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
Finishing a development branch
roronoazoroshao369/vibe-coding-os/skills/core/finishing-a-development-branch Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/git-guardrails Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/grill-user-before-building Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/guard-bypass-protocol Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/incremental-review Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/receiving-code-review Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/requesting-code-review Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/review-before-merge Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/self-review-before-response Skill
1★ repoRun a mandatory self-review checklist on your own diff before responding to the user.
Setup pre commit quality gates
roronoazoroshao369/vibe-coding-os/skills/core/setup-pre-commit-quality-gates Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/using-git-worktrees Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/core/verification-before-done Skill
1★ repoVibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.
roronoazoroshao369/vibe-coding-os/skills/prompts/critique-pass Skill
1★ repoWriter and critic phases for challenging a draft or implementation before final response.
skillsmith-dev/ai-skills/skills/contract-guard Skill
no license1★ repo个人合同审查助手——帮你逐条审查租房合同、劳动合同、服务合同、买卖合同等日常合同中的不利条款、隐藏陷阱和法律风险。提供通俗解读、修改建议和谈判话术,让普通人也能看懂合同不吃亏。
quantum-box/agent-packages/plugins/quantum-box/skills/final-quality-gate Skill
no license1★ repoRun final host-side quality checks before committing, pushing, or handing off completed Tachyon work. Select build, format, lint, type, and test commands for the changed packages or crates. Use Docker checks only when explicitly requested or when container-specific parity is required.
MarioJames/skill-foundry/skills/asset-validation Skill
1★ repoProduction-proven agent skills: agent-swarm, asset-validation, browser-harness, awesome-presentation, workspace-knowledge-graph.
kastriasani/google-ads-skills/skills/google-ads-roast Skill
1★ repoUse when someone wants to roast, pressure-test, stress-test, or sanity-check a Google Ads idea, campaign plan, media plan, budget, offer, or account strategy before spending, get a brutal second opinion before launch, "convene the council", or says "/roast". Spins up a five-persona adversarial council (Contrarian, Performance Skeptic, Account Strategist, Researcher, Searcher) that attacks the plan from every angle, then a Judge returns one GO, RESHAPE, or KILL verdict with the cheapest 48-hour test to de-risk it before budget goes live. Works for any idea, tuned for paid search.
Bulk change governance and rollback
scumunna/programmatic-skills/skills/bulk-change-governance-and-rollback Skill
1★ repoGovern cross-platform bulk edits with scope control, before-state exports, diff review, canary rollout, maker-checker approval, verification, and rollback evidence. Use for SDF uploads, editor imports, API batches, spreadsheet uploads, campaign clones, budget updates, targeting edits, taxonomy fixes, and any large account change.
Change management and incident response
scumunna/programmatic-skills/skills/change-management-and-incident-response Skill
1★ repoMake changes safely and run incidents calmly in live ad accounts. Use when the user says "change management", "approval process", "four eyes", "maker checker", "bulk edit safely", "pre-flight check", "rollback", "incident", "runbook", "runaway spend", "spend spike", "a deal went dark", "pixel outage", "brand-safety breach", "postmortem", or asks how to apply a large edit without breaking live delivery. Covers the four-eyes approval pattern, a bulk-edit safety sequence, severity tiers, first-five-minutes containment, escalation, and a postmortem template.
Cm360 verification and active view
scumunna/programmatic-skills/skills/cm360-verification-and-active-view Skill
1★ repoMeasure and report viewability and ad verification in Campaign Manager 360 using Active View against the MRC standard, across the eligible, measurable, and viewable tiers. Use when the user asks about Active View, viewability, viewable impressions, viewable rate, measurable vs eligible impressions, why viewability is low or missing, the MRC 50%/1s display and 50%/2s video standards, non-measurable causes (cross-domain iframes, unsupported tags, VPAID, mobile app SDK), MRC accreditation, audible/AV video metrics, or pulling Active View metrics through the CM360 API v5.
Consent signal verification and decode
scumunna/programmatic-skills/skills/consent-signal-verification-and-decode Skill
1★ repoDecode and validate IAB TCF v2.3 and GPP consent strings and prove that opted-out users were actually suppressed across DSPs and tags. Use when the user asks how to decode a TCF or GPP string, read a euconsent-v2 or __gpp value, check DisclosedVendors, verify a vendor got consent for a purpose, confirm a Global Privacy Control (GPC) opt-out was honored, audit that denied users saw no personalized ads, reconcile consent state with delivery logs, or debug why a consented user was dropped or an opted-out user was still targeted.
Creative review and approval queue
scumunna/programmatic-skills/skills/creative-review-and-approval-queue Skill
1★ repoManage creative intake, spec QA, legal or brand approval, platform review, trafficking readiness, rejection handling, swaps, expirations, and evidence for programmatic campaigns. Use when creative assets, VAST tags, HTML5, native, CTV, audio, DOOH, landing pages, click URLs, or approval statuses block launch or in-flight delivery.
Supply chain transparency adstxt sellersjson
scumunna/programmatic-skills/skills/supply-chain-transparency-adstxt-sellersjson Skill
1★ repoImplement and audit the ad supply-chain transparency files (ads.txt v1.1, app-ads.txt, sellers.json v1.0, and the OpenRTB SupplyChain object) to verify who is authorized to sell an impression and prune unauthorized or opaque paths. Use when the user asks how to write or fix an ads.txt or app-ads.txt file, what OWNERDOMAIN / MANAGERDOMAIN / INVENTORYPARTNERDOMAIN mean, how to read sellers.json, what seller_type PUBLISHER / INTERMEDIARY / BOTH means, how the schain / SupplyChain object works, how to cross-check ads.txt against sellers.json against schain, how to catch a not-authorized or unverifiable seller, or how to run a supply-chain authorization audit.
mtthsnc/tempest/plugins/tempest/skills/review Skill
1★ repoUse when you have a diff, a PR, or a set of changed files and want a staff-engineer-level audit before it merges — correctness and security bugs, error handling, and simplification/reuse opportunities — with findings classified by severity and confidence and high-confidence fixes optionally applied and verified. Skip for trivial typo-level changes.
mtthsnc/tempest/plugins/tempest/skills/verify Skill
1★ repoUse when you need to confirm a code change actually works by running the app and observing real behavior — not by trusting green unit tests. Triggers — verify a PR or fix, confirm a feature works, manually validate a change before shipping, start the app/server/CLI and exercise the specific behavior the change targets, judge PASS/FAIL on observed evidence. For web-UI behavior, hand off to the `qa` skill.
comment-hq/skills/skills/delivery-methodology Skill
1★ repoChoose and enforce a pragmatic engineering delivery topology: a direct PR for independently shippable work or a controlled lift branch for foundational work with unsafe intermediate states. Defines bounded SHA-delta reviews, risk-scaled reviewer counts, review receipts, lift freeze/promotion, and a technical-ready stopping point. Delivery skills call it before planning or shipping; invoke directly when deciding how a large change should reach main.
comment-hq/skills/skills/review-loop Skill
1★ repoReview an explicit plan/code/PR SHA delta with a risk-scaled panel, fix one complete finding batch, validate the changed delta, and emit a durable review receipt. Defaults to one reviewer, adds targeted lenses for sensitive work, caps normal finding-bearing rounds, and avoids re-reading already certified branch history. Only invoke as `$review-loop` / `/review-loop`, or when a delivery skill calls it. Works identically under Codex and Claude Code.
brian8a1/senso-agent-skills/skills/product-review Skill
no license1★ repoPrepare a recurring product, weekly, roadmap, or backlog review from the current Senso workspace. Use when a product manager or product leader needs what changed, growing Opportunities, blocked Decisions, unowned or stalled Backlog work, new contradictions, integration health, or launched Solutions awaiting an Outcome.
brian8a1/senso-agent-skills/skills/signal-review Skill
no license1★ repoReview evidence already present in Senso Signals and make explicit triage corrections. Use when a product manager asks to review new Signals, discard noise, resolve an orphan, fix incorrect grouping, split or combine evidence, or inspect pending deal-breaker suggestions before Opportunities are acted on.
keithhegit/sci-using-kit/skills/sci-reviewer-preflight Skill
1★ repoUse before arXiv release, SCI submission, advisor review, rebuttal preparation, or when a manuscript needs a rigorous reviewer-style risk audit
Fatih0234/pi-caveman/skills/caveman-review Skill
1★ repoUltra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
The same file is in 11 other repositories
duandigi/duandigi-growth-marketing-skill/skills/growth-ethics-review Skill
1★ repoUse this skill when reviewing a growth idea, experiment, automation, message, incentive, tracking plan, or loop for manipulation, spam, privacy, accessibility, discrimination, brand, legal, or platform-policy risk.
duandigi/duandigi-growth-marketing-skill/skills/permission-scope-review Skill
1★ repoUse this skill when reviewing OAuth scopes, API permissions, WordPress roles, service-account access, or connector capabilities for least privilege, user trust, and staged read or write access.
cosmefae/claude-skills/skills/commit-guided Skill
1★ repoUniversal guided git workflow to validate, commit, and open a PR. Generates a Conventional Commits message, checks branch, creates PR template. Includes admin override for emergencies.
po4yka/llm-wiki-skills/skills/llm-wiki-critique-audit Skill
1★ repoProduce an adversarial risk audit for an LLM-Wiki proposal, domain, vault, rollout, or product plan. Use when the user wants a failure-mode register, bad-fit decision, mitigation plan, residual-risk scorecard, or criticism-first stress test; route short adoption answers to llm-wiki-faq.
po4yka/llm-wiki-skills/skills/llm-wiki-github-action Skill
1★ repoConfigure GitHub Actions for LLM-Wiki maintenance. Use when the user wants scheduled wiki lint reports, PR-based documentation updates, Agent Skills validation, provenance checks, or safe repo-docs maintenance without direct writes to main.
po4yka/llm-wiki-skills/skills/llm-wiki-security-review Skill
1★ repoReview an existing LLM-Wiki or Agent Skills setup for practical security gaps. Use when the user asks whether current permissions, MCP/API exposure, exports, cloud-model use, or data boundaries are safe enough; route new architecture threat modeling to llm-wiki-threat-model.
po4yka/llm-wiki-skills/skills/llm-wiki-trust-audit Skill
1★ repoAudit an LLM-Wiki system for anti-slop controls such as provenance, review gates, protected human synthesis, stale claims, and unsafe agent write permissions. Use when the user asks whether their wiki can be trusted; route setup/permission safety reviews to llm-wiki-security-review and proposal risk audits to llm-wiki-critique-audit.
po4yka/llm-wiki-skills/skills/wiki-lint Skill
1★ repoRun structural and trust health checks for an LLM-Wiki vault. Use for broken links, orphan pages, missing provenance, stale claims, contradiction reports, taxonomy drift, protected-section edits, and review queue generation.
Recipe academic literature review
flowleap-ai/flowleap-plugins/plugins/flowleap/skills/recipe-academic-literature-review Skill
1★ repoMap the gap between published research and filed patents — a scholarly sweep across Semantic Scholar, arXiv, and OpenAlex aligned against a matching patent search, output centered on the published-versus-protected gap rather than a ranked novelty list. Trigger when the user asks for a literature review, a state-of-the-art survey, or a comparison of academic research against patents.
The same file is in 1 other repository
flowleap-ai/flowleap-plugins/plugins/flowleap/skills/recipe-invention-disclosure Skill
1★ repoProsecution recipe for turning an inventor conversation into a complete invention disclosure form (IDF) — structured technical capture, bar-date audit, novelty pre-check across patents and literature, landscape context, and a filing recommendation. Trigger when the user asks to document an invention, create an invention disclosure, or run a pre-filing novelty sanity check.
The same file is in 1 other repository
ceilidhboy/skills/skills/creating-pull-requests Skill
1★ repoCompany pull request workflow and branch policy. Use when user says "create a PR", "make a pull request", "open a PR", or when managing GitHub pull requests for company projects.
yoelgal/better-dev/skills/browser-capability Skill
1★ repoUse when a work item's done-criteria need a real browser - verify a page actually renders, run an end-to-end or visual check against the running UI, screenshot or inspect the live DOM - and no browser tool is wired yet. The worked example of sourcing a tool on a capability gap.
yoelgal/better-dev/skills/design-brief Skill
1★ repoUse when a work item has real UI surface and its visual direction isn't settled - a request to make something look good, design a landing page or a screen, pick an aesthetic or a design system, fix a UI that reads as generic AI slop, or turn a vague "looks nice" into visual done-criteria the loop can verify. This is the design front-end `/groundwork` composes to settle foundation tokens and `/plan-grill` composes for a UI feature. Composes the host's design skill and sources one on a gap; hardcodes no aesthetic or stack. Not for auditing existing UI code against accessibility or style guidelines - that is a host design-review skill (`/web-design-guidelines`) or `/review`.
yoelgal/better-dev/skills/guardrails-install Skill
1★ repoUse when a repo needs its guardrails installed or recorded - a missing commit-time or CI gate (no pre-commit hook, no lint/typecheck gate, no CI workflow), the autonomous loop's blast-radius policy (the high-consequence paths it should escalate rather than auto-edit, the change classes that gate a human, the scope threshold), the committed bash policy that prompts before a destructive command (`.omp/config.yml`, `bash.patterns`), or the recorded rules downstream skills read - deploy-* (including deploy-migrate and deploy-env, or a recorded deploy-surface of none), dev-run, seed-reset, ops-runner, version-surface, release-automation, and obs-* with absence as a named gap. Invoked by /onboard while bootstrapping the minimum base, run directly to fill a guardrail gap or record the safety policy without touching what the repo already has, or when the operator keeps answering the same non-safety gate yes run after run - a re-run then proposes the standing allowance the kept record has earned.
yoelgal/better-dev/skills/ios-capability Skill
1★ repoUse when a work item's done-criteria need a real iOS device or simulator - verify a screen renders on hardware, drive a flow by touch, capture an on-device screenshot - and no on-device check is wired yet. The mobile sibling of /browser-capability: the same prove-done-against-the-running-surface practice.
yoelgal/better-dev/skills/plan-grill Skill
1★ repoUse when the user wants a new feature or capability built and it is not a one-to-two-step change - "I want to add X", "let's build a way to Y", "can we add", "new feature Z", a rough intent that needs a plan before code. When the input is somebody else's adjective rather than an intent the operator owns, /brief-to-problem decodes it into a measurable problem first and hands the result here. Checks the baseline, ideates and grills the design watertight, and pins the observable done-criteria the loop drives to. For a bug or "X is broken" reach for /diagnose; for a whole new app or epic, /groundwork; for a trivial one-to-two-step change, just make it - still in its own worktree branch, skipping only the planning. Chore-class work enters here too - "upgrade to React 19", clearing the CVE the audit gate flagged, a behavior-preserving refactor, test or docs debt - on the contract-lite path.
yoelgal/better-dev/skills/pr-and-verify Skill
1★ repoUse when a change is ready to land - "ship it", "open a PR", "let's merge this", "raise the pull request" - or the loop has settled DONE / DONE_WITH_CONCERNS. Opens or refreshes the PR into the integration branch, reads CI truthfully, and verifies the contract's done-criteria end-to-end before it can merge. The clean review verdict is an entry precondition it checks, not a step it runs.
yoelgal/better-dev/skills/review Skill
1★ repoUse when a diff or branch needs an independent verdict inside the better-dev loop - the loop's gate after an implementer reports done, a whole-branch pass before a PR into the integration branch, or "review since X" against a fixed point - or when a colleague's inbound human-authored PR needs this repo's recorded policy applied over the host's PR-review mechanics. It is the loop's spec+standards evaluator; for a quick working-diff scan the host /code-review is fine.
yoelgal/better-dev/skills/security-pass Skill
1★ repoUse when a diff or work-item touches an untrusted-input, auth, money/PII, file-upload, external-fetch, or LLM/agent surface and needs a security verdict - as /review's Security channel when the host ships no /security-review, as /plan-grill's abuse-case reference, invoked directly on a work-item, or when deciding whether some tool/log/model output is safe to act on.
yoelgal/better-dev/skills/worktree-branching Skill
1★ repoUse when a feature, fix, or chore work-item is about to start and needs its own isolated branch off the integration branch - before planning, diagnosis, or the autonomous loop runs - or when detecting whether such a worktree already exists. For removing one after merge, see this skill's teardown notes; for moving a half-finished item to a colleague or another machine, its handoff notes.
chobizzy/llm-wiki/skills/daily-update Skill
1★ repoRun the daily wiki maintenance cycle: check all source freshness, update the index, and regenerate hot.md. Use this skill when the user says "/daily-update", "run the daily update", "update everything", "morning sync", "refresh the wiki index", or when triggered by the launchd cron at 9 AM. Also use to set up or verify the cron + terminal notification infrastructure for the first time ("set up the daily cron", "install the terminal notification", "how do I get the morning reminder?").
chobizzy/llm-wiki/skills/impl-validator Skill
1★ repoValidate whether an implementation matches its stated goal. Use this skill when a skill or agent wants a second opinion on its own output, when the user says "check this implementation", "validate what you did", "is this correct?", "review the output", or "did you do this right?". Also spawned automatically as a subagent by other skills (memory-bridge, daily-update) to self-check their outputs before presenting to the user. Returns a structured pass/warn/fail verdict with specific actionable issues.
The same file is in 1 other repository
chobizzy/llm-wiki/skills/wiki-lint Skill
1★ repoAudit and maintain the health of the Obsidian wiki. Use this skill when the user wants to check their wiki for issues, find orphaned pages, detect contradictions, identify stale content, fix broken wikilinks, or perform general maintenance on their knowledge base. Also triggers on "clean up the wiki", "what needs fixing", "audit my notes", or "wiki health check". Add --consolidate to switch from report-only to act-and-report mode (the "dream cycle"): fixes broken links, adds missing cross-references for orphans, corrects lifecycle states, demotes stale peripheral pages, normalizes tag aliases, and adds contradiction callouts — all with a dry-run preview and explicit user confirmation before any writes.
chobizzy/llm-wiki/skills/wiki-stage-commit Skill
1★ repoReview and promote staged wiki pages to their final locations. Use when WIKI_STAGED_WRITES=true and the user says "/wiki-stage-commit", "review staged pages", "commit staged writes", "promote staged pages", "approve staged changes", or "what's waiting in staging". Shows each staged file, lets the user accept or reject it, and moves accepted files to their final wiki locations. Rejected files are moved back to _raw/ for manual editing.
The same file is in 1 other repository
kadenn/skills/skills/senior-review Skill
1★ repoRun an architecture-first, high-signal review of a pull request, branch, commit range, patch, or working-tree diff. Use when the user asks for a senior review, full review, deep review, architecture review, or a review that must prioritize concrete bugs and design risks over lint-style commentary. Inspect beyond the diff, lock architectural conclusions, then report only evidence-backed implementation findings.
kadenn/skills/skills/shipit Skill
1★ repoRun a safe, repository-aware git delivery workflow covering status inspection, explicit staging, commit-message matching, validation, pushes, pull requests, rebases, and merges. Use when the user asks to commit, push, open or update a PR, rebase, merge, ship changes, or handle version control end to end. Preserve unrelated work, scan for secrets, and require immediate confirmation before merges or destructive git actions.
ggoosen/Digital-Workforce/.claude/skills/docx-review Skill
1★ repoReview and mark up a Microsoft Word (.docx) document the way a human reviewer does, with real Word comments, threaded replies, and tracked changes. Use whenever you are asked to review / comment on / redline / mark up a .docx, or to reply to someone's comments in a Word doc. Stamps comments with the ACTUAL time, registers the author so replies thread, and always emits a markdown mirror. Voice triggers: "review this doc", "comment on", "redline", "mark up", "reply to the comments", "Word review".
ggoosen/Digital-Workforce/.claude/skills/wiki-lint Skill
1★ repoHealth-check your context/ knowledge wiki. Finds contradictions, stale claims, orphan pages, broken/missing cross-references, index drift, and gaps — then fixes the ones you approve. Run it periodically (weekly is good). Voice triggers — "wiki lint", "lint the wiki", "check my context", "wiki health", "is my context stale", "clean up the wiki".
ifitsmanu/landing-studio/skills/webgl-3d Skill
1★ repoDecide, prototype, and verify selective 3D or WebGL for one landing-page section. Use when a real model, spatial comparison, product interaction, or shader effect may communicate the selected concept better than static media. Choose among a static treatment, model-viewer, Three.js, React Three Fiber, or a custom shader only after a measured proof; enforce transfer, geometry, draw-call, frame-time, accessibility, reduced-motion, context-loss, cleanup, and equivalent static-fallback gates.