Review & quality
19,284 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
ctoth/sql-skills-plugin/plugins/sql/skills/sql-constraints-and-integrity Skill
no license0★ repo32 agent skills for writing correct, portable, modern standard SQL (ISO/IEC 9075) — vendor-neutral, with per-feature portability across PostgreSQL, MySQL/MariaDB, SQLite, and more.
agentic-workflow-kit/technical-design/skills/enforce-architecture Skill
0★ repoUse when a user wants to enforce architecture boundaries, generate dependency-cruiser or ESLint boundary rules, run enforce-architecture, or convert a settled DDD technical design enforcement map into TS-first CI gates. Requires seeded violations for declared rules so enforcement cannot pass vacuously.
intelligems-io/intelligems-mcp-skills/skills/client-performance-review Skill
0★ repoUse when preparing a monthly or quarterly Intelligems performance review for an agency client, customer, account, or stakeholder meeting.
sina-z/redpen/skills/redpen Skill
0★ repoReviews a code diff the way a calm, veteran reviewer would — catching the embarrassing leftovers before they reach production. Use this skill when the user is about to open, update, or finalize a pull request; when they ask to "review my diff", "check before I push", "red-pen this", or "is this ready to ship"; or any time staged/uncommitted changes should be checked for debug output, commented-out code, unresolved TODOs, placeholder junk, hardcoded local values, stray secrets, or test artifacts left behind. Operates on the DIFF, not the whole repo.
e3742526/agent-skills-for-quality/skills/off-nominal-review Skill
0★ repoReview software and operational workflows using NASA-style nominal versus off-nominal scenario analysis. Use when auditing safeguards, fault management, containment, degraded behavior, and operator-visible handling of unexpected conditions.
Tsurai7/agentic-playbook/skills/create-pr Skill
0★ repoCreate or update GitHub pull requests using gh. Use when the user asks for a PR, or to open/update a pull request after branch work is ready.
gadost/regitize/skills/regitize-date-customize Skill
0★ repoRedistribute Git author and committer dates evenly across a branch, starting at a user-supplied date and ending at today, while preserving snapshots and merge topology. Use when the user invokes regitize-date-customize with a start date, asks to stretch or spread commits over time, or wants historical commit timestamps normalized into a chosen date range.
ballisarium/aiogram-bot-skills/skills/aiogram-bot-verify Skill
0★ repouse after changing aiogram bot code or when verification is requested; проверка, тесты, verify, syntax, imports, no polling, webhook, real token, or network.
bilals2008/bilal-skills/skills/git-leak-prevention Skill
0★ repoScan repositories for sensitive files (.env, secrets, API keys, build artifacts, node_modules, dist, releases) before pushing to GitHub. Automatically fix .gitignore to prevent leaks. Use when the user asks to check for secrets, scan for leaks, fix gitignore, or perform any security-related task.
dianbrown/rocky/skills/rocky-commit Skill
no license0★ repoWrite tight Conventional Commit messages — imperative subject ≤50 chars, body explains why over what, zero filler. The commit text itself stays professional; only the chat around it uses the rocky voice. Use when user invokes /rocky-commit or asks for a commit message.
yeyitech/duty-loops/.agents/skills/duty-loop-reviewer Skill
0★ repoReview a Duty Loop's recent runs for usefulness, notification noise, stale context, missing gates, and over-engineering. Use when Codex should inspect BLUEPRINT.md, state, and logs to suggest small improvements to a long-lived AI worker without turning it into a heavy workflow system.
galaxyuliana/skill-graph/tests/fixtures/claude-home/plugins/cache/demo-market/demo-plugin/1.0.0/skills/critique-diff Skill
0★ repoUse when reviewing a pull request diff to find bugs and style issues in changed files
Kamicyus/skill-forge/skills/deploy-guard Skill
0★ repoProduction deploy guard — runs a git sync-check BEFORE any production deploy and BLOCKS if the working copy is behind or divergent from the canonical branch (stale). Use when the user says "deploy", "production deploy", "ship it", "push to prod", "vercel --prod", or runs any prod deploy command. Prevents the classic stale-branch production incident.
gulmezeren2-byte/industrial-engineering-ai-skills/skills/forecast-accuracy-review Skill
0★ repoEvaluate demand-forecast quality honestly - WMAPE, bias and Forecast Value Added against a naive benchmark over a rolling-origin backtest. Use when the user mentions forecast accuracy, MAPE, demand planning performance, tahmin doğruluğu, talep tahmini, or asks whether a forecasting process or tool is worth it. Differentiator - judges the process (value added vs doing nothing), not just the model.
ZC0325/sol-native-guardrails/plugins/sol-native-guardrails/skills/git-isolation-handoff Skill
0★ repoSafely perform user-authorized Git isolation and delivery operations, including worktrees, branches, commits, pushes, pull requests, merges, and cleanup. Use only when Git workflow changes are explicitly in scope or necessary to carry out the requested development workflow.
angpysha/api2skill/.agents/skills/aot-compat-check Skill
0★ repoPublish Native AOT and check for trim/reflection warnings (IL2xxx/IL3xxx). Use when Native AOT mode is enabled.
tylensthilaire/skill-llm-wiki/skills/llm-wiki-lint Skill
no license0★ repoHealth-check the project's agent-maintained wiki and produce a lint report: dead links, orphan docs, contradictions, stale claims, coverage gaps, index drift, and suspected duplicates. Use this whenever the user asks to lint, health-check, audit, or tidy the wiki or knowledge base; whenever they ask "is the wiki up to date" or "how healthy is the knowledge base"; after any large batch of ingests; and whenever the due check shows a lint is due (no lint entry in the log within the threshold).
ArcanEdge-AI/claude-code-agent-playbook/skills/senior-code-review Skill
0★ repoUse before finalizing a meaningful code change. Reviews the final diff for correctness, scope control, maintainability, validation gaps, safety risk, performance risk, accessibility risk, and subagent claims that still need verification.
The same file is in 1 other repository
silkyland/deep-plan/skills/deep-plan Skill
0★ repoResearch-first, evidence-first implementation planning in seven gated phases: frame the task, inventory the real codebase, verify ground truth from vendor source or official docs, adversarially audit existing code, analyze gaps, commit to design decisions, and write a phased plan document with timeline, risks, and verification. Enforces "no claim without evidence, no design before research". Use when the user asks to plan, design, architect, audit, or review before implementing a feature, refactor, migration, or system, or mentions deep-plan, /deep-plan, or Plan mode.
DeliriumPulse/codetruss-plugins/plugins/codetruss/skills/codetruss Skill
0★ repoOperate CodeTruss local acceptance gates for coding-agent changes. Use when a developer asks to bind an agent task to allowed or denied files, configure repository verification, install or diagnose Claude Code or Codex hooks, review a working-tree or staged diff before commit, interpret or verify a signed CodeTruss receipt, repair a failed verdict, or explicitly opt into provider-backed review or receipt sync.
connorjjarvis/interview-me/review-me Skill
0★ repoA staff-level review copilot for a branch or PR. Reads the diff, gives you a ranked map of review points (correctness, risk, design, tests, security, nits) each with the reasoning and a draftable comment in your voice, then lets you drill into the ones that matter. It does not score you and does not post anything — it helps you understand the code and write the review yourself, and it learns your project's conventions over time. Use when the user says "review me", "review this branch", "review this PR", "help me review", or "help me write a review". (For being interviewed and scored on your own decisions, use interview-me instead.)
DevOtts/review-it/plugins/review-it/skills/deploy-verify Skill
0★ repoStaging/prod deploy verification \u2014 proves the build actually works in the live environment, not that a dashboard says "Ready". Runs the deployed-code ladder (curl the new route, grep served HTML, digest-pin \u2014 merged \u2260 deployable \u2260 deployed), re-runs the Test Contract's [REAL]-tagged cases against the live env under Tier-2 rules, walks the release checklist (rollback, monitoring, feature flags, migration safety, credential hygiene), and emits READY / NOT-READY with per-item evidence. Invoked by /review-it when the target is "staging"/"prod"/a release, or standalone when the user says "verify the deploy", "is it actually live", "pre-release check", "can we ship this".
liftli-ai/skills/skills/ai-sounding-post-checker Skill
0★ repoUse when the user asks "does this sound like AI?", wants a draft humanized, or wants AI tells removed — audits a post for filler openers, tell-vocabulary, and mechanical patterns, then fixes the real problem: what's missing (specifics, stakes, voice), not just the words.
DejusDevspace/my-skills/commit-changes Skill
no license0★ repoCreates well-structured commits from a batch of file changes. Groups files by layer (schema, service, router, etc.) and by side (frontend/backend). Generates an executable commit script with conventional commit messages. USE FOR: finalizing work, creating commits, preparing PRs, organizing changes into logical commits. DO NOT USE FOR: work that hasn't been written yet, mid-work snapshots, or exploratory branches where structure doesn't matter.
adeilsonrbrito/cross-model-consult/consult-grok Skill
0★ repoConsult the Grok Build CLI for an independent, cross-model second opinion on a decision, design, interpretation, diagnosis, or piece of work. Grok Build runs a different model and provider (default: grok-4.5 at high reasoning effort), so its take is genuine divergence — not an echo of your own reasoning, which is what makes it useful. Reach for it on a genuinely hard or high-stakes call: a decision that is costly or hard to reverse, a design or plan worth pressure-testing before committing to it, a risky diff worth an outside review, or a tie between two interpretations you cannot break from the evidence alone. The user may run it explicitly (/consult-grok), but also self-invoke it — without being asked — when an outside perspective would actually change the risk on a hard call. Skip it for trivial lookups, routine edits, and decisions you are already confident in: each consult spends real tokens and a few seconds, so spend it only where cross-model divergence would genuinely change the outcome.
asker26/agent-skills/skills/reviewer-ultra Skill
0★ repoDeep PR review: 3 finder agents (regressions, bugs, code smells) + 3 validators + a root-cause adjudication pass that rejects defensive/monkey-patch 'fixes'. Usage: /reviewer-ultra <PR#> [repo]
CongBao/skill-steward/packages/engine/tests/fixtures/native-inventory/codex/cache/vendor/review/1.2.0/skills/review Skill
0★ repoReview fixture Skill
Kofiloski/ios-release-quality-toolkit/plugins/ios-release-quality-toolkit/skills/ios-ai-ui-check Skill
0★ repoAdd, operate, or debug reproducible iOS Simulator UI checks in GitHub Actions with ios-ai-ui-check. Use when someone asks for AI-planned or deterministic XCUITest checks from a plain-English goal, wants video/screenshots/logs/xcresult artifacts and a PR summary, needs to scaffold an app-owned runner or scenario, or is troubleshooting planner validation, Simulator, runner, artifact-manifest, or pull-request-comment failures. Keep app launch state, fixtures, accessibility identifiers, UI interactions, and assertions in the app repository; keep the reusable action provider-agnostic.
arniesaha/ctxops/skills/blindspot-pass Skill
0★ repoWHEN a plan, spec, or big prompt is about to drive real work and the unknowns haven't been surfaced. Run it before implementation starts. Triggers: 'what am I missing?', 'poke holes in this plan', 'what would you ask me?', 'sanity-check this spec', 'interview me about X', before a handoff prompt. OUTPUT: prioritized questions that would reshape the approach, plus flagged ambiguities, weak assumptions, and undefined behavior. PAIR AFTER: ctx-pack (ground first). PAIR BEFORE: decision-review (pressure-test the reshaped plan). NOT FOR: choosing between options (use decision-review), gathering context (use ctx-pack).
sandev/engineering-os/skills/building-and-delivering/code-review Skill
0★ repoPerform a high-signal code review focused on correctness, design, security, and maintainability, and deliver feedback that is clear and prioritized. Use when reviewing a pull request, examining a diff, or when the user asks for a code review.
soltraveler-sri/Steerable-Protocol/skills/integration-audit Skill
0★ repoAudit an existing or claimed Steerable integration against the canonical SA-CONF conformance checklist, drive the running target through the required live pass, run the anti-pattern recognition sweep, and produce a structured severity-ranked findings report. Use when a user asks to verify, review, gate, or audit a Steerable integration in an unfamiliar codebase, or to check whether a conformance claim holds.
meo9805/mininglamp-oss-octo-spec/templates/octospec-init/.claude/skills/octospec-init Skill
0★ repoUse the FIRST time you bring the octospec engineering standard into a repo that does not have it yet — to onboard octospec / initialize octospec into a fresh checkout. Triggers on requests like "onboard octospec", "initialize octospec", "set up octospec here", "add the octo-spec standard to this repo", 在这个仓库接入 octospec, 启用 octo-spec 标准, 初始化 .octospec。 This is a one-time接入引导: copy the template, pin the global version, run the sync script, confirm the agent-instruction block landed, and self-check with lint. Once the repo already has a working `.octospec/`, stop using this skill — the day-to-day 4-phase flow is owned by the octospec-workflow skill instead.
yuri-semenenko/ai-engineering-workspace/claude-code/.claude/skills/codebase-map Skill
0★ repoOrient fast in unfamiliar code — a new repo, a subsystem you don't own, or a PR touching code you don't know — and produce a short, high-signal map: what it is, entry points, architecture sketch, domain glossary, key seams, risky areas, how to run and test, known tradeoffs. Use for "map this repo", "orient me in this codebase", "where do I start", "help me understand this project", "разберись в репозитории", "с чего начать". Different from Codex project-onboarding / an AGENTS.md pass (that writes durable agent config; this is a read-first orientation for a human or reviewer, and can feed it), /complexity-audit (a whole-tree critique of over-engineering; this is comprehension, not judgment), and /debug (drives a known failure; this orients before you know where anything is).
kadenn/skills/skills/chronos Skill
0★ repoUse reliable wall-clock context to handle deadlines, schedules, elapsed work, return gaps, and long-running execution. Use when timing changes the correct response, the user mentions a deadline or schedule, sustained focus may need a progress check, a long-running approach needs reassessment, or a chronos hook supplies time metadata. Verify current time rather than guessing, and do not trigger for requests where time is irrelevant.
tejask0/agent-skills/check-sentence Skill
0★ repoCheck a sentence, phrase, or short passage for grammatical and semantic errors, verify it is the correct way of expressing the idea in modern English, and suggest a few alternative ways of saying the same thing. Trigger whenever the user says things like "check this sentence", "is this correct English", "check my grammar", "is this the right way to say it", "grammatically correct?", "check if this sounds right", "fix my sentence", or pastes a sentence/phrase and asks if it's fine, correct, or proper. Also trigger when the user shares something they wrote and wants quick language validation — even if they don't use the word "grammar". Do NOT trigger for creative writing or when the user explicitly wants a full rewrite.
JoaoAlavarse/cursor-config/skills/code-review Skill
0★ repoReviews code changes for correctness, security, reliability and maintainability. Use when reviewing pull requests, diffs, or when the user asks for a code review.
prikotov/become-role/examples/skills/style-check Skill
0★ repoCheck a code change for naming, structure, and readability; surface style nits separately from correctness findings.
RTOAI/Convbox-DiagClaw/utilities/config-health-check Skill
0★ repoConvbox-DiagClaw Prof.Skill 的配置与 API 健康自检工具(聚焦凭证与接口连通,区别于店铺「经营健康」分析)。两阶段:校验 CONVBOX_API_KEY 与 access.yaml 是否就绪;对 access.yaml 中全部端点全量探测并按字段定义校验响应 schema。在「报错查不到数据」「上线/换环境前自检」「数据质量与追踪治理」场景由 Prof.Skill 调用。
cristianmoroaica/bountyverdict/skills/check-mcp-tool-drift Skill
0★ repoCompare complete MCP 2025-11-25 tools/list snapshots before accepting a server upgrade or changed tool catalog. Use after notifications/tools/list_changed, at agent startup when a catalog hash differs from the pinned baseline, or before installing, enabling, or repinning a catalog-serving endpoint.
YangsonHung/ui-ux-interaction-review/skills/zh-cn/ui-ux-interaction-review-cn Skill
0★ repo当用户需要审查或重构 UI/UX 交互组件与状态逻辑,并提供 UI 截图、原型图、组件交互描述,或提到交互逻辑、状态设计、开关/Tab/联动、体验优化、设计走查、UI 审查时使用。
dm1681/skills/skills/semantic-pr-review Skill
no license0★ repoPull and explain a GitHub pull request as a source-referenced hierarchy and interactive semantic flowchart with complete execution branches, DTO-labeled handoffs, source-excerpt hover cards, and code-linked details. Use when a user wants to understand a PR, trace its architectural layers, compare execution strategies, inspect boundary or ownership shifts, or receive a standalone interactive walkthrough instead of a flat diff summary.
Zwin-ux/kit/catalog/queue/git-commit Skill
0★ repoWrite clear, honest commit messages and small reviewable commits.
control-decks/reality-check/plugins/reality-check/skills/check-sources Skill
0★ repoVerify the sources supporting the current HACP Working Object, distinguish direct evidence from inference and unknowns, and append a sources-checked annotation without replacing the object. Use only when the user invokes CHECK SOURCES or explicitly asks to verify the current sources.
game-dev-rta-club/rubber-ducking-skill/skills/rubber-duck-partner Skill
0★ repoUse when you are asked as a subagent, thread, rubber-duck partner, double-check partner, critique partner, sparring partner, draft challenger, reviewer, or dialogue partner to inspect another agent's draft, plan, reasoning, judgment, proposed response, or implementation approach. Triggers include rubber ducking, double-check, falsify, challenge, critique, quality improvement, better-nearby checks, deletion candidates, misalignment, assumptions, and final draft review. Respond yourself in the current conversation; do not launch, coordinate, or delegate to another worker.
atomgunlk/skills/skills/engineering/fix-pr-mantra Skill
0★ repoUse when addressing pull-request review comments or feedback — "fix the review comments", "address the PR feedback", "go through the comments on this PR", a reviewer (human or bot like CodeRabbit/ultrareview) left comments, or a PR URL is pasted with review feedback to act on. Triggers on /fix-pr-mantra.
hugyu/AgentKernel/examples/skills/project-review Skill
0★ repoReview a project before proposing focused changes
skyestrela/ai-agent-skill-preview/code-review-gate Skill
0★ repoAutomated pre-commit review — security scan, quality gates, and auto-fix suggestions. Catches secrets, dead code, and common anti-patterns before they hit main.
prathakmalik/agent-standards-kit/skills/review-changes Skill
0★ repoReviews a set of code changes (a diff, a branch, or staged/uncommitted work) for correctness, edge cases, security, performance, and consistency with the repo's conventions. Use when the user asks to review changes, review a PR, check a diff, or sanity-check work before committing. Trigger phrases: "review my changes", "review this PR", "check this diff before I commit".
artaasd95/SLM-skills/Test-runner-analyzer Skill
0★ repoRead existing tests, build a short execution plan, run the test files, capture results, and summarize exact failures. Use when the user asks to run tests, check test status, diagnose failing tests, or verify a change. Do not write new production code.
lpaiu-cs/root-cause-gates/contribution-review-gate Skill
0★ repoSelf-review the user's OWN contribution pull requests and route each finding by a severity gate — P2-or-higher gets posted inline on the PR, everything below (P3 / nits / questions) is accumulated into scoped cleanup draft PRs instead of cluttering the feature PR. Use this whenever the user asks to review their own PR(s), "apply the gate", "run the P2 gate", process a batch of their contribution PRs, self-audit a PR before or after opening it, or asks where a finding should go (post now vs. collect for later) — even if they don't say the word "gate". NOT for reviewing other people's PRs, where normal review posting is expected.
Listinggood amazon compliance checker
ryanyang828/listinggood-skills/skills/listinggood-amazon-compliance-checker Skill
no license0★ repoUse this skill when users need to check, audit, or validate Amazon product listings for policy compliance, restricted content, or suppression risks. Covers Amazon Terms of Service red lines, category-specific rules, image compliance, intellectual property issues, and listing health scoring. Trigger on: Amazon 合规, compliance check, listing 审计, Amazon policy, 为什么被下架, suppressed listing, listing health, 合规体检. Part of the ListingGood toolkit — free preliminary compliance scan and AI listing generation at https://www.listinggood.com/scan.
zl3311/alpha-mining/.cursor/skills/brain-check Skill
0★ repoHow to check BRAIN alpha details and all 8 submission checks. Use after simulation to verify submission viability. Trigger on: check, BRAIN check, submission check, alpha check, IS check, all pass.
blakebauman/skillist-validator/skills/skill-quality-audit Skill
0★ repoReview the quality of an agent skill beyond specification conformance — whether its instructions are grounded in real expertise, calibrated between prescriptive and open, economical with context, and structured for progressive disclosure. Use when the user asks to review, critique, improve, or audit a skill; asks why a skill produces poor or inconsistent results; wants feedback on a SKILL.md they wrote; or asks whether a skill is worth keeping. Complements spec validation, which catches format errors but says nothing about whether the instructions are any good.
cycoresecure/grc-skills/skills/evidence-reviewer Skill
no license0★ repoQuality-review a compliance deliverable or evidence package before it goes to an auditor or client. Catches spelling, grammar, and truncated content, wrong framework terminology (ISMS vs AIMS, Type I vs Type II), invalid control IDs, confidentiality leakage (other companies' names, secrets, placeholders, metadata), weak finding language, and screenshot hygiene problems. Use when someone says "review this deliverable", "QA this report", "check this evidence before the audit", "proofread this gap assessment", or wants a sanity check on anything audit-facing or client-facing.
rolson24/cad-sim-agent-skills/skills/cad-sim-design-orchestrator Skill
0★ repoStep 2 of the reset CAD workflow. Use after cad-sim-project-intake has produced intake/project_brief.yaml, or after the user supplies an equivalently complete brief, to author the first CAD/product-system candidate: CAD/source files, canonical annotation_view, handoff.json, viewer3d validation and serving, visual-fidelity evidence, build/use or system-integration package, design-decision and option-space evidence, artifact-centric Primary Outcome Surface handoff, prototype handoff, allowed lightweight research/analysis/simulation/bounded optimization, Next-Action Worthiness, Next-Action Design Fidelity, Reference Archive Import, Exemplar-Calibrated Handoff, Profile-Critical Falsification Checks, Verifier-Backed Spatial Evidence, Quality Harness rows, and stage-entry tooling-scout triage for approved new stages. Use cad-sim-review-revise-loop instead when a current annotation_view already exists and the main task is reviewer-driven critique, revision, maturity promotion, or autonomous continuation.
creative-int/abbie-plugins/skills/abbie-proof-review Skill
0★ repoThis skill should be used when an Abbie Task has produced a change set that needs inspection, when deciding whether to apply it locally or publish a draft pull request, or when verifying an existing action receipt. Triggers include 'review this Abbie task', 'apply the change set', 'make a draft PR', 'check the proof', and 'what did this task change'.
bigblueboo/expert/skills/thermo-nuclear-expert-review Skill
0★ repoRun a thermo-nuclear code quality review through GPT-5.6 Pro via the `expert` CLI - an extremely strict structural maintainability audit of a branch or diff, with as much of the repository attached as the token budget allows. Use when asked for a thermo-nuclear review, a thermonuclear review, an expert deep code quality audit, or an especially harsh external review of maintainability, abstraction quality, and spaghetti growth.
martonpaulo/skills/architecture-review Skill
0★ repoReview an existing codebase for high-value architectural improvements, using concrete code evidence to identify weak boundaries, shallow modules, duplication, coupling, scattered responsibilities, and unstable seams.
gitt510/agent-skills/skills/build-pr-description Skill
0★ repoWrite a PR description from scratch or fully rebuild an existing one. Gathers facts from the diff, commits, and conversation, then writes only the facts a reviewer needs to read the diff, as a Why / What / Test / Notes outline with one fact per bullet. An existing body is broken down sentence by sentence and only facts corroborated by other evidence survive. Use when creating or rewriting a PR body, including when running gh pr create or gh pr edit. Not for a few added lines to an existing description — a normal edit covers that.
ridermw/my-skills/skills/adversarial-review Skill
0★ repoPortable, self-contained agent skills for Copilot CLI / Claude Code / Cursor. First skill: project-room.