В каталоге 183 730 навыков в 14 категориях.
Review a PRD for completeness, quality, and actionability
Review an existing PRD for completeness, quality, and anti-patterns when the user asks to review, critique, or check a P...
Use as a pre-commit quality gate — review the working diff for stub patterns (TODO/FIXME/`unimplemented!()`/`todo!()`),...
Pre-merge review focusing on correctness, testing, security, refactor safety, and maintainability. Spawns the senior-rev...
Audit a Zeebe BPMN process and its glue-code (workers, process adapter, tests) for consistency and coverage, producing a...
Review a product from the user's perspective — build/refine a user persona, map their use cases (jobs-to-be-done), then...
Review app polish — native feel, user-facing text, UX quality, and professional presentation
Load and review the complete JSON state for a workflow project before task work. Use when the user asks to review projec...
Review and analyze LLM prompts using the 10-Layer Architecture. Provides detailed assessment without modifying files.
Generates smart App Store review prompt infrastructure with configurable conditions and platform detection. Use when use...
Write effective code review prompts, review context documents, and AI-assisted review infrastructure for any project. Co...
Review direct and indirect prompt-injection exposure in LLM, RAG, multimodal, copilot, and agentic applications through...
Review a prompt plan against its source spec: launches an internal prompt plan review and `/peer-review` in parallel and...
用于审查现有物理推导或解答，检查是否存在跳步、错误近似、量纲问题、边界条件遗漏和概念混淆。
Review PRs in brave/brave-core for best practices violations. Supports single PR (#12345), state filter (open/closed/all...
Use for "check open PRs", "review PRs across my repos", "merge the dependabot PRs", "clean up PRs". Scans every git repo...
Reviews one GitHub pull request and prepares a verified local review or posts its exact approved contents. Use when the...
Perform an expert frontend code review directly from a GitHub Pull Request using gh CLI.
Run the Python code review protocol on scripts in code/py/. Checks code quality, reproducibility, pandas idioms, figure...
Comprehensive Python/FastAPI backend code review with optional parallel agents
Use this skill when you need to review Python code changes with an extremely high quality bar. This agent should be invo...
Reviews test files (Pytest/Jest) for quality, coverage, and mocking standards.
Analyze code for cross-file quality issues: duplicated logic, architectural inconsistencies, and abstraction opportuniti...
Use on every workspace.new_asks or review_item.added event, when writing the morning hit list, when Bryan asks what need...
Work through a whole review queue with a token-lean loop. Use when the user says "review my queue", "what is waiting for...
Quick code review focusing on correctness, style, DX, UX copy, and overengineering. Spawns the senior-review-specialist...
Run the R code review protocol on R scripts. Checks code quality, reproducibility, domain correctness, and professional...
Read-only R code review protocol for `.R` scripts. Checks code quality, reproducibility, domain correctness, tidyverse i...
Audit for race conditions in timers, hotkeys, callbacks, and shared state
Open Audit for race conditions in timers, hotkeys, callbacks, and shared state
Audit retrieval-augmented generation pipelines, vector and embedding systems, enterprise search, and agent knowledge sto...
Detects review-blocking configuration issues including sub-1.0 version numbers, beta in app name, staging endpoints, and...
Use when the lead wants tasks vetted before juniors start them — "vet these before I hand them out", "are these tasks st...
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or techni...
Load this skill when looking back over a period of work in a repo: what shipped, how work flowed, and the issues the his...
Audit the paint and frame loop paths for STA message pump reentrancy — COM calls that can dispatch timer/hotkey callback...
Facilitate a structured conversation to customize how the review molecule works -- atom loading rules, severity classifi...
Pre-release readiness review. Scans for debug artifacts, version mismatches, changelog gaps, git hygiene issues, breakin...
Comprehensive Remix v2 code review with optional parallel agents. Detects Remix v2 in package.json, loads relevant revie...
Execute /review-renovate slash command.
リポジトリ全体を構造、コード品質、テスト、ドキュメントの観点から体系的にレビューし、優先度付きの改善レポートを生成する
Use when asked to review or critique finished implementation work ("review this", "code review", "look at the PR"), or w...
Detects improper use of SKStoreReviewController.requestReview() that violates Guideline 5.6.1 — including prompts trigge...
Coordinate one durable specification or code review as the requestor through the shared review-exchange launcher.
Verify research findings against the sources they cite, in fresh sub-agents that read each claim in context and quote ea...
Review and validate a resource implementation follows all patterns. Use after creating a resource or when refactoring ex...
Audit for memory leaks, handle leaks, GDI leaks, and CPU churn
Open Audit for memory leaks, handle leaks, GDI leaks, and CPU churn
Manage and respond to WooCommerce product reviews. Build customer relationships through thoughtful responses, handle neg...
Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "w...
Respond to online reviews. Use when: drafting replies for Google, Yelp, G2, or building review response templates.
Systematic review response strategy guide for RebuttalStudio. Use when developing response strategies for reviewer comme...
Write the right reply to a customer review — positive, negative, or mixed. Use when asked to respond to a review, reply...
Generates on-brand responses to both 5-star and 1-star reviews to protect reputation.
Machine-readable findings count that closes every review or QA report for the task board.
Comprehensive PM resume review and tailoring against 10 best practices including XYZ+S formula, keyword optimization, jo...
Resume an interrupted review through its typed migration, status, and role workflow.
Mine past automated-review runs for recurring process and judgment failures, then propose fixes to the review setup as o...
Meta-audit all review skills for stale references, drifted architecture claims, and cross-skill inconsistencies
Review an architecture RFC against project architecture standards and best practices. Use when an RFC document needs des...
Review an implemented RFC in a fresh context against its acceptance criteria, RULES.md and the test plan, and save the r...
Review RFCs for the ToolHive ecosystem. Use when the user wants to review, critique, or provide feedback on an RFC for t...
Pruefung: Internationaler Bezug und Schnittstellen im Plugin ki governance; schärft Rollen, Belege, Fachnormen, Risiken,...
Review a roadmap in a fresh agent before lock. Use for /review-roadmap.
Run a change round for planning units the user reviewed - read the numbered changes in each unit's Review section and ha...
Run one review round of CLAUDE.md on this branch
Routes PR review by diff — delegates to backend/frontend specialist.
Routes ambiguous review or planning to one leaf workflow. Do not use for a clear code, security, UI, architecture, or mi...
Use when preparing a PR description, suggesting reviewers, or flagging risk — produces owner-mapped roles plus historica...
Comprehensive Ruby and Rails code review using Sandi Metz rules and SOLID principles. Automatically runs rubycritic and...
Nezávislé review rule s čistým kontextem — posoudí konformitu s konvencemi (pojmenování, tvar `paths`, vymahatelnost jed...
セッションの会話から恒久的な振る舞いルールを抽出し、AGENTS.md と突き合わせて追加すべきものを提示する。出力は rules と agents_md_patch の二部構成。
Comprehensive Rust code review with optional parallel agents
Run all review-rust* skills as a comprehensive code review. Applies review-rust-code (best practices, type-driven design...
Review and enforce Rust async/tokio concurrency patterns. Use when writing, reviewing, or debugging async Rust code. Cov...
Review and enforce Rust best practices, clean code principles, and idiomatic patterns. Use when reviewing code, writing...
Review and enforce Rust memory optimization patterns. Use when writing, reviewing, or debugging Rust code for memory eff...
Review a data-contract or serialization-schema change against named producers, consumers, stored records, compatibility...
Provides the complete code review scoring rubric with 10 weighted categories, severity multipliers, and deduction calcul...
Scrape product reviews from G2, Capterra, and Trustpilot using Apify. Single script with platform dispatch. Use when you...
Review a script for documentation quality, code standards, and reproducibility. Helps ensure code is ready for the metho...
Use when the user says "review security", "/review-security", "security review", "is this safe", "check for vulnerabilit...
A specialised skill for detecting security vulnerabilities in Python/JS codebases.
White-box security audit. Blue-teamer and lead red-teamer run in parallel isolation for an independent first pass — neit...
Internal security review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit;...
Security-focused review covering vulnerabilities, privacy, infrastructure security, data integrity, and supply chain. Sp...
Use this agent when you need to perform security audits, vulnerability assessments, or security reviews of code. This in...
Security audit for vulnerabilities, secrets, and unsafe patterns. Use before releases, after adding auth code, or when r...
Review application and infrastructure changes for exploitable security risks by tracing assets, trust boundaries, attack...
보안 관점에서 코드를 검토합니다. OWASP Top 10, credential 노출, injection 공격 등을 체크합니다.
Analyze code for security vulnerabilities, insecure patterns, and security regressions using strict determination criter...
Review and triage semgrep security scan results to identify true positive vulnerabilities. Use when analyzing semgrep ou...
Internal SEO review pass of the agentic-workflow review pack — composed in-turn by review-change and product-audit; not...
Retrieval practice session to test retention on a topic. Use when user wants to test their knowledge, practice recall, q...
Shared severity levels, issue ID format, and verdict criteria for all code reviewers. Use when performing code reviews o...
Audit HLSL pixel shaders for GPU performance — math optimizations, ALU reduction, texture efficiency at 120-240fps
Incremental HLSL shader audit — grep-driven, no agent swarm, built for codebases with prior optimization passes
Use when reviewing, debugging, or hardening Shell/Bash scripts in this repo (.github/workflows/*.yml steps, website buil...
Review the authenticated user’s saved Shopify apps, markets, keywords or developers and compare selected earlier finding...