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
arthjean/skills/skills/rust-doctor Skill
no license3★ repoDeep analysis of Rust projects — scan with rust-doctor CLI, triage by priority, read source context for each finding, apply senior Rust reviewer expertise, produce before/after fixes, verify score improvement. Triggers on "scan", "health check", "rust-doctor", "code quality", "audit this Rust project".
arthjean/skills/skills/security-review Skill
no license3★ repoComprehensive security audit of code changes. Analyzes changed files for OWASP Top 10 vulnerabilities, injection flaws, authentication issues, secrets exposure, and insecure patterns. Produces a structured report with severity ratings, confidence scores, and actionable remediations. Use when the user says 'security review', 'security audit', 'check for vulnerabilities', 'OWASP check', 'is this safe', 'check my code', 'vulnerability check', '/security-review', or asks to review code for security issues. Do NOT trigger for general code quality reviews, refactoring, or non-security concerns.
Thermo nuclear code quality review
arthjean/skills/skills/thermo-nuclear-code-quality-review Skill
no license3★ repoRun an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
The same file is in 5 other repositories
QinghongLin/paperdoctor/skills/read-code Skill
no license3★ repoVerify paper claims with evidence_type "code" against the actual codebase. Use after read-txt to check if code matches what the paper says.
QinghongLin/paperdoctor/skills/read-prior Skill
no license3★ repoWeb-search validation of citation and novelty claims from check_claim.json. Checks whether cited facts are accurate and novelty claims ("first", "pioneering") hold against published literature.
QinghongLin/paperdoctor/skills/read-theory Skill
no license3★ repoVerify theoretical claims — mathematical derivations, proofs, and formal arguments. Targets claims with evidence_type "theoretical" from check_claim.json.
Wang-Cankun/skillshelf/fixtures/library/.agents/skills/commit-push Skill
3★ repoStage all changes, write a conventional-commit message, and push to the current branch's remote. Use when the user says "commit and push", "commit this", or finishes a unit of work and wants it saved upstream.
Wang-Cankun/skillshelf/fixtures/library/commit-push Skill
3★ repoStage all changes, write a conventional-commit message, and push to the current branch's remote. Use when the user says "commit and push", "commit this", or finishes a unit of work and wants it saved upstream.
roebi/agent-skills/skills/session-git-lifecycle-en Skill
no license3★ repoDefines the git-based lifecycle for agent chat sessions: CREATE for new projects (git init with explicit main branch) and RESUME for continuing work from a delivered tar.gz containing a .git folder. Use this skill whenever an agent starts a new software project from scratch, or whenever a user provides a versioned tar.gz to continue work in a new or resumed session. Also covers the handover tag namespace convention (handover/vN) that keeps session delivery tags safely separated from software version tags (vX.Y.Z) used by GitHub Actions release workflows. Trigger phrases: "start new project", "new session", "resume project", "continue from tar", "here is myproject_vN.tar.gz", "untar and continue", "pick up where we left off", "add github actions release workflow".
stdin/buy-vs-build/plugins/buy-vs-build/skills/buy-vs-build-review Skill
3★ repoUse when reviewing a code diff, pull request, or local changes for buy-vs-build mistakes, avoidable custom code, unnecessary dependencies, missed built-ins, missed platform features, or weak decision notes.
stdin/buy-vs-build/skills/buy-vs-build-review Skill
3★ repoUse when reviewing a code diff, pull request, or local changes for buy-vs-build mistakes, avoidable custom code, unnecessary dependencies, missed built-ins, missed platform features, or weak decision notes.
leek/agent-skills/skills/grill-me-plus Skill
3★ repoInterview the user relentlessly about a plan, decision, or idea until reaching shared understanding, resolving each branch of the decision tree. Use Claude Code's AskUserQuestion or Codex's request_user_input when available so decisions are click-to-answer. Use when the user says "grill me", wants to stress-test their thinking, compare design choices, or resolve ambiguous implementation decisions.
leek/agent-skills/skills/laravel-herd-worktrees Skill
3★ repoCreate, list, or remove git worktrees for Laravel projects served by Laravel Herd on macOS. Use when the user needs a branch worktree, .test URL, or per-worktree PHP/composer isolation.
leek/agent-skills/skills/repository-cleanup Skill
3★ repoPersonal collection of agent skills for Claude
uzysjung/uzys-agent-harness/.claude/skills/model-orchestration Skill
3★ repoApply the fixed model-role and thinking-effort policy whenever work is delegated to subagents or a model/effort choice is made: the orchestrator (top-tier model) DIRECTLY sets service direction, reviews plan/spec documents (with multi-persona-review), improves shipped features, and hunts performance/security problems; plan/spec/planning documents are AUTHORED by Opus, which also owns core implementation and V&V, at xhigh or above; repetitive implementation and E2E tests go to Sonnet at high or above — never delegate below those effort floors. Use whenever you are about to spawn an Agent/Task/Workflow worker, pick a model for a subtask, set a thinking/effort level, assign verification, or hand off orchestration because the current model's quota is exhausted. Trigger on "위임해", "에이전트로 돌려", "오케스트레이션", "모델 역할분담", "어떤 모델로", "effort 얼마로", "thinking level", "서브에이전트", or in English "delegate this", "spawn an agent for", "which model should", "route this task", "verify with", "orchestrate". Fire even when the user doesn't name the policy — any delegation decision is in scope.
uzysjung/uzys-agent-harness/.claude/skills/multi-persona-review Skill
3★ repoA panel-review skill that critiques ONE artifact (launch post, README, doc, markdown, plan, design) via 3-5 disjoint user-perspective personas running in parallel, then synthesizes deduped, severity-ranked improvement points (P0/P1/P2). Use when the user says "작성글을 사용자 관점의 페르소나를 여러명 만들어서 (손넷 모델정도로) 피드백 받아바", "다면 리뷰 해볼까", "페르소나로 리뷰", "여러 관점으로 피드백", or in English "multi-persona review", "review this from different user perspectives", "get persona feedback on this post/README/doc", "panel review this artifact". Lighter than a full service audit — point it at ONE artifact, not a whole codebase. NOT for a whole-codebase multi-dimension audit (use ultracode-service-audit) or a single-axis gap-vs-benchmark loop (use gap-analysis-e2e).
uzysjung/uzys-agent-harness/.claude/skills/verification-loop Skill
3★ repoA comprehensive verification system for Claude Code sessions. Every run ends with a fixed verdict — PASS / PASS_WITH_NITS / FAIL — plus severity-labeled findings (CRITICAL/HIGH/MEDIUM/LOW).
uzysjung/uzys-agent-harness/templates/skills/model-orchestration Skill
3★ repoApply the fixed model-role and thinking-effort policy whenever work is delegated to subagents or a model/effort choice is made: the orchestrator (top-tier model) DIRECTLY sets service direction, reviews plan/spec documents (with multi-persona-review), improves shipped features, and hunts performance/security problems; plan/spec/planning documents are AUTHORED by Opus, which also owns core implementation and V&V, at xhigh or above; repetitive implementation and E2E tests go to Sonnet at high or above — never delegate below those effort floors. Use whenever you are about to spawn an Agent/Task/Workflow worker, pick a model for a subtask, set a thinking/effort level, assign verification, or hand off orchestration because the current model's quota is exhausted. Trigger on "위임해", "에이전트로 돌려", "오케스트레이션", "모델 역할분담", "어떤 모델로", "effort 얼마로", "thinking level", "서브에이전트", or in English "delegate this", "spawn an agent for", "which model should", "route this task", "verify with", "orchestrate". Fire even when the user doesn't name the policy — any delegation decision is in scope.
uzysjung/uzys-agent-harness/templates/skills/multi-persona-review Skill
3★ repoA panel-review skill that critiques ONE artifact (launch post, README, doc, markdown, plan, design) via 3-5 disjoint user-perspective personas running in parallel, then synthesizes deduped, severity-ranked improvement points (P0/P1/P2). Use when the user says "작성글을 사용자 관점의 페르소나를 여러명 만들어서 (손넷 모델정도로) 피드백 받아바", "다면 리뷰 해볼까", "페르소나로 리뷰", "여러 관점으로 피드백", or in English "multi-persona review", "review this from different user perspectives", "get persona feedback on this post/README/doc", "panel review this artifact". Lighter than a full service audit — point it at ONE artifact, not a whole codebase. NOT for a whole-codebase multi-dimension audit (use ultracode-service-audit) or a single-axis gap-vs-benchmark loop (use gap-analysis-e2e).
uzysjung/uzys-agent-harness/templates/skills/ui-visual-review Skill
3★ repoCaptures screenshots of key UI flows after E2E tests pass, runs an agent-side first-pass diff (regressions, console errors, layout shifts), then surfaces a checklist for the user's final approval. Also owns the browser-launch procedure the `playwright-launch` rule delegates here: use it whenever a browser must be opened for a human to drive or for automated capture — manual E2E checks, UX/fidelity comparison against a reference product, or a one-time OAuth login. Use after E2E tests pass on a UI track (csr-*, ssr-*, full).
uzysjung/uzys-agent-harness/templates/skills/verification-loop Skill
3★ repoA comprehensive verification system for Claude Code sessions. Every run ends with a fixed verdict — PASS / PASS_WITH_NITS / FAIL — plus severity-labeled findings (CRITICAL/HIGH/MEDIUM/LOW).
gerodp/hermes-productivity-skills/development/git-report Skill
3★ repoReport the commits you authored across every git repo under one folder, for any time window (grouped by repo, with optional line churn).
JayRHa/AgentSkills/code-reviewer Skill
3★ repoReviews a code diff or pull request for correctness bugs, security vulnerabilities, and quality/maintainability problems, producing severity-ranked findings with file/line references and concrete fix suggestions. Use this skill when the user asks to "review this PR", "review my diff", "code review", "look over these changes", "check this code before merge", "find bugs in this change", or pastes a diff/patch and wants feedback. Applies to git diffs, GitHub/GitLab PRs, staged changes, or a set of changed files in any language.
JayRHa/AgentSkills/debug-detective Skill
3★ repoSystematically root-causes software bugs using a reproduce → isolate → hypothesize → bisect → verify methodology, replacing guess-and-check debugging with a disciplined, evidence-driven investigation. Use this skill when a user reports a bug, a test is failing intermittently or consistently, behavior differs between environments, a regression appeared after a change, something "used to work" and now doesn't, an error/stack trace needs root-causing, or when asked to "debug", "find the root cause", "figure out why X happens", or "track down" a defect. Triggers include crashes, wrong output, flaky tests, hangs/deadlocks, memory leaks, performance regressions, heisenbugs, and works-on-my-machine problems.
JayRHa/AgentSkills/git-workflow Skill
3★ repoGuides safe, professional Git usage — branching strategies, atomic clean commits, conventional commit messages, interactive rebase (squash/fixup/reword/reorder), merge vs rebase decisions, conflict resolution, and recovery of lost work via reflog. Use this skill when the user asks to create or clean up a branch, write or amend commits, squash or reorder history, rebase onto main, resolve merge conflicts, undo a bad commit/merge/reset, recover deleted commits or branches, find lost work, fix a detached HEAD, force-push safely, or generally "clean up my git history" before opening a PR.
JayRHa/AgentSkills/okr-writer Skill
3★ repoWrites strong OKRs (Objectives and Key Results) with outcome-focused, inspiring objectives and measurable, ambitious, time-bound key results. Use this skill when the user asks to write, draft, review, critique, or improve OKRs, goals, or quarterly/annual objectives, when they mention "objectives and key results", "set goals for the team", "turn this strategy into OKRs", "are these good key results", or when distinguishing outcomes from outputs/tasks for planning and performance.
JayRHa/AgentSkills/regex-architect Skill
3★ repoDesigns, explains, hardens, and tests regular expressions for parsing and validation tasks (emails, URLs, dates, IPs, log lines, CSV fields, identifiers, etc.) while actively defending against catastrophic backtracking (ReDoS). Use this skill when the user asks to "write a regex", "build/fix a regular expression", "match/extract/validate X with regex", "explain this regex", "why is my regex slow/hanging", check for "ReDoS"/"catastrophic backtracking", or convert a pattern between flavors (PCRE, Python re, JavaScript, Java, Go RE2, .NET). Covers capturing/named groups, anchors, lookarounds, Unicode, and flavor portability.
JayRHa/AgentSkills/secrets-manager Skill
3★ repoDetects, prevents, and remediates leaked credentials and teaches safe secret handling using environment variables, vaults (HashiCorp Vault, AWS/GCP/Azure secret stores), KMS envelope encryption, and rotation. Use this skill when a user mentions hardcoded API keys, passwords, tokens, or .env files in code; asks how to store, inject, or rotate secrets; wants to set up a vault or KMS; needs to scrub a leaked credential from git history; or asks to add pre-commit secret scanning.
JayRHa/AgentSkills/secure-code-review Skill
3★ repoPerforms a security-focused review of code or a diff, hunting for injection, broken authentication/authorization, insecure crypto, hardcoded secrets, unsafe deserialization, SSRF, path traversal, and missing input validation, with exploit scenarios and concrete fixes ranked by severity. Use this skill when the user asks to "do a security review", "audit this code for vulnerabilities", "is this code secure", "check for security issues before deploy", "review this auth/crypto code", or wants a security pass on a PR. Complements general code review with a threat-focused lens.
control-decks/think-it-through/plugins/think-it-through/skills/grill Skill
3★ repoStress-test a proposal, assumption, decision, design, or plan through a relentless multi-turn grill that follows its decision tree one question and recommendation at a time. Use only when the user invokes grill or asks for a demanding challenge; never begin silently.
hcaiano/skills/skills/ask-peer Skill
3★ repoOpposite-model request for one focused pass. In Codex, reach for this autonomously to escalate to Fable (through `claude -p`) when you need stronger reasoning, a second opinion, or a scoped review; in Claude Code it stays manual — Claude asks Codex through `codex exec` only when the user invokes it. Use for a focused pass without a live Herdr pair.
hcaiano/skills/skills/check-logs Skill
3★ repoHenrique Caiano's custom agent skills (Claude, Codex, herdr). Install with: npx skills@latest add hcaiano/skills
hcaiano/skills/skills/review-pr-comments Skill
3★ repoOn-demand review cleanup for an existing PR that has actual feedback: verify each comment, apply valid in-scope fixes in one batched round, respond where useful, and leave the PR merge-ready. Only runs when the user explicitly invokes review-pr-comments.
Ahoo-Wang/skills/plugins/ahoo-wow-skills/skills/wow-code-review Skill
3★ repoUse when reviewing Wow framework code, PR diffs, or pre-merge changes involving aggregates, commands, events, sourcing, sagas, projections, command gateway, Query DSL, starter configuration, or Wow tests
Ahoo-Wang/skills/sources/Wow/skills/wow-code-review Skill
3★ repoUse when reviewing Wow framework code, PR diffs, or pre-merge changes involving aggregates, commands, events, sourcing, sagas, projections, command gateway, Query DSL, starter configuration, or Wow tests
kinhluan/rules-quarkus-skills/.agent-skills/code-reviewer Skill
3★ repoExpert skill for conducting high-quality code reviews following Google's Engineering Practices. Focuses on speed, standards, and mentorship.
liutao773680119-cmyk/relay-dev-skills/.relay/skills/relay-verify Skill
3★ repoUse when about to claim completion or a fix, and verification evidence must be recorded first. 中文常见触发:先做验收、完成前先验证、别先说修好了。
liutao773680119-cmyk/relay-dev-skills/skills/relay-verify Skill
3★ repoUse when about to claim completion or a fix, and verification evidence must be recorded first. 中文常见触发:先做验收、完成前先验证、别先说修好了。
liutao773680119-cmyk/relay-dev-skills/starter/relay-kit-v1/global-skills/relay-verify Skill
3★ repoUse when about to claim completion or a fix, and verification evidence must be recorded first. 中文常见触发:先做验收、完成前先验证、别先说修好了。
Orfi/trackbed/copilot/skills/trackbed-dod Skill
3★ repoInternal Trackbed skill (invoked by trackbed-orchestrate at phase transition, or directly for a mid-phase dry-run). Runs the nine-check Definition-of-Done gate on the outgoing phase, records evidence in the per-phase note, and writes one compact gate stamp. Green or waived stamp required before orchestrate may advance to the next phase; red or missing stamp blocks the transition.
Nembie/claude-code-skills/agents/full-stack-reviewer Skill
3★ repoComplete codebase audit combining code review, Prisma query optimization, and TypeScript analysis with intelligent routing. Use when asked for a full project review, complete codebase audit, or comprehensive quality check of a full-stack application.
Nembie/claude-code-skills/skills/code-reviewer Skill
3★ repoAutomated code review for security, performance, and maintainability. Use when asked for code review, security audit, quality check, PR review, or to find issues in code.
The same file is in 2 other repositories
Nembie/claude-code-skills/skills/env-config-validator Skill
3★ repoValidate environment configuration files, detect missing or misconfigured variables, and generate typed env schemas. Use when asked to validate env files, check environment config, generate .env.example, audit env variables, or create typed env validation.
Nembie/claude-code-skills/skills/git-commit-composer Skill
3★ repoGenerate conventional commit messages from staged git changes. Use when asked to compose a commit message, write a commit, generate conventional commits, or describe staged changes.
The same file is in 2 other repositories
Nembie/claude-code-skills/skills/prisma-migration-reviewer Skill
3★ repoReview Prisma SQL migration files for risks before production deployment. Use when asked to review a migration, check migration safety, analyze schema changes, or audit Prisma migrations before deploying.
The same file is in 2 other repositories
myksyut/pev-harness/skills/pev-dual-review Skill
3★ repo--strict モード専用。Reviewer A (Opus xhigh、固定) と Reviewer B (Sonnet high / Codex CLI から選択) を並列起動し、両者の structured JSON verdict を merge して NICE/NAUGHTY 判定。v2.0 で Reviewer B が選択可能になり、 dual-codex mode (codex CLI subprocess) で真の external model diversity を実現
myksyut/pev-harness/skills/pev-e2e-verify Skill
3★ repoAC に UI / E2E 系の項目が含まれる時、 Playwright CLI で end-to-end test を実行して verify する skill。 token 効率のため MCP ではなく CLI を採用、 Playwright Agents (planner/generator/healer) を reference して test 生成・修復は委譲する。 verifier から auto-dispatch (AC keyword 検知) もしくは --e2e フラグで明示起動される。
myksyut/pev-harness/skills/pev-external-reviewer Skill
3★ repo外部 LLM CLI (v2.0 では OpenAI Codex) を Reviewer として subprocess invoke する skill。 git diff + plan.md + rubric を組み立てて codex exec --json --output-schema に渡し、 structured JSON output を verify.json に merge する。 timeout / non-zero exit / 認証失敗時は自動で dual-claude にfallback (graceful degrade)。
AKSoftCode/aicrew/codex-skills/aicrew-conclude Skill
3★ repoWrap up a session in Codex with summary, tests, risks, and a commit message proposal.
GhostlyGawd/recursive-harness/plugins/recursive-verify/skills/verify Skill
3★ repoProduce a deterministic structural scorecard, run a fixed Atlas-style query, inspect an eval corpus without executing repository code, or emit a review-only proposal diff. Use when a user asks for portable evidence about a repository, its tests or instructions, eval-corpus health, or a proposed verification change without modifying the project.
GhostlyGawd/recursive-harness/skills/build-loop Skill
3★ repoThe per-feature build→review discipline — run it on ANY non-trivial build/feature/fix/refactor (anything with a definition of done or that changes behavior) so you stop re-prompting it and stop shipping green-but-wrong code. Sequence: align on intent → criteria+predict → write FAILING example + PROPERTY tests → fresh-context review of spec+tests BEFORE coding → build to green → verify in practice end-to-end → capture eval → PR. A conductor that COMPOSES calibration/critic/verify/eval-capture — never reimplements them. Skip only trivial one-liners, pure lookups, read-only analysis.
GhostlyGawd/recursive-harness/skills/guard Skill
3★ repoConfigure or explain Recursive Guard, a separately trusted Codex plugin that is inert unless a repository explicitly adds a reviewed .recursive-guard.json policy. Use when a user wants opt-in protection for instruction, provider, hook, or other sensitive repository paths without replacing existing agent configuration.
GhostlyGawd/recursive-harness/skills/harness-authoring Skill
3★ repoStandards for writing or modifying the harness's own artifacts — skills, commands, agents, hooks, user-model entries. Use whenever /retro routes a learning into a new or edited artifact, when promoting a project-level learning upstream, or when refactoring existing skills. Encodes budgets, provenance, falsifiability, and the duplication check. Writing an artifact without this skill produces lint failures and junk-drawer drift.
GhostlyGawd/recursive-harness/skills/harness-pr-ops Skill
3★ repoUse while DRIVING a harness change onto trunk — opening/merging PRs, especially several at once (a roadmap or /retro batch), or the moment a guard unexpectedly BLOCKS a git/gh/bin-harness command mid-flow. Encodes the operating mechanics the enforcement guards + GitHub impose that aren't obvious until they bite: stacked-PR merge order, running locked-path commands cleanly, and what to expect at the human gate. Pairs with harness-pr (the PR template), windows-host-paths (token mechanics), worktree.
GhostlyGawd/recursive-harness/skills/loop-prompt-architect Skill
3★ repoConsultant procedure for authoring self-contained loop prompts. Trigger when the user asks for a prompt that runs "until it's done/verified/bug-free", wants /goal + /loop templates, says "loop Claude until X is finished", needs a fuzzy goal turned into checkable done-criteria, or returns with a failed loop-run to autopsy. Forges wishes into 3-7 binary Definition-of-Done criteria, per-iteration verification, a state artifact, a stuck protocol, and three exits (success/budget/blocked). AUTHORS loop prompts as deliverables — NOT the built-in /loop runner, NOT build-loop.
GhostlyGawd/recursive-harness/skills/nested-repos Skill
3★ repoChoose HOW one git repo lives inside another — submodule vs subtree vs gitignore+materialize-hook vs vendor-and-commit. Trigger when you reach for `git submodule`/`git subtree`, weigh a "repo inside a repo", need a sub-project (plugin/lib with its own repo) to ALSO live here AND ride into worktrees, or want a vendored dep that stays updatable. Each trades worktree presence vs in-place dev vs history ownership; pick blind → empty submodule, or a plugin missing from worktrees. NB `.worktreeinclude` canNOT carry a nested-repo dir (verified). Defers to vendoring-skills + worktree.
GhostlyGawd/recursive-harness/skills/venture-build Skill
3★ repoEnd-to-end procedure for turning a charter (GOAL.md or inline brief) into a validated, managed venture: predict, scaffold the subproject, stand up a markdown PM board, fan out a strategy-IP workflow, build the MVP contract-first with tests-as-you-go, validate LIVE (not just unit tests), run an adversarial-review workflow and fix findings, write the venture ledger, branch+commit and score. Trigger when the user asks to build/spin up/stand up a company, product, MVP, or venture end-to-end, or runs /venture. Skipping it yields demos without validation gates or a ledger.
GhostlyGawd/recursive-harness/skills/verify Skill
3★ repoProduce a deterministic structural scorecard, run a fixed Atlas-style query, inspect an eval corpus without executing repository code, or emit a review-only proposal diff. Use when a user asks for portable evidence about a repository, its tests or instructions, eval-corpus health, or a proposed verification change without modifying the project.
hollandkevint/data-product-operator/skills/data-product-validation Skill
3★ repoScore whether a data product idea is worth building before committing resources. Validation scorecard, experiment design, and go/kill decisions. Use when evaluating feasibility, making go/no-go decisions, validating demand, sizing bets, or when someone asks "is this worth building?" or "should we invest in this?"
hollandkevint/data-product-operator/skills/grill-me-data Skill
3★ repoDecision tree exploration for data product plans. Interview relentlessly about schema decisions, consumer contracts, quality SLAs, and delivery choices. Use when planning a data product, designing a schema, choosing a delivery method, or when someone asks "grill me on this data product" or "what am I missing in this design?"