Review & quality
19,169 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
Paretofilm/superpowers-gstack/skills/macos-native-review Skill
no license2★ repoAfter a PRD/spec/plan for a macOS app, before implementation: validate the artifact against Apple HIG via WebFetch citations. Asks "is this Apple-native?" — complements pitfall-verification and quality-review.
Paretofilm/superpowers-gstack/skills/pitfall-verification Skill
no license2★ repoAfter any PRD, spec, plan, or code change: verify artifact-specific pitfalls don't apply before declaring done. For ship-worthy changes, auto-chains Codex + a third model house + adversarial synthesis.
Paretofilm/superpowers-gstack/skills/quality-review Skill
no license2★ repoAfter a PRD, spec, or plan, before implementation: hunt perceived-quality pitfalls (silent failures, missing loading/empty states, error recovery, state drift) that make a product feel cheap. Complements pitfall-verification.
Paretofilm/superpowers-gstack/skills/third-lens-review Skill
no license2★ repoAfter Claude self-pitfall + Codex on a ship-worthy/architecture/RT/security/contract change: run a third external model house (distant training distribution → different blind spots) on the patched artifact, then adversarial synthesis.
Atypical-Consulting/claude-legends-review/skills/legends-review Skill
2★ repoUse when the user wants a comprehensive code review from multiple perspectives, or invokes a team-based review combining business, design, and engineering viewpoints with debate and consensus. Trigger this skill whenever the user asks for a "legends review", "team review", "full review", "review from all angles", or wants business + design + engineering perspectives debated together. Also trigger when the user wants Elon, Jobs, AND Linus to review the same code, or asks for a multi-perspective review with debate and consensus. ALSO the home of the suite's shared report layer — trigger to render, regenerate, or merge existing review reports ("regenerate the review report", "combine the reviews", "make an HTML report from this report.json"): the schema reference and generator used by the solo elon/jobs/linus reviews are bundled here (references/report-format.md, scripts/generate_report.py). This is the flagship skill — use it when no single persona is enough.
Atypical-Consulting/claude-legends-review/skills/linus-review Skill
2★ repoUse when the user requests a code review focused on engineering correctness, code quality, and technical rigor. On-demand Linus Torvalds persona review evaluating abstractions, error handling, security, logging/observability, performance, and whether the code is actually good. Trigger this skill whenever the user asks for a "linus review", "linus style", "engineering review", "correctness review", "technical review", deep code quality analysis, or wants to know if their code is actually correct, thread-safe, or maintainable. Also trigger when reviewing error handling, DI patterns, race conditions, or anything where rigorous engineering scrutiny is needed.
launch52-ai/flutter-template/.claude/skills/phone-auth Skill
2★ repoPhone OTP authentication - country data, phone formatting, E.164 validation, rate limiting, retry patterns. Use when implementing phone verification flows. Supports Supabase and custom backends.
launch52-ai/flutter-template/.claude/skills/skill-create Skill
2★ repoCreate and validate Claude Code skills with proper structure, checklists, and validation scripts. Use when creating a new skill, auditing existing skills, or ensuring skills meet quality standards. Generates complete skill scaffolds with SKILL.md, check scripts, guides, and templates.
ForgeyClap/claude-forge/.claude/skills/forge-doctor Skill
2★ repoRun Forge's self-test + secret/leak scan — node --check every source, run all test suites, verify the honesty gate still rejects unknown events, confirm the dashboard SPA is intact, and scan git-tracked files for leaked secrets. Use before shipping, after big changes, or when the owner asks "test everything / does it execute / find leaks".
ForgeyClap/claude-forge/.claude/skills/forge-graded-verify Skill
2★ repoAdvisory GRADED verification for high-stakes answer-quality Forge tasks (RAG/research/scraping/prediction). Use when output quality is subjective and needs per-criterion scoring + actionable feedback — ALONGSIDE (never replacing) forge-verify (structural) and forge-evals (deterministic binary gate). Keywords: graded, rubric, quality, verify, review, answer quality, RAG quality, source grounding.
ForgeyClap/claude-forge/.claude/skills/forge-verify Skill
2★ repoRun Forge's verify-loop — after an agent (or a work package) claims to be done, check whether that claim actually holds against events.jsonl and the ticket store, and send the task back to the agent when it doesn't. Use after every agent/work-package completion in a /forge run, and again at the end of the run before the final report.
ForgeyClap/claude-forge/.claude/skills/ship-readiness Skill
2★ repoADVISORY pre-deploy / pre-handoff checklist (not a blocker). Use when preparing a project for deployment, release, or client/handoff to sanity-check it's genuinely ready — covers websites/landing pages, full-stack apps, APIs, dashboards, n8n workflows, scraping, AI/RAG chatbots, prediction systems, Telegram bots, and business automations. Trigger on "deploy", "ship", "go live", "release", "hand off".
ForgeyClap/claude-forge/plugins/forge/skills/forge-doctor Skill
2★ repoRun Forge's self-test + secret/leak scan — node --check every source, run all test suites, verify the honesty gate still rejects unknown events, confirm the dashboard SPA is intact, and scan git-tracked files for leaked secrets. Use before shipping, after big changes, or when the owner asks "test everything / does it execute / find leaks".
ForgeyClap/claude-forge/plugins/forge/skills/forge-graded-verify Skill
2★ repoAdvisory GRADED verification for high-stakes answer-quality Forge tasks (RAG/research/scraping/prediction). Use when output quality is subjective and needs per-criterion scoring + actionable feedback — ALONGSIDE (never replacing) forge-verify (structural) and forge-evals (deterministic binary gate). Keywords: graded, rubric, quality, verify, review, answer quality, RAG quality, source grounding.
ForgeyClap/claude-forge/plugins/forge/skills/forge-verify Skill
2★ repoRun Forge's verify-loop — after an agent (or a work package) claims to be done, check whether that claim actually holds against events.jsonl and the ticket store, and send the task back to the agent when it doesn't. Use after every agent/work-package completion in a /forge run, and again at the end of the run before the final report.
ForgeyClap/claude-forge/plugins/forge/skills/ship-readiness Skill
2★ repoADVISORY pre-deploy / pre-handoff checklist (not a blocker). Use when preparing a project for deployment, release, or client/handoff to sanity-check it's genuinely ready — covers websites/landing pages, full-stack apps, APIs, dashboards, n8n workflows, scraping, AI/RAG chatbots, prediction systems, Telegram bots, and business automations. Trigger on "deploy", "ship", "go live", "release", "hand off".
Fergius-Engineering/instincts/skills/feasibility-guard Skill
2★ repoUse when about to build or agree to build a feature, test, or check, especially when the request sounds big or clever.
Fergius-Engineering/instincts/skills/independent-review-gate Skill
2★ repoUse when about to call complex or shippable work done, or before merging.
Fergius-Engineering/instincts/skills/verify-against-code Skill
2★ repoUse when about to assert any factual claim about what code or a product does - in an answer, a doc, a commit message, or anything a user will see.
fagemx/prismstack/.claude/skills/self-check Skill
2★ repoAudit Prismstack's own skills using its own 15D quality rubric. Trigger: "check our skills", "self audit", "eat our own dog food", "self-check" Do NOT use when: checking a user's domain stack (use the product /skill-check for that)
fagemx/prismstack/skills/skill-check Skill
2★ repoPrismstack 的品質審查 meta-skill。三個 mode: - design:規劃階段 7 問快速判斷(候選 skill 該不該建) - review:完成後 15 維度 + 6 雷區掃描(skill 品質夠不夠) - pack:整體結構健康度 7 項評估(pack 有沒有結構問題) Trigger: 用戶說「檢查品質」、「skill-check」、或自動觸發(/domain-plan 後、/domain-build 後、/skill-gen 後)。 Do NOT use when: 要改 skill 內容(用 /skill-edit)。
PuckAPI/claude-sports-analytics/skills/walk-forward-validation Skill
2★ repoThe correct evaluation methodology for time-series sports prediction models. Use when user asks about model validation, cross-validation, train/test split, accuracy evaluation, overfitting detection, or statistical significance of sports model results. Refuses to run k-fold cross-validation on time-series data -- always redirects to walk-forward. Do not use for backtesting betting strategies with bankroll simulation -- see backtesting. Do not use for building the model itself -- see model-building.
The same file is in 1 other repository
RockyHong/super-bootstrap/plugins/super-bootstrap/skills/commit Skill
2★ repoCommit the current session's changes only, gateway-inline. Session-isolated (never -A), doc-sync-gated. The gateway runs the commit inline — it already holds the diff, session file list, and change intent; only the doc-sync scan dispatches, and only when a mechanical grep-gate shows the diff touches the doc surface. Conventional message, commits directly, offers push on explicit confirmation. Bundled with super-bootstrap — encodes the harness commit rules.
RockyHong/super-bootstrap/plugins/super-bootstrap/skills/merge Skill
2★ repoAbsorb one or more feature branches into the base branch. Recommends merge vs rebase per branch. On conflict, aborts that branch + surfaces the file list + stops. Resolution out of scope; routes to the harness-named conflict-resolution agent or the user.
spideynolove/claude-code-in-action/00-materials/claude-howto/03-skills/code-review Skill
2★ repoComprehensive code review with security, performance, and quality analysis. Use when users ask to review code, analyze code quality, evaluate pull requests, or mention code review, security analysis, or performance optimization.
atuljha23/holocron/skills/pr-review-rubric Skill
2★ repoStaff-level PR review rubric — correctness, contract, clarity, tests, blast radius. Use when reviewing code (yours or others') before merge.
jperrello/C0BALT_CUT/.claude/skills/first-span-feedback Skill
no license2★ repoThe pre-fanout LEARNING GATE. start.sh finishes SPAN 0 alone (through the normal edit/captions/completion chain) before any lane launches, then this skill records a shot-scraper `video` demo of a generated per-span REVIEW PAGE (the 9:16 player + the grade/tier + the retention signals with the failing one flagged), has a Claude reviewer WATCH it via a contact sheet (like director-pass), and — when the reviewer names a SYSTEMIC defect that clears a hard three-gate re-verify (re-render span 0, grade≥prev + flagged signal cleared, re-record + re-review defect-gone) — makes a PERMANENT codebase change and commits only the fixer's paths, so every later span in the run and every future run inherits the fix. NON-FATAL everywhere (missing shot-scraper / record fail / parse fail / rejected gate / push fail all leave span 0 and the code untouched, exit 0). Idempotent via .fsfmeta. Gated by FIRST_SPAN_FEEDBACK (default 1), bounded by FSF_MAX_ITERS (default 1). Wired into start.sh / shorts.sh; autopilot.sh inherits it.
jperrello/C0BALT_CUT/.claude/skills/qc-clip Skill
no license2★ repoSanity-check a rendered short with ffprobe. Verifies duration is in range and file size is non-trivial. Pass/fail boolean plus a short reason. Use as a final gate before saving a render.
jperrello/C0BALT_CUT/.claude/skills/style-gate Skill
no license2★ repoThe online VERIFY half of the style-replication loop — the first-span-feedback discipline with a different oracle (match against the Group C exemplar corpus in references/targets.json) and a different sensor (a sidecar-free Style Profile of the DELIVERED span-0 pixels via profile-clip, never our plans). On a levered-field mismatch (|z| > SG_Z vs the corpus distribution) it runs a bounded knob-first fix loop — moves.py maps the worst mismatches to CLAMPED ephemeral env deltas (JUMP_CUT_SEG, JUMP_CUT_MAX_GAP, SPEED, SWITCH_SPACING) in work/<id>/style.env, the entrypoint-owned SG_RERENDER_CMD re-renders span 0 with them, and the fix is accepted only when accept.py passes (no checked field worse, at least one improved, no new mismatch) AND span 0's grade.json did not regress (reuses first-span-feedback's check_grade.py). Accepted knobs steer spans 1..N (the entrypoint sources style.env before fan-out) and land in references/accepted.jsonl; mismatches no knob can reach are SURFACED for an operator-approved durable code change. Self-arming — no corpus targets or n < SG_MIN_REFS → exact no-op, so the stock pipeline is unchanged until a corpus is learned. NON-FATAL everywhere, idempotent (.sgmeta), STYLE_GATE=0 force-disables.
jperrello/C0BALT_CUT/.claude/skills/verify-bookends Skill
no license2★ repoPost-edit verification of a short's opening and closing 1.5s. Claude sees a 3-frame strip from each end plus the trimmed transcript text around each end and returns {action:keep}, {action:trim,t0,t1} (inward-only), or {action:drop,reason}. Checks three things — (1) cleanliness (partial words, breath cutoffs, off-shot frames); (2) opening-hook strength (snap t0 inward to a stronger hook line if the first 3s is pure setup); (3) payoff landing (snap t1 to ~80ms past the payoff word when the tail trails into filler). Runs after tighten-pace, before fit-vertical. Inward-only — bookend-trim's outward pass already had its chance. Drops the span only on cleanliness failures requiring >2s of trim — never on hook-weakness alone.
jperrello/C0BALT_CUT/.claude/skills/verify-coherence Skill
no license2★ repoPost-pick gate that re-reads each picked span's transcript and either keeps it as-is or tightens its [t0,t1] to cover only the dominant topic. Prevents shorts that feel like two unrelated clips spliced together.
jperrello/C0BALT_CUT/.claude/skills/verify-completeness Skill
no license2★ repoArc-completeness gate. Re-reads each picked span's ASSEMBLED arc (the words inside its cuts) plus a tail lookahead and asks Claude whether the short LANDS as a standalone story — setup → turn → real landing, not an abrupt "so what?" stop. When the payoff is cut off but recoverable in the immediate source tail, it nudges t1 (and the last cut's end) OUTWARD to the landing sentence, within dmax. The outward counterpart to verify-bookends (inward-only). Runs after bookend-trim, before cut-clip, in SOURCE coordinates. Non-fatal, idempotent, disable with VERIFY_COMPLETENESS=0.
multiplex-ai/muggle-ai-teams/skills/django-verification Skill
2★ repoVerification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
The same file is in 2 other repositories
multiplex-ai/muggle-ai-teams/skills/laravel-verification Skill
2★ repoVerification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.
The same file is in 1 other repository
multiplex-ai/muggle-ai-teams/skills/security-review Skill
2★ repoUse this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
The same file is in 1 other repository
multiplex-ai/muggle-ai-teams/skills/springboot-verification Skill
2★ repoVerification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
The same file is in 7 other repositories
multiplex-ai/muggle-ai-teams/skills/verification-loop Skill
2★ repoA comprehensive verification system for Claude Code sessions.
The same file is in 8 other repositories
lbk-open/super-spec/skills/ss-code-review Skill
2★ repoUse for a comprehensive code review of a diff — standalone (a pull request, a SHA range, or the current branch) or as the post-coding review step invoked by ss-coding. Dispatches independent subagents for general code quality, coding-standard compliance (global, stack, and project level, plus OpenSpec compliance when specs are present), and, in post-coding mode with enough scope, a cross-task integration review; then filters by confidence, deduplicates, and produces one consolidated verdict.
lbk-open/super-spec/skills/ss-coding-workflow Skill
2★ repoExecutes a ready-made plan or a plain-language change instruction end to end — branch, multi-agent coding with built-in review, and PR/commit delivery. Use for running an existing execution plan or a simple, well-scoped code change; use ss-feature-workflow instead when a proposal and plan still need to be drafted.
lbk-open/super-spec/skills/ss-create-branch Skill
2★ repoUse when starting new development work to cut a properly named branch from the remote default branch, decide whether to develop it in an isolated git worktree, push it immediately, and set up upstream tracking. Takes a branch name, a requirement link, or a plain-language description as input.
lbk-open/super-spec/skills/ss-create-pr Skill
2★ repoUse once coding and code review are complete and it's time to open a pull/merge request. Runs pre-flight checks (tests, cleanup scan), rebases onto the target branch, verifies again if the rebase changed anything, then opens a PR on GitHub (via gh) or an MR on GitLab (via glab) depending on the repository's remote. Falls back to a local conventional-commit summary if there's no remote or forge CLI available, or if the user declines — that fallback is a normal outcome, not a failure.
lbk-open/super-spec/skills/ss-feature-workflow Skill
2★ repoEnd-to-end feature delivery — takes a PRD, requirement description, or requirement doc link and orchestrates branch creation, a complexity-gated technical proposal (complex requirements only), execution plan, multi-agent coding with built-in review, and PR/commit delivery. Use only when the user explicitly asks for the full feature pipeline, not for a single edit or question.
lbk-open/super-spec/skills/ss-proposal Skill
2★ repoUse when you have a PRD or requirement description and need a complete technical proposal before writing any code. Filters the requirement down to this repository's boundary, analyzes the existing architecture and conventions, and produces a Markdown proposal covering architecture, data flow, key interfaces, alternatives, risks, and milestones — gated by a self-review and, when available, an independent reviewer pass.
lbk-open/super-spec/skills/ss-troubleshooting-workflow Skill
2★ repoEnd-to-end defect fix — takes an issue link, alert ID, or problem description and orchestrates root-cause investigation, human confirmation, branching, a fix plan, multi-agent coding with built-in review, and PR/commit delivery. Use only when the user explicitly asks for the full diagnose-to-delivery pipeline, not for diagnosis alone.
ViktorsBaikers/DevRites/pack/.claude/skills/devrites-source-driven Skill
no license2★ repoVerify uncertain framework/library behavior against official docs or installed source before relying on it. Use when the user says "check the docs", "verify this assumption", or hits an unfamiliar API. Not for internal code.
ViktorsBaikers/DevRites/pack/.claude/skills/rite-review Skill
no license2★ repoReview polished feature diff for correctness, readability, architecture, security, tests proving acceptance, Critical/Important findings, and quality dimensions before seal.
ViktorsBaikers/DevRites/pack/.claude/skills/rite-ship Skill
no license2★ repoShip the sealed feature: commit, push, tag, archive, close. Use when the user says "ship it", "push the branch", "tag the release", or "close the task" after /rite-seal GO. Not for GO/NO-GO readiness.
ViktorsBaikers/DevRites/pack/generated/claude/skills/devrites-source-driven Skill
no license2★ repoVerify uncertain framework/library behavior against official docs or installed source before relying on it. Use when the user says "check the docs", "verify this assumption", or hits an unfamiliar API. Not for internal code.
ViktorsBaikers/DevRites/pack/generated/claude/skills/rite-review Skill
no license2★ repoReview polished feature diff for correctness, readability, architecture, security, tests proving acceptance, Critical/Important findings, and quality dimensions before seal.
ViktorsBaikers/DevRites/pack/generated/claude/skills/rite-ship Skill
no license2★ repoShip the sealed feature: commit, push, tag, archive, close. Use when the user says "ship it", "push the branch", "tag the release", or "close the task" after /rite-seal GO. Not for GO/NO-GO readiness.
ViktorsBaikers/DevRites/pack/generated/codex/skills/rite-review Skill
no license2★ repoReview polished feature diff for correctness, readability, architecture, security, tests proving acceptance, Critical/Important findings, and quality dimensions before seal.
ViktorsBaikers/DevRites/pack/generated/codex/skills/rite-ship Skill
no license2★ repoShip the sealed feature: commit, push, tag, archive, close. Use when the user says "ship it", "push the branch", "tag the release", or "close the task" after $rite-seal GO. Not for GO/NO-GO readiness.
citedy/skills/skills/code-review-agent-team Skill
2★ repoParallel multi-agent code review using Agent Teams with 4 specialized reviewers. Spawns a coordinated team of security, performance, test coverage, and code quality agents. Teammates can share findings with each other for cross-domain insights. Produces unified report with severity-ranked findings saved to /output/. Requires Claude Code with Agent Teams support (TeamCreate, TaskCreate, SendMessage). Use when asked to: - "review code", "code review", "check my changes", "review PR" - "security review", "performance review", "test coverage check" - "full code review", "multi-agent review", "parallel review" Examples: - `/code-review-team` -- review uncommitted changes (git diff) - `/code-review-team 42` -- review PR #42 - `/code-review-team --scope=security` -- security-only review of uncommitted changes - `/code-review-team 42 --scope=performance,tests` -- specific reviewers for PR
The same file is in 2 other repositories
hajibabaie/combinatorial-optimization-skills/skills/branch-and-bound Skill
2★ repoWhen the user wants to implement a custom branch-and-bound algorithm — designing bounding functions, branching rules, node selection (depth-first vs best-first), dominance rules, and incumbent management — or to decide when custom B&B beats a MIP solver. Also use when the user mentions "custom branch and bound," "bounding function," "branching rule," "node selection," "best-first search," or when the bounding relaxation is combinatorial rather than an LP. For solver-internal B&B and MIP gaps, see integer-programming-techniques; for branch-and-price trees, see column-generation.
hajibabaie/combinatorial-optimization-skills/skills/git-for-research-code Skill
2★ repoWhen the user wants to version-control optimization research code - small commits per experiment change, tags for paper result snapshots, .gitignore for solver logs, linking result tables to commit hashes, and branch strategy for risky refactors. Also use when the user mentions "git workflow," "version control research," "tag results," "reproducible experiments git," "gitignore solver," or when a paper number must trace to an exact code state. For repository layout, see optimization-project-structure; for tidy result tables, see pandas-experiment-management.
Optimization project structure
hajibabaie/combinatorial-optimization-skills/skills/optimization-project-structure Skill
2★ repoWhen the user wants to organize optimization research code into a reproducible project — separating the src package, scripts, configs, and results; JSON/YAML config systems; factory registration of algorithms and problems; seed discipline; atomic result writing; and light testing. Also use when the user mentions "project structure," "research code organization," "config file," "factory pattern," "reproducible runs," or "random seed," or when results can no longer be traced to the exact code and parameters that produced them. For result tables and aggregation, see pandas-experiment-management; for commit and tag discipline, see git-for-research-code.
hajibabaie/combinatorial-optimization-skills/skills/solution-validation-testing Skill
2★ repoWhen the user wants to verify optimization code: independent feasibility checkers, objective recomputation separate from the solver, unit tests for constraint builders and operators, known-optimum regression tests, and exact-vs-heuristic cross-validation on small instances. Also use when the user mentions "validate solution," "feasibility checker," "test optimization code," "verify objective," "regression test optimum," or when a heuristic appears to beat a proven optimum. For repairing infeasible solutions, see constraint-handling-techniques; for seeded test instances, see instance-generation-and-benchmarks.
2389-research/git-repo-prep/skills/review Skill
2★ repoUse when auditing a codebase for openness, checking for secrets, missing docs, or gaps before public release. Re-runnable at any point.
cubha/claude-workflow-plugins/plugins/design-lint/skills/design-lint Skill
2★ repo결정론적(no-LLM) 디자인 안티패턴 린터. 렌더된 HTML/CSS(또는 standalone 프로토타입 HTML, 라이브 URL)를 DESIGN-TOKENS.md Ground Truth 대비 검사해 토큰 위생·색/폰트/스페이싱 일관성·AI-default 클리셰(beige 배경·text gradient·uppercase eyebrow 등)를 pass/fail로 판정한다. LLM 디자인 리뷰는 비재현적이라 게이트로 못 쓰지만 이 스킬은 동일 입력→동일 판정·0토큰이라 CI/파이프라인 게이트로 쓸 수 있다. '/design-lint', '디자인 린트', '디자인 검사', '토큰 위생 검사', 'design-lint', '안티패턴 검사', 'AI-default 검사', '디자인 일관성 검사' 언급 시, 그리고 리팩토링/리디자인 파이프라인이 시각 산출물을 검증할 때 호출한다.
The same file is in 2 other repositories
cubha/claude-workflow-plugins/plugins/ship/skills/ship Skill
2★ repo현재 브랜치의 변경사항을 commit → push → PR 생성 → merge → 브랜치 정리까지 한 번에 처리한다. develop 브랜치가 있으면 git-flow(feature→develop→main), 없으면 GitHub Flow(feature→main)로 자동 적응하고, 머지 전 기능 게이트+보안 스캔+DB 검토+민감파일 차단을 실행한다. '/ship', 'ship', '배포해줘', '커밋하고 머지까지' 등 언급 시 호출
The same file is in 2 other repositories