Skills tagged review: 80 agent skills for Claude Code

• advisor — Advisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done.
• agents-sdk — Build, debug, or review Cloudflare Agents SDK applications using the agents package.
• analyzing-release-readiness — Trigger a pre-merge release readiness review on a GitHub PR, GitLab MR, or local branch.
• autoplan — Auto-review pipeline — reads the full CEO, design, eng.
• benchmark-due-diligence — Runs adversarial due-diligence on a benchmark the user envies — a founder, KOL, company.
• cavecrew — When to delegate to `cavecrew-investigator` (locate code).
• caveman-evidence-review — Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings.
• caveman-learn — Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned.
• caveman-review — Compressed code review - one line per finding with location, problem and fix. Use for /caveman-review, "review this PR", or "review the diff".
• claude-md-progressive-disclosurer — Optimize, slim, or restructure CLAUDE.md/AGENTS.md with progressive disclosure and zero information loss. Use when the user explicitly asks to audit, 精简, 瘦身.
• claude-migrate-memory-to-doc — Migrates Claude Code personal memory (the per-project memory/ directory) into tool-agnostic reference docs.
• code-improver — Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names.
• code-review — Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes.
• copy-editing — When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content.
• design-review — Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)
• deslop — Remove AI-generated code slop and clean up code style
• devex-review — Live developer experience audit. (gstack)
• devils-advocate — 结构化压力测试一个论点（devil's advocate / 魔鬼代言人）：把论点拆成显性断言与隐性假设（A1/A2 编号）， 逐条在用户给定的证据材料里检索带出处的反方论证，标 High/Medium/Low 风险等级，补基础比率外部视角， 最后给出「可监测的证伪信号」清单；输出结构化 findings +.
• differential-review — Performs security-focused differential review of code changes.
• docs-cleaner — Consolidates redundant documentation while preserving all valuable content; keeps a doc set truthful after things change.
• document-release — Release documentation audit. (gstack)
• emil-design-eng — This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
• expo-design-system — Framework (OSS). Build and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow.
• fact-checker — Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation.
• find-animation-opportunities — Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't.
• get-pr-comments — Fetch and summarize review comments from the active pull request
• git-safety-net — Audits, preserves, recovers, and safely retires local Git state: unpushed or wrong-branch commits, dirty or detached worktrees.
• github-review-pr — Reviews or re-reviews one contributor pull request—including an explicitly named closed PR being reconsidered—or a bounded newest-to-oldest sweep of all open.
• grill-me — A relentless interview to sharpen a plan or design.
• grill-with-docs — A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
• grilling — Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
• gstack-openclaw-ceo-review — Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope.
• gstack-openclaw-retro — Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking.
• improve-animations — Survey a codebase's animation and motion code as a senior motion advisor.
• improve-codebase-architecture — Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
• interrogate — Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
• ios-design-review — Visual design audit for iOS apps on real hardware. (gstack)
• maintain-verification-skill — Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature.
• make-pr-easy-to-review — Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior.
• meeting-minutes-taker — Transforms raw meeting transcripts into high-fidelity, structured meeting minutes (notes / summaries).
• no-comments — Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
• plan-ceo-review — CEO/founder-mode plan review. (gstack)
• plan-design-review — Designer's eye plan review — interactive, like CEO and Eng review. (gstack)
• plan-devex-review — Interactive developer experience plan review. (gstack)
• plan-eng-review — Eng manager-mode plan review. (gstack)
• Poteto Mode — poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
• pr — Use when writing a PR body.
• pr-review-canvas — Generate an interactive PR review walkthrough as an HTML page.
• principle-attack-the-premise — Apply when two or more fixes that share one premise have failed the same gate.
• principle-minimize-reader-load — Apply when reviewing or shaping code that's hard to trace.
• principle-prove-it-works — Apply after completing a task, before declaring done.
• principle-test-behavior-not-implementation — Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value.
• prior-work-retrieval — Only for explicit prior-work/reuse/history requests; never for read-only status or inspection.
• read-docx-review — 读取 Word/WPS 审阅后的 docx，把批注（comments）与修订（track changes）提取成可逐条裁决的 markdown 对账表或 JSON。触发场景：对方批注完的合同/协议/书稿/报告回来了要读意见；「提取 docx 批注」「审阅意见对账」「读一下修订」「谁批了什么、批在哪」；WPS.
• reflect — Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill.
• remediating-with-aws-security-agent — Pull AWS Security Agent findings (penetration tests and code reviews) and drive remediation.
• retro — Conduct a retrospective on a coding session.
• retro — Weekly engineering retrospective. (gstack)
• review — Pre-landing PR review. (gstack)
• review-and-ship — Review the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
• review-animations — Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
• review-plugin-submission — Audit a Cursor plugin for marketplace readiness. Use when validating manifests, component metadata, discovery paths, and submission quality before publishing.
• review-walkthrough — Generates an interactive HTML walkthrough for reviewing code changes. Use only when explicitly called.
• run-learning-retrospective — Evaluate learning progress, identify blockers, and adjust the learning plan
• show-me-your-work — Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result).
• skill-reviewer — Reviews and improves Claude Code skills against official best practices.
• technical-writing — Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax.
• test-audit — Find low-value or duplicate tests and the test-only code they keep alive. (gstack)
• thermo-nuclear-code-quality-review — Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.
• thermo-nuclear-review — Comprehensive security and correctness audit of a branch's changes.
• thermos — Launch both thermo-nuclear review subagents in parallel, then synthesize their findings.
• transcript-fixer — Corrects speech-to-text transcription errors with dictionary rules and Claude's built-in AI (no external API key required).
• typescript-best-practices — TypeScript best practices. Use when reading or editing any .ts or .tsx file.
• unslop — Cut AI tells from any writing. Must always apply.
• verify-and-stop — Prove existing work meets acceptance conditions without expanding scope.
• web-design-guidelines — Review UI code for Web Interface Guidelines compliance.
• weekly-review — Produce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work
• what-did-i-get-done — Summarize authored commits over a user-specified time period into a concise update
• why — Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
• workers-best-practices — Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.