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
Yue-Zhou1/zkcrypto-audit/plugins/crypto-primitive-auditors/skills/ecc-pairing-auditor Skill
3★ repoAudit elliptic-curve, pairing, and BLS signature code for point-validation, subgroup, serialization, DST, and pairing-equation failures. Use when reviewing deserialization, `hash_to_curve`, aggregate verification, or batch pairing logic.
Yue-Zhou1/zkcrypto-audit/plugins/crypto-primitive-auditors/skills/signature-scheme-auditor Skill
3★ repoAudit classical signature schemes — generic ECDSA across curves, Schnorr/ BIP-340, EdDSA/Ed25519, RSA-PSS and PKCS#1 v1.5 — for verification-equation correctness, malleability, canonical encoding, public-key validation, and hash/prehash semantics. Use for standalone signature library review outside Ethereum application encoding, BLS, or threshold protocols.
Yue-Zhou1/zkcrypto-audit/plugins/evidence-and-tooling/skills/formal-verification-bridge Skill
3★ repoBridge validated audit findings into optional external formal-verification tooling (Ecne, Picus, Circomspect) with explicit environment checks, reproducible exports, and tool-scoped caveat capture.
Yue-Zhou1/zkcrypto-audit/plugins/evidence-and-tooling/skills/kani-harness-gen Skill
3★ repoGenerate Kani proof harnesses for Rust crypto code. User-triggered only — never auto-invoked by the audit flow. Produces formal verification evidence for crypto-fp-check.
Yue-Zhou1/zkcrypto-audit/plugins/implementation-safety/skills/fault-injection-auditor Skill
3★ repoAudit cryptographic code for active fault-injection attacks: RSA-CRT Bellcore faults, ECDSA/EdDSA differential fault analysis, verification-skip glitches, redundant-computation bypass, and verify-after-sign gaps. Use when the threat model includes an attacker who can glitch computation, distinct from passive side-channel leakage.
KrishnaShettyDev/dosed/code-review Skill
3★ repoAmphetamine+Ketamine enhanced code review. Combines hyperfocus thoroughness with objective distance. Produces comprehensive, actionable code review feedback. Activates with "/code-review", "review this code", "PR review", or when user shares code for feedback.
jovd83/restassured-skill/coverage_plan/review Skill
3★ repoUse when Codex needs to present a generated Rest Assured API coverage plan to the user, request explicit approval, and block implementation until the scope is confirmed.
ribeirogab/specwright/plugins/sw/skills/plan Skill
3★ repoA multi-host plugin for Claude Code, Codex, and OpenCode. It gives a repository one explicit, change-driven engineering workflow:
ribeirogab/specwright/plugins/sw/skills/pr Skill
3★ repoOpen the pull request for the current issue, following specwright PR conventions — resolves branch/base, pushes if needed, fills the repo PR template, English Conventional-Commit title and body, records the runtime-verification results, no AI attribution. Use as the delivery step of the issue pipeline, or whenever the user asks to open a PR.
ribeirogab/specwright/plugins/sw/skills/review Skill
3★ repoA multi-host plugin for Claude Code, Codex, and OpenCode. It gives a repository one explicit, change-driven engineering workflow:
hnikoloski/imlazy/skills/imlazy-code-review Skill
3★ repoTwo roles — request a code review (dispatch reviewer subagent) and receive a code review (process feedback rigorously). Use after each task in planning full mode, before merge, or when stuck
hnikoloski/imlazy/skills/imlazy-finish-branch Skill
3★ repoUse when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
hnikoloski/imlazy/skills/imlazy-receive-review Skill
3★ repoUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
hnikoloski/imlazy/skills/imlazy-request-review Skill
3★ repoUse when completing tasks, implementing major features, or before merging to verify work meets requirements
hnikoloski/imlazy/skills/imlazy-verify Skill
3★ repoA comprehensive verification system for Claude Code sessions.
xonika9/agent-skills/skills/x9-codex-delegation Skill
3★ repoClaude Code only; never use in a Codex session. Use when substantial, well-scoped work should actually be delegated to Codex — «отдай в Codex», «делегируй Codex», «передай эту часть работы в Codex, чтобы распределить лимиты», "use Codex", implementation, migration, codebase analysis, logged-in browser work, UI verification, or a second-opinion review. Do not use for checking or planning subscription quotas without a concrete task, trivial work, choosing between Claude models, or merely drafting a prompt/brief that is not explicitly being sent to Codex.
coroboros/agent-skills/skills/code-ultrareview Skill
3★ repoEight-axis judgment code review for the current diff — Correctness, Simplification, Tests, Documentation, Style, Intent, Design/API, Performance (+ Coherence on metadata changes). Five-phase pipeline scope → deterministic tool battery (npx/uvx-preferred, zero-install for the JS + Python majority) → 8 parallel LLM axis reviewers → Haiku validators on sub-80 findings (verbatim rubric, ≥80 threshold) → synthesis with no-silent-drop + Conventional Comments JSONL. Every report closes with "What I did NOT check" (security → /security-review, runtime perf, flaky detection). Opt-in flags `--verify-build`, `--mutation-test`, `--reconcile`, `--apply-safe`. Public-skill posture — zero auto-install, graceful skip on missing native tools. Invoke before a commit or PR — "review my changes", "deep review", "did I miss anything", "check before I commit", "audit this PR", "drift / gaps / blind spots".
The same file is in 1 other repository
coroboros/agent-skills/skills/design-system Skill
3★ repoGovern an existing DESIGN.md — Google's open standard for design tokens (YAML frontmatter + eight prose sections). Auto-activates during UI edits to enforce token-only sourcing for colors, typography, spacing, and corner radius when a DESIGN.md is present; steps aside when none exists — it never forces or authors one (`/award-design` authors it up front, then builds under it). Exposes seven CLI-backed subcommands — audit (lint + fix), diff (regression check), export (Tailwind / DTCG), spec (canonical spec), migrate (port legacy Stitch), init (minimal scaffold fallback), audit-extensions (drift check vs globals.css @theme). Token-affecting UI changes update DESIGN.md first, audit, then propagate to code.
coroboros/agent-skills/skills/scaffold Skill
3★ repoBootstrap a new web project on a strictly opinionated Cloudflare Workers stack — Next.js 16 or Astro 6, TypeScript strict, pnpm, Biome, Tailwind. No fallbacks: no Vercel/Netlify, no ESLint/Prettier, no swap. Skip if the user wants any of these. Use when the user says "start a new project", "bootstrap", "init", "scaffold", "create a new site", or is working in an empty directory and wants production-ready foundations.
lythos-labs/lythoskill/packages/lythoskill-project-cortex/skill Skill
3★ repoRegister tasks BEFORE fixing bugs. Close epics when work is done. Always use CLI for state transitions — never mv files by hand. CLI moves update Status History; manual mv causes probe mismatches. Never leave state drift for the next agent to discover via git log. GTD-style governance: ADR, Epic, Task, Wiki. Numeric-prefixed directories enforce workflow order. Timestamp IDs prevent collision. ZK task review (WHAT/WHY/HOW) ensures subagent-readable requirements before assignment. probe detects stale backlog, epic drift, and history mismatches. **Task-git discipline**: One task = 2-5 commits (core, tests, docs, trailer). Every commit includes TASK-xxx for traceability. Task card includes Commit Map and Verification Matrix.
lythos-labs/lythoskill/packages/lythoskill-sober/skill Skill
3★ repoStay clear-headed. Before you commit to a conclusion, check your basis. Is this evidence or assumption? Do the sources agree? What's the confidence per claim — not in general, but specifically? When you catch yourself listing risks without checking, or hesitating between directions without data, that's the signal to stop and verify.
lythos-labs/lythoskill/skills/lythoskill-project-cortex Skill
3★ repoRegister tasks BEFORE fixing bugs. Close epics when work is done. Always use CLI for state transitions — never mv files by hand. CLI moves update Status History; manual mv causes probe mismatches. Never leave state drift for the next agent to discover via git log. GTD-style governance: ADR, Epic, Task, Wiki. Numeric-prefixed directories enforce workflow order. Timestamp IDs prevent collision. ZK task review (WHAT/WHY/HOW) ensures subagent-readable requirements before assignment. probe detects stale backlog, epic drift, and history mismatches. **Task-git discipline**: One task = 2-5 commits (core, tests, docs, trailer). Every commit includes TASK-xxx for traceability. Task card includes Commit Map and Verification Matrix.
lythos-labs/lythoskill/skills/lythoskill-sober Skill
3★ repoStay clear-headed. Before you commit to a conclusion, check your basis. Is this evidence or assumption? Do the sources agree? What's the confidence per claim — not in general, but specifically? When you catch yourself listing risks without checking, or hesitating between directions without data, that's the signal to stop and verify.
TheColliery/CoalLedger/skills/doc-grounding Skill
3★ repoDocs-health grounding scan — doc claims verified against their SOURCE OF TRUTH: the code (README-vs-code, docstring params, examples that must run), the data (figures, tables, cited records), an original text (a rendering such as a translation, summary, or quote vs what it renders), or reality (versions, dates, external facts — verified REAL-TIME against MULTIPLE authoritative sources). Catches WRONG docs: fabricated claims, stale assertions, numbers that do not recompute. Triggers on: "/doc-grounding", "doc-grounding", "does the doc match the code", "verify doc claims", "fact-check this doc". Semantic (consent-gated Full) plus a cheap mechanical recompute layer (stated arithmetic, unit sanity). Offline or unverifiable degrades safe to "⚠️ unverified" — never a guess. Severity judged by context, never mechanical; claims needing formal verification escalate to CoalBoard.
Martin-Hausleitner/martins-awesome-skills/skills/github/github-code-review Skill
3★ repoReview code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with gh CLI or falls back to git + GitHub REST API via curl.
Martin-Hausleitner/martins-awesome-skills/skills/software-development/requesting-code-review Skill
3★ repoPre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.
The same file is in 1 other repository
mrDesign-ww/vault-os/shell/claude/skills/git-guardrails-claude-code Skill
3★ repoSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
The same file is in 18 other repositories
mrDesign-ww/vault-os/shell/claude/skills/grill-me Skill
3★ 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
mrDesign-ww/vault-os/shell/claude/skills/prototype Skill
3★ repoBuild a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
The same file is in 11 other repositories
mrDesign-ww/vault-os/shell/claude/skills/setup-pre-commit Skill
3★ repoSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
The same file is in 19 other repositories
nbialk/quiver-cli/template/.agents/skills/design/impeccable Skill
3★ 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.
nbialk/quiver-cli/template/.agents/skills/repo/repo-init-node Skill
3★ repoScaffold a new Node.js/pnpm project with TypeScript, ESLint, Prettier, .gitignore, and CLAUDE.md.
gy910210/hermes-research-skills/skills/role-review-panel-zh Skill
3★ repo多职责评审面板:围绕同一份方案或文稿,模拟架构、产品、算法、工程等不同职责视角进行中文审查、互相提问、多轮讨论与收敛,输出分歧点、取舍与修订动作。适合技术方案评审、路线图收敛与复杂研究判断。
angad-kandhari/deliberate/skills/review Skill
3★ repoCode review discipline. Load when reviewing a PR (your own or someone else's) or auditing existing code. Covers reading intent first, reviewing in layers top-down, labeling comments by severity, hunting for what isn't there, reviewing tests like code, and self-reviewing before submit.
angad-kandhari/deliberate/skills/verify Skill
3★ repoVerification discipline. Load before claiming work is done, reporting progress, or handing off a change. Covers demonstrating done instead of declaring it, never weakening a check to make it pass, exercising real behavior beyond green tests, hunting the almost-right bug, reporting observations instead of expectations, disclosing what wasn't verified, and making human verification cheap.
MiaoY0uShan/FP/.claude/skills/review-changes Skill
3★ repoPerform a structured code review using change detection and impact
MiaoY0uShan/FP/.codebuddy/skills/review-changes Skill
3★ repoPerform a structured code review using change detection and impact
MiaoY0uShan/FP/.gemini/skills/review-changes Skill
3★ repoPerform a structured code review using change detection and impact
MiaoY0uShan/FP/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/aider/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/claude-code/.claude/skills/fp/references/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/cline/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/codex/.agents/skills/fp/references/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/cursor/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/gemini-cli/fp/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/github-copilot-cli/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/github-copilot-editor/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/kiro/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/opencode/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/roo-code/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/universal/.fp-package/payload/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
MiaoY0uShan/FP/install/windsurf/fp/delegated-execution Skill
3★ repoUse only when routed by FP after an executable plan is accepted and the current host exposes a verified subagent runtime; dispatch a fresh implementer, task reviewer, bounded fixer/re-review loop, final integration reviewer, and parent verification.
lawzava/megapowers/plugins/mega-orchestration/skills/cross-model-verification Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
Finishing a development branch
lawzava/megapowers/plugins/megapowers/skills/finishing-a-development-branch Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
lawzava/megapowers/plugins/megapowers/skills/receiving-code-review Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
lawzava/megapowers/plugins/megapowers/skills/requesting-code-review Skill
3★ repoUse when finished work needs review before merge. Triggers on "review this", "ready to merge", or "check my work". Verify behavior first.
lawzava/megapowers/plugins/megapowers/skills/using-git-worktrees Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
Verification before completion
lawzava/megapowers/plugins/megapowers/skills/verification-before-completion Skill
3★ repoSkills, plugins, and hooks that change how coding agents work — Claude Code, Codex, OpenCode, Antigravity. Measured, not vibed.
NaderNabil216/skillsmith/skills/process-pr-comments Skill
3★ repoFull PR/MR review-comment workflow for GitHub, GitLab, and Bitbucket. Use whenever the user wants to process, address, or work through pull- or merge-request review comments — e.g. "process PR comments", "address review feedback on PR/MR 123", "apply PR review comments", "work through MR X". Detects the forge (CLI-first, REST fallback), sets up the branch, scores unresolved comments against the actual code, gets per-comment approval (or one-shot auto-apply), plans and implements fixes, suggests a commit message, and (advanced) extracts reusable rules.
NaderNabil216/skillsmith/skills/review-pr Skill
3★ repoUniversal PR review workflow for any AI assistant to verify architecture, clean code, SOLID design, and test quality in any programming language. Two modes: simple (default) reviews the diff with severity-ranked findings; advanced adds existing-comment dedup (never repeat what reviewers already said — agree/reply/react instead), security/performance/dependency review, and optional build+test verification in a temporary worktree. Use when asked to "review PR 123", "review this MR", "review this branch against develop", "compare and review feature/x", or "do a deep/advanced/thorough review of this PR".