/chore/ci/build/revert)で commit message を作成・検証する。発火: git commit 失敗 (validator 弾き)、複雑な変更を分割 commit する時、PR タイトル設計時
Git prepush secret remote check
bokuwalily/claude-code-skills/skills/git-prepush-secret-remote-check Skill
0★ repogit pushやパブリック公開の直前に実行する。リモートURLが自分のリポジトリを指しているか確認し、ステージ・差分内のAPIキー/トークン/PII漏洩をスキャンする。複数セッションで「サードパーティforkへのwrong-remote」と「PII流出」が実際に発生したことへの対策。
bokuwalily/claude-code-skills/skills/human-review-gate-shell Skill
0★ repoバッチ生成したファイル(記事・コード・レポートなど)をシェルで対話的に1件ずつレビューし、approve/skip/reject/editで振り分けるゲートスクリプトを作るとき。
Llm content pipeline quality gate
bokuwalily/claude-code-skills/skills/llm-content-pipeline-quality-gate Skill
0★ repoLLMでコンテンツを自動生成し、品質スコアが閾値未満なら棄却・再生成するパイプラインをシェルスクリプトで組むとき。claude -p による1コール生成→スコア抽出→閾値ゲート→型/テーマローテーションログまで一連を含む。
bokuwalily/claude-code-skills/skills/phaser-mcp-verify-throttled Skill
0★ repoブラウザMCP(claude-in-chrome等)でPhaser3ゲームを自動検証する際、対象タブが非フォアグラウンドでRAFスロットリングされゲームループが止まり、delayedCall/シーン遷移が発火しない/待っても進まないとき
bokuwalily/claude-code-skills/skills/responsive-overflow-guard Skill
0★ repoWebフロントのレイアウト/CSS/Tailwindを編集したら発火。スマホ表示の横スクロール溢れ・中央ズレを、頼まれる前に機械検出して直す。Next/React等のレスポンシブUI変更時に必須
bokuwalily/claude-code-skills/skills/tsc-build-check Skill
0★ repoTypeScript/Next.js プロジェクトで commit/push 前に行う型チェック→ビルド検証の標準パターン。発火: TS プロジェクトで `tsc --noEmit` `npm run build` 連続呼び出し時、CI失敗時、本番デプロイ前のローカル verify
bokuwalily/claude-code-skills/skills/vercel-commit-author-blocked Skill
0★ repoVercelのデプロイが完了せず status UNKNOWN のまま固まり、本番に反映されない時の診断と解除。特に git author を変えた直後(匿名化・別ハンドル化)に発生する COMMIT_AUTHOR_REQUIRED ブロックの対処。
jorgenosberg/shakespeare/skills/shakespeare-review Skill
0★ repoReview a pull request or diff and return ornate, Early Modern English comments — one per finding, each anchored to `file:line`. Use when the user types /shakespeare-review or asks for a "bard review". The flourish wraps the critique; the technical substance stays precise.
zeybek/apex/plugins/apex/skills/apex-review Skill
0★ repoUse this skill when asked to review code, a diff, pull request, patch, migration, design implementation, or repository change. Perform a language- and framework-independent, risk-first review for correctness, security, data integrity, concurrency, compatibility, reliability, maintainability, performance, and missing verification. Report actionable findings by severity and location; do not use it to implement fixes unless explicitly requested.
specdd/plugin-claude/skills/specdd-review Skill
0★ repoUse when Claude Code needs to review changes against active SpecDD specs.
opendatadiscovery/odd-team/.claude/skills/doc-gap-check Skill
0★ repoRun the doc-gap-finder reducer subagent over the per-node enrichment sidecars + the concept catalog + the live documentation site. Produces or refreshes `lineage/{repo}/doc-gaps.md` — a ranked list of DOC-NNN candidates (broken URLs, missing anchors, code-doc drift, missing pages, coverage gaps, stale pages) with full citations the maintainer triages into the backlog.
opendatadiscovery/odd-team/.claude/skills/panel Skill
0★ repoRun the methodology meta-review — a single methodology-reviewer agent that traces the whole current methodology (APPROACH.md, the ADRs, the agent contracts, the skills, the playbooks, the case-law, the live artefacts), diffs against the prior review, runs fresh blind spot-checks against real source, and emits real gaps + improvement proposals at lineage/{repo}/meta-reviews/{date}/review.md. `/panel` runs it; `/panel --show` prints the latest; `/panel validate` runs the acceptance-corpus check.
opendatadiscovery/odd-team/.claude/skills/review Skill
0★ repoVerify a `review-ready` work item (or an entire batch) meets every acceptance criterion and every Quality Bar gate. Reject by default — each check requires cited evidence. Must run in a session distinct from the `/implement` session that produced the item.
Saturate/skills/make-pr Skill
no license0★ repoCreates pull requests on GitHub or Azure DevOps by analyzing commits and generating descriptions. Detects platform from git remote and uses gh CLI or az CLI. Use when asked to create PR, open PR, make pull request, submit PR, create pull request, new PR, raise PR, push PR, open pull request, submit changes, PR workflow, or when user mentions PR creation. Generates casual, context-aware PR descriptions that explain WHY not WHAT.
Saturate/skills/pr-review Skill
no license0★ repoPerforms comprehensive code reviews checking for bugs, security issues, performance problems, testing gaps, and code quality. Accepts branch names or PR URLs (GitHub/Azure DevOps) to automatically checkout and review. Use when reviewing PRs, pull requests, code changes, commits, diffs, or when asked to review code, check code, audit changes, review my changes, check PR, review branch, or perform code review.
deltafly/doom-cheats-for-claude-code/plugins/doom-cheats/skills/iddqd Skill
0★ repoIDDQD — "god mode" / invincibility. A bulletproof safety-harness mode for risky or hard-to-reverse work: it FIRST creates a real restore point (runs a bundled script — git stash-create snapshot, or a timestamped .bak), ONLY THEN touches anything, then verifies hard (tests, running the app, adversarial self-review of the diff), and only calls it done after verification — on failure it says so honestly and offers a rollback. Use when the user types /iddqd, or asks to "make this bulletproof", "god mode", "don't let it break", "safety net", "add a guard", or in Hungarian "csináld golyóállóra", "nehogy eltörjön", "biztonsági háló", "ne basszunk el semmit" — and proactively before any dangerous, wide-reaching or hard-to-reverse change (mass file edits, migrations, deletes, build/deploy config).
gordon1210/agent-goodies/plugins/idea-workbench/skills/review-design-doc Skill
0★ repoEvaluate an existing product or technical design document for comprehension, consistency, risk coverage, and implementation readiness. Use before approval or implementation planning, after substantial design changes, or when a team needs an independent critique that exposes missing decisions, contradictions, unsupported assumptions, unsafe failure modes, and verification gaps without rewriting the source by default.
Honorboxx/crew/skills/crew-verify Skill
0★ repoUse before claiming any work is done, fixed, working, or passing, and before committing or opening a PR. Converts each claim you're about to make into observed evidence from this session, and downgrades anything unproven to "changed but unverified".
kennyolofsson23-netizen/claude-code-config/skills/code-review Skill
no license0★ repoCode Review Plugin
kennyolofsson23-netizen/claude-code-config/skills/code-review/review-local-changes Skill
no license0★ repoComprehensive review of local uncommitted changes using specialized agents with code improvement suggestions
kennyolofsson23-netizen/claude-code-config/skills/code-review/review-pr Skill
no license0★ repoComprehensive pull request review using specialized agents
kennyolofsson23-netizen/claude-code-config/skills/design-review Skill
no license0★ repo7-phase frontend design review with accessibility (WCAG 2.1 AA), responsive testing, visual polish. Use for PR reviews, UI audits, or encountering contrast issues, broken layouts, accessibility violations, inconsistent spacing, missing focus states.
The same file is in 2 other repositories
kennyolofsson23-netizen/claude-code-config/skills/kaizen/plan-do-check-act Skill
no license0★ repoIterative PDCA cycle for systematic experimentation and continuous improvement
kennyolofsson23-netizen/claude-code-config/skills/qa Skill
no license0★ repoFull QA pass: run all tests, check types, catch regressions, write missing tests. Use when the user says "run tests", "QA", "verify changes", "check for regressions", "test everything", or "make sure it works".
kennyolofsson23-netizen/claude-code-config/skills/reflexion/critique Skill
no license0★ repoComprehensive multi-perspective review using specialized judges with debate and consensus building
kennyolofsson23-netizen/claude-code-config/skills/security-review Skill
no license0★ repoSecurity-focused differential code review for PRs, commits, and diffs. Calculates blast radius, checks test coverage, models attacks, and generates markdown reports. Based on Trail of Bits methodology. Use for PR reviews, commit audits, and pre-deployment diff checks. For full codebase audits, use /security-audit instead.
kennyolofsson23-netizen/claude-code-config/skills/ui-design-review Skill
no license0★ repoComprehensive visual design and aesthetics evaluation. Analyzes typography, color, spacing, hierarchy, consistency, branding, and modern design trends for polished, professional interfaces.
kennyolofsson23-netizen/claude-code-config/skills/webapp-testing Skill
no license0★ repoTest and debug local web applications using Playwright. Captures screenshots, verifies UI behavior, checks browser logs, and runs E2E test scenarios. Use when the user says "test the app", "check the UI", "take a screenshot", "debug the frontend", "run E2E tests", "verify the page works", or "Playwright test".
taewanu/skills/skills/in-progress/visual-code-review Skill
0★ repoRender a diff, PR, or slice of code as a single self-contained HTML page: the real diff with inline margin annotations, a flow diagram, key snippets, risks, open questions. Click-to-copy notes round-trip decisions to chat. Two modes: **review** (a change/diff/PR) and **explain** (existing code or a subsystem). Use whenever the user wants a change or codebase made legible visually ("이 diff 설명해줘", "PR 리뷰 보기 좋게 만들어줘", "이 코드 흐름 그림으로", "아키텍처 html로 설명", "walk me through this PR", "explain this diff/PR as html", "visualize this change", "help me understand this module") or is about to dump a long diff as plain markdown. NOT a graded correctness audit: that's `/code-review`; this can lay those findings over the diff.
jimmynotjames/simple-recurring-budgets/.claude/skills/appstore-push-release-build Skill
no license0★ repoBuild and upload the App Store release-candidate build — confirms the release checklist has been worked through, prompts for the new App Store version number, bumps MARKETING_VERSION on a release branch, then runs `fastlane ios beta` so the candidate lands in TestFlight (auto-bumps build number from ASC, archives, uploads, auto-commits the pbxproj bump), then pushes, opens a chore PR, waits for CI, and squash-merges. The same binary is then manually tested via TestFlight and attached to the App Store version in ASC — one build serves both. Does NOT submit for review — that stays a manual App Store Connect step. Use when the release checklist reaches the release-candidate build step, or when asked to push a release build. Invoked via /appstore:push-release-build.