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
Aryan1718/developer-agent-skills/skills/change-impact Skill
0★ repoUse this skill when the user asks what recent code changes will affect, what might break, what depends on a modified file, or wants an impact review before committing, opening a PR, or merging. Triggers on: "change-impact", "what will this affect", "what might break", "what depends on this", "analyze the impact of my changes", "did I miss anything after changing this", or similar post-change impact analysis requests. Focus on uncommitted changes, staged changes, the last commit, or a branch diff, then identify confirmed impact, likely impact, risk signals, and practical follow-up checks using read-only repository analysis.
cytoph/agent-skills/skills/update-git-skills Skill
0★ repoUse when updating externally-sourced skills from Git repositories in the current project or user-level .claude/skills directory. Use when skills may be outdated or after adding a new .gs-meta source file.
tnagatomi/skills/skills/chunked-impl Skill
no license0★ repoImplement a feature or fix incrementally by splitting the work into small chunks and building each chunk test-first with the tdd skill's red-green-refactor loop, then committing once tests are green. Depends on the tdd skill (https://github.com/mattpocock/skills/tree/main/skills/engineering/tdd) for the per-chunk red-green-refactor discipline. Use this skill whenever the user asks to implement, build, or fix something with phrases like "implement X chunk by chunk", "commit as you go", "test and commit each step", "incremental implementation", "split this into small commits", or any time the user wants steady, verifiable progress with a clean git history rather than a single big change. Prefer this skill for non-trivial changes that have (or should have) automated tests.
asdlem/pr-workflow/docs/i18n/zh-CN Skill
no license0★ repo使用项目原生模板、仓库语言/风格一致性、提交前预览和安全的 gh/glab CLI 操作,准备并可选择性创建 GitLab Merge Request 或 GitHub Pull Request。当用户要求准备、编写、预览、创建、提交或打开 MR/PR、合并请求、拉取请求或就绪分支时使用。
vanities/skills/skills/roast-me Skill
0★ repoBrutally honest critique mode. Role-play as a sharp, talented reviewer (recruiter, senior peer, hiring manager, principal engineer, founder) and tear into the work — resume, plan, design, repo, pitch, anything. Use when user wants real feedback and asks to be roasted, mentions "roast me", "be brutal", "what's actually wrong with this", or asks for an honest critique they can take.
MoaidHathot/Zakira.Conduit/skills/zakira-conduit Skill
0★ repoUse, configure, and troubleshoot Zakira.Conduit - the .NET 10 global CLI tool that mirrors agent skills from GitHub, Azure DevOps, or local directories into one or more target folders via a conduit.json (or conduit.jsonc) manifest. Activate when the user mentions conduit, conduit.json, conduit.jsonc, .conduit-state.json, syncing or mirroring agent skills, pinning a commit, unpinning to restore branch tracking, the in-string `-> Name` alias or `{source, as}` wrapper, include/exclude globs, the orphan cleaner, or runs commands such as `conduit sync`, `conduit list`, `conduit status`, `conduit pin`, `conduit update`, `conduit unpin`, `conduit clean`, `conduit watch`, `conduit init`, or `conduit validate`.
The same file is in 1 other repository
Kofiloski/app-store-review-risk/skills/app-store-review-risk Skill
0★ repoAudit Apple-platform app code, configuration, metadata, release branches, or Git diffs for likely App Store Review, TestFlight, and notarization rejection risks. Use when someone asks "will Apple reject this?", "is this ready to submit?", "why was my app rejected?", or requests an App Store preflight for iOS, iPadOS, macOS, Mac Catalyst, watchOS, tvOS, or visionOS. Trigger for Info.plist permission strings, PrivacyInfo.xcprivacy and required-reason APIs, entitlements, tracking and App Privacy answers, StoreKit paywalls, subscriptions and restore flows, external purchase links, Guideline 4.8 or social login, account deletion, UGC moderation, screenshots, review notes, demo access, and target-specific pull request changes. Run the deterministic scanner, verify findings in context, and report file-backed fixes without promising approval.
The same file is in 1 other repository
SystemicVoid/agentic-research-skills/skills/literature-review Skill
0★ repoAudit and synthesize a retrieved literature corpus against a research project.
cskwork/skill-ab-eval/examples/conventional-commit Skill
0★ repoWrite git commit messages that follow Conventional Commits plus this team's house rules. Use when writing or rewriting a commit message.
Evan-Joseph/agent-workflow-skills/skills/design-competition-entry Skill
0★ repoManage a design competition entry from brief verification to deliverable planning. Use when an agent must check official rules, choose the correct deliverable branch, define a concept, write image or layout prompts, review drafts, and prepare submission assets.
Architectural alignment validation
meyverick/agy-skills/skills/architectural-alignment-validation Skill
0★ repoEvaluates and validates codebase architectural structure. Use when auditing SOLID, DRY, Demeter, or DDD decoupling principles.
Acuris-GmbH/acuris-agent-context/agent-skill/acuris-eudi Skill
0★ repoAcuris EUDI Wallet Verifier — a hosted OID4VP relying-party service at https://eudi.acuris-geo.com that accepts EU Digital Identity Wallet presentations (SD-JWT VC PID), validates the credential against EU 27 member-state trust lists (LOTL → TSL → x5c → CRL), and cross-checks the disclosed residence address against Acuris's address-validation pipeline. Use when the user is integrating EUDI Wallet verification into a bank KYC / branch onboarding flow, building a relying-party backend that initiates verification sessions and polls for results, generating OID4VP presentation_definitions, handling SD-JWT VC responses, or interpreting verification_status, accuracy_type, and credential_validity in poll responses.
vikenpatel14/cursor-qa-skills/bug-origin-checker Skill
no license0★ repoDetermine if a bug found during feature branch testing is pre-existing or introduced by the branch. Analyzes PR code changes and compares against the bug area. Use when the user finds a bug on a feature branch build and wants to know if it was already there or introduced by the branch.
0xdeafcafe/skills/skills/drive-change Skill
0★ repoUse when the user says "/drive-change", "drive the change", "make this change happen", "implement and review", "ship this fix", or wants Claude to drive a change end-to-end (implement if needed + audit + fix) without going through formal planning. For quick or clear changes where the implementation can be derived from conversation intent. For substantial changes warranting an ADR + Gherkin spec, use /drive-plan instead. drive-change runs the audit pipeline (slice → fan-out to /review-* specialists in parallel → merge with apply-validation → cross-slice verify → dispatch fix-applier agents under sensitivity gating). Sensitive paths (auth, crypto, IPC) route to Opus fix-appliers; everything else goes to Sonnet. Adds /review-ux automatically if UI files are touched (.tsx/.jsx/.vue/.svelte/.astro/.html/.css/.scss/.less). Produces a single unified report grouped by severity.
eltntawy/idea-discovery-playbook/skills/behavior-led-validation Skill
0★ repoOrchestrates behavior-led idea and market validation—problem interviews, pretotype experiments, paid traffic, demand proxies, competitor revenue estimates, and unit economics—before build. Use when validating a business idea end-to-end, testing willingness to pay, or planning experiments before build.
flaviomilan/skills/skills/dependabot-validation Skill
0★ repoRevisa (read-only) os PRs do Dependabot e os alertas de segurança de um repositório GitHub, classifica cada atualização por risco aplicando guardrails de versão configuráveis (ex.: travar o Spring Boot em 3.x), cruza PRs com alertas de segurança e entrega um relatório priorizado de o que pode subir com segurança e o que precisa de revisão ou deve ser segurado. Use quando precisar verificar as dependências de um repositório. Informe o repositório como owner/repo.
cmdecker95/skills/skills/cavecrew Skill
no license0★ repoDecision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
The same file is in 7 other repositories
justinramos101/agent-skill-kit/.agents/skills/skill-reviewer Skill
0★ repoUse when reviewing or editing proposed or existing skills in this catalog (public or repo-local) for structure, metadata, source safety, usefulness, validation, and release readiness. Do not use for building a new skill from source material; use `skill-curator` for that.
dd3ok/lucid/fixtures/policy-pack-claude/.claude/skills/reviewer Skill
0★ repoFixture Claude skill.
nbsp1221/wayrail/template/.agents/skills/wr-review Skill
no license0★ repoUse when reviewing an implemented and verified wayrail spec item into review.md. Reads a selected spec item, checks Review Handoff readiness, inspects the current diff read-only, synthesizes findings, resolutions, residual risk, and a verdict, and writes only review.md. Do not use for implementation, verification command execution, fixing findings, waiver approval, merge, commit, release approval, or editing spec.md/plan.md/verification.md.
samariafar/agents/skills/git Skill
0★ repo🤖 agents 🧠 skills 🔌 mcp
Sparvovic/agent-skill-foundry/examples/good-skill Skill
0★ repoUse when the user asks an AI coding agent to turn a git diff into concise release notes with risks, validation evidence, and reviewer-ready wording.
skillrig/skillrig.github.io/.agents/skills/impeccable Skill
0★ repoUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
The same file is in 4 other repositories
rauleburro/skills/skills/auto-review-dispatch Skill
no license0★ repoUse when the user asks for a code review of their current work — phrases like "revisá mi PR", "quiero un review imparcial", "lanzá un review con contexto limpio", "code review this", "review before merging", "que otro Codex revise esto", or after they finish a chunk of work and mention merge/PR/review/listo. Auto-detects branch, PR number, base commit, modified files, and project stack from AGENTS.md, then dispatches a fresh-context code review subagent with the full brief pre-filled. Saves the user from typing out context every time they want a review.
giostriquer/agent-workshop/.claude/skills/push Skill
0★ repoUse when committing and pushing changes in the project repository; detect the current branch, pull origin for that branch before committing, prefer the newest meaningful update in docs/change-log.md as the commit message source when available, otherwise derive the message from the primary diff, then stage all changes, commit, and push to the same current branch.
Ceschiu/finance-portfolio/claude-skills/interview-answer-formatter Skill
0★ repoStructure a buy-side / finance interview answer using template (definition → intuition → formula → use case → pitfalls). Not for valuation or ratio computation (see dcf-analyzer, ratio-analysis).
fxjim/agent-commerce-guard/.well-known/skills/try-agent-commerce-guard Skill
no license0★ repoEvaluate non-sensitive AI-agent commerce action manifests with the free Agent Commerce Guard hosted policy endpoint. Use when a user wants to preflight wallet spend, paid API calls, deployments, token launches, marketplace jobs, social actions, destructive commands, billing changes, or credential access before execution. Never send secrets, private source, customer data, or credentials to the hosted demo.
Godot art consistency reviewer
schmoenraad/godot-gamestudio/plugins/godot-gamestudio/skills/godot-art-consistency-reviewer Skill
0★ repoIndependently review Godot visual assets for style, palette, perspective, scale, lighting, outlines, silhouettes, readability, import quality, and cohesion with established art direction. Use as the opposing reviewer for sprite and static-art deliverables.
tjrice42/design-judgment-skills/case-study-writer Skill
no license0★ repoDraft a portfolio case study from raw project materials — build journals, project decks, scattered notes, screenshots, chat transcripts, or a designer's verbal rambling about a project. Use this skill whenever the user wants to write, draft, start, or restructure a case study, turn a build journal or project notes into portfolio content, or says "help me write up this project." Pairs with build-journal (input), voice (style), portfolio-edit-pass and portfolio-critique (downstream review).
eyupcanbodur/agent-knowledge-hub/skills/hub-lint Skill
0★ repoHealth-check an agent-knowledge-hub sub-hub for rot. Use when the user says "lint the hub", "hub-lint", "check the hub", "/hub-lint", or before relying on hub notes for important work. Runs the deterministic gate first (orphans, broken links, missing INDEX/log entries, em dashes, missing TL;DRs), then an LLM pass for what scripts cannot see (contradictions between notes, duplicate topics, stale/hedged claims). Propose-only, never auto-fixes.
qa-veritas/skillpack/skills/check_disk_pressure Skill
0★ repoDecide whether a node's storage is under pressure and recommend an action. Use when a mount is filling, a workload reports no-space-left, or capacity planning needs a verdict.
JAlex1201/pr-presubmit Skill
0★Use this skill to run a structured pre-submit checklist on a change before it goes out for review, helping the author catch everything catchable before a reviewer ever looks. Activate when a user is about to open or push a pull request, is getting ready to submit or merge changes, wants to know whether their PR is ready, asks for a pre-submit or pre-flight check, or describes a change and asks whether anything is missing before requesting review. Do not use this skill for writing or improving a PR title and description (use pr-best-practices for that), reviewing someone else's code (use pr-review for that), or running automated tests or linters directly on behalf of the user.
Agent skill instruction review
Nick2bad4u/codex-skills/skills/agent-skill-instruction-review Skill
no license0★ repoPersonal multi-skill repository for reusable Codex workflows.
MSal2020/skillguard/examples/clean-skill Skill
0★ repoUse this skill when the user wants to pretty-print, format, or validate JSON. Trigger on messy JSON, minified JSON, or "format this JSON" requests.
krkrkrr/skills/skills/deps/dep-lib-review Skill
no license0★ repoPeriodic dependency review for Node.js/pnpm projects — outdated package triage, security audit, update batching strategy (patch/minor/major), validation checklist. Run monthly or before major releases. Use when asked to review or update dependencies in a repo.
vincendiary/agents/skills/grill-me Skill
no license0★ 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".
The same file is in 23 other repositories
Build the oracle before the answer
XyraSinclair/ideonomy/skills/build-the-oracle-before-the-answer Skill
0★ repoDefeat answer-then-rationalize: when a claim is checkable more cheaply than it is producible (a row count, a benchmark number, "this refactor preserves behavior", a combinatorial count, "this query returns X"), write the independent truth-check AND commit its expected value BEFORE you produce the answer. The failure it prevents: an LLM emits a fluent answer and then manufactures support for whatever it already said — verification collapses into self-agreement because the check was built after the answer. Triggers on any quantitative or verifiable claim, especially counts, latencies, "this works", and anything you'd be tempted to assert without running.
amolb1986/skill-lint/examples/good Skill
0★ repoGenerate a grouped, human-readable changelog from git history between two refs
vishnujchandran/.agents/skills/code-quality-check Skill
no license0★ repoTop-tier code quality audit skill for correctness, maintainability, readability, and testability with prioritized, minimal-diff fixes.
smanaton/git-coach/skills/git-explain Skill
0★ repoExplain a git concept in plain language, with no execution. Answers conceptual questions like what is the staging area, rebase vs merge, what does HEAD~2 mean, what is a detached HEAD, what does reset actually do, how the reflog works, or fetch vs pull. Grounded in git help and Pro Git, not memory. Use when the user wants to understand git rather than do something. Skip when they want to run an operation, which is git-guide-me, or when they are stuck and need their current state diagnosed, which is git-next.
payne0420/claude-ultracode-agents/cursor-agent Skill
0★ repoDrive Cursor's CLI agent non-interactively via `cursor-agent -p` (headless print mode) to delegate coding work to a second, independent agent. Use this skill when the user wants a second opinion on a design or bug, an independent implementation plan, an independent code review of a diff or PR, a self-contained implementation task run headlessly, isolated work in a git worktree, or cross-checking your own work against another model. Also use when the user explicitly mentions "cursor-agent", "cursor agent", "cursor CLI", or asks to "have cursor plan / look at / build / review" something. Triggers: "ask cursor", "get a second opinion from cursor", "have cursor plan this", "have cursor review this", "run cursor-agent on X", "delegate this to cursor", "cursor-agent -p ...".
ChristinaAgent/OpenSkillBench/examples/code-review-skill Skill
0★ repoReview code changes for correctness bugs, regressions, and missing tests before a pull request is merged.
Avarce/repo-vetting-skills/skills/repo-security-check Skill
0★ repoUse when the user is about to install or adopt a third-party repository or package (GitHub repo, npm/PyPI/crates/Go module) and wants it vetted first — "is this safe to install", "do a security check", "audit this dependency", "vet this before I install", "check this for malware". Companion to repo-research, which answers the broader "should I use this?"; use this skill specifically for the is-it-safe-to-install question.
PR Author Best Practices Skill
JAlex1201/PR_Author_Best_Practices_Skill Skill
0★Use this skill to author strong pull requests across GitHub, GitLab, and Bitbucket. Activate when a user is opening, drafting, splitting, or polishing a pull request or merge request; writing a PR title or description; wondering whether a PR is too big to review; addressing or responding to review feedback; or summarizing changes for a reviewer. Also activate right after a push when the next natural step is opening a PR. Do not use this skill to review someone else's code (use pr-review for that), to run a pre-submit checklist before opening a PR (use pr-presubmit for that), or to manage CI/CD pipelines or deployment workflows.
kindaidai/agent-skills/skills/code-review Skill
no license0★ repoAI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).
The same file is in 13 other repositories
codecraftersautomation/claude-code/plugins/ccp/skills/diff-audit Skill
no license0★ repoAudit the current git diff before a handoff or commit to catch problems. Use when the user asks to "review my changes", "audit the diff", "check before handoff/commit", "did I leave anything bad in here", or before /ccp:handoff. Looks for accidental edits, generated/committed-by-mistake files, secrets, formatting noise, unfinished TODOs, risky permission changes, and destructive changes. Writes .claude/ccp/handoff/DIFF_AUDIT.md and does NOT modify files unless explicitly asked.
JAlex1201/pr-review Skill
0★Use this skill to write thoughtful, collaborative code review comments on a pull request or diff. Activate when a user wants a PR or diff reviewed, asks for feedback on code changes, wants help leaving review comments, pastes a diff and asks what you think, or frames a request as a code review, a critique, or acting as a reviewer. Also activate when a diff is shared for feedback without the word "review." Do not use this skill for authoring a new pull request description (use pr-best-practices for that) or running a pre-submit checklist before opening a PR (use pr-presubmit for that).
lensetek/Research-Agent-Skills-Collection/skills/academic_peer_reviewer Skill
no license0★ repoMensimulasikan proses review sejawat (peer review) secara objektif dan konstruktif terhadap draf naskah sebelum dikirim ke penerbit ilmiah resmi.
Yaphet2015/ya-skills/skills/design-grill Skill
0★ repoUse when stress-testing an idea, design, plan, architecture, PRD, or implementation approach before coding.
Melmonster13/antigravity-skills-project/.agents/skills/git-commit-formatter Skill
no license0★ repoFormats git commit messages according to Conventional Commits specification. Use this when the user asks to commit changes or write a commit message.
Munizada/project-audit-council/skills/project-audit-council Skill
0★ repoPerform evidence-based audits of a repository, subsystem, branch, pull request, or diff for security, breakage, dependency risk, architecture problems, database integrity, and production readiness. Use for audits, red-team reviews, production checks, and fix planning. Not for ordinary feature work or small edits.
primitivedotdev/codex-plugin/plugins/primitive/skills/primitive-inbox Skill
0★ repoReceive email — check what arrived, wait for a specific message, and read full threads. Use REACTIVELY when the user wants an address to receive replies, verification codes, alerts, or signups, or asks "did anything come in?" / "check the inbox" / "wait for the reply." Use PROACTIVELY when you sent something and need to watch for the response, or are building an email-driven workflow that triggers on receipt. Requires the Primitive MCP server (bundled).
yuelenghan/orbit/skills/bitbucket Skill
0★ repoUse when the user needs Bitbucket Data Center repository, branch, pull request, comment, merge, or build-trigger operations.
ydkulks/DevSync/.claude/skills/devsync-commit Skill
0★ repoStart a Socratic walkthrough of the changes in commit $1
pablonification/grok-build-consult-claude/skills/conventional-commits Skill
0★ repoWrite git commit messages using Conventional Commits v1.0.0. Invoke when committing, staging for commit, amending, rebasing commit messages, or when the user asks for feat:/fix:/docs: format. Do NOT load for unrelated coding tasks.
gawakawa/gh-skill/skills/review-memory Skill
no license0★ repoDistill PR review comments into reusable lessons and save them to Claude Code memory for automatic recall in future sessions.
gvago/unofficial-qodo-review-skills/skills/terraform-review Skill
0★ repoUse when a PR diff adds or modifies Terraform/OpenTofu (.tf / .tofu / .tftest.hcl) — flags identity churn (missing `moved` blocks, `count` index churn), secrets that land in state, unsafe destroy/state ops, version-floor violations, and backend/state antipatterns in the CHANGED HCL only. Skip for non-IaC diffs.
chieaid24/skills/skills/catch-up Skill
0★ repoDaily reviewer for the dependency-aware GitHub Issues queue: reconstructs what shipped since the last run, reports active, blocked, and human-gated (HITL) work, diagnoses stalled lanes, and starts the repo's dev server for review. Read-only except for a fast-forward of a clean `main`. Use on a daily cron or on demand: catch me up, what happened yesterday, review progress, daily catch-up, or /catch-up.
cp3hnu/agent-skills/skills/react-formatting Skill
0★ repoUse when setting up or fixing lint/format inconsistencies in a React project without Next.js (Vite, CRA, etc.), when commit messages fail conventional-commit checks, or when configuring eslint-plugin-react, Prettier, Husky, lint-staged, commitlint, and VSCode/Cursor plugins.
satejbidvai/skills/skills/pr-review Skill
no license0★ repoReview a PR using Satej's personal review standards