Каталог навыков агентов

Advanced code review with multiple sequential agents. Customize for your project.

Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification...

Multi-specialist collaborative work review using independent subagents for comprehensive analysis

Levantamento de atividade de um membro do time (GitHub + JIRA) durante uma sprint. Aceita nome, GitHub username ou parte...

Review a plan before work or a diff after it in five lanes, findings first with file:line anchors. Use when asked if a p...

Complete quality assurance workflow orchestrating validation, comprehensive review, and functional testing. Sequential w...

Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing...

Use when reviewing pull requests. Covers PR examination, code quality checks, adding feedback, and pass/fail decisions.

Design spec-based review workflows with visual proof and issue classification. Use when setting up review processes, val...

Writes a critical review of a book, film, exhibition, album, restaurant, or performance from the reviewer's notes and a...

Deterministic, multi-model code review system and skill for XYZ. Summon frontier reviewers (Command Code -> Qwen 3.8-Max...

Reviewable synthetic skill that fetches a remote template before processing notes.

検証Agent - 全層の結果を検証し、最終判定（PASS/REVISE/REJECT）を下す

Start de rapport_reviewen workflow. Gebruik dit wanneer de gebruiker een rapport of sectie wil laten nakijken op taal, A...

專案規範審查與萃取：讀取專案內的規範文件執行合規審查，或從現有程式碼反向萃取隱含慣例產出 .standards/ 草稿。 規範文件由使用者維護在專案中（如 .standards/ 目錄），skill 提供審查與萃取兩種工作流。 使用時機：實...

MUST BE USED for code review. Use PROACTIVELY when /review command is invoked or after any code changes to check correct...

Read-only code reviewer for agent-flow. Reviews one diff against the issue's acceptance criteria, repo rules in AGENTS.m...

Skill do Reviewer Final para validação completa antes do deploy. Use quando precisar validar que todos os passos do pipe...

Code review, PR analysis, and quality feedback. USE WHEN user mentions review, PR, pull request, code quality, best prac...

Friendly code review specialist providing constructive feedback with mentor style. Use when reviewing code quality, sugg...

A built-in agent for conducting code reviews, architectural audits, and providing constructive feedback on implementatio...

Review the code for quality, bugs and maintainability and emit an APPROVED / CHANGES-REQUESTED gate verdict. Invoke afte...

代码审查员,守护质量闸口。对所有部门(Backend/Frontend/SCF/Deploy)的 PR 进行安全、性能、正确性、可维护性、可观测性的系统性审查。遵循证据先行、问题分级、签发修复卡、独立克制的工程基线。适用于收到任一部门提交...

코드 리뷰 스킬. 버그, 보안, 성능, 가독성 체크. PR 리뷰, 자기 검토 시 사용.

Senior engineer conducting thorough, constructive code reviews. Round-2+ reviews use adversarial framing to find missed...

Critiques your paper draft as a skeptical reviewer would. Use when asked to review a paper draft, find weaknesses in a p...

Code review and audit agent for pull requests and code quality

Address reviewer/editor comments by number with localized, traceable edits. Use when the user provides numbered reviewer...

Code reviewer shared rules — context, SonarQube, commit style.

Shared reviewer baselines — prompt defense, epistemic honesty and verification, mandatory post-review learning gate. Loa...

Test-only explicit agent-task boundary fixture.

Run matched A/B reviewer calibration for /f through the binary-owned review controller, using digest-bound prompts, enve...

各レビュアーエージェント（backend, frontend, database, security, infra, req, basic-design, detailed-design）の共通設定、動作モード、出力形式、スコアリング基準を...

Use when the user wants to anticipate reviewer questions, select the strongest ablations to present, prepare rebuttals,...

Peer reviewer for scientific contribution and honesty. Checks scope vs claims, failure disclosure, overclaiming. Use dur...

Peer reviewer for methodological rigor. Checks arithmetic consistency, mock data use, reproducibility, and honest report...

Reviewer mindset — production-survival bias and critical questions.

Working playbook preloaded into the reviewer helper; the coach updates its Lessons after each round. Use only when actin...

When a chapter draft is completed/revised or before manuscript build, verify with check_reviewer_readability.py that the...

Draft structured point-by-point responses to peer reviewers and editors, including polite rebuttals, revision summaries,...

Selects exactly one reviewer for a feature branch or pull request, with one backup, using changed files, git history, an...

Given an open issue or PR, scores the project's configured reviewer roster across three signals — touched-area eligibili...

Peer reviewer for statistical correctness. Verifies numbers against source files, checks appropriate tests, effect sizes...

Get second opinions from external models (Codex, Gemini) for adversarial review, tie-breaking, and multi-model consensus...

Human review protocol for whether AI output is grounded in its sources: claim-by-claim attribution, hallucination classe...

Analyze AI/ML technical content (papers, articles, blog posts) and extract actionable insights filtered through enterpri...

Validate quality with multi-agent review, auto-fix issues, generate organized commits, and create PRs with rich context....

Eng manager-mode plan review. Lock in the execution plan, data flow, diagrams, edge cases.

Use when reviewing authentication or authorization code. Provides comprehensive security guidance on JWT validation, tok...

Review Go code using Casbin authorization for security issues, model correctness, policy design, and common anti-pattern...

Review an actual candidate against the user's acceptance and scope, then carry findings through fixes, affected checks a...

Reviews Claude configuration files for security, structure, and prompt engineering quality. Use when reviewing changes t...

Perform a thorough code review focused on correctness, maintainability, performance, and best practices.

Before main skill execution, perform guardrail checks.

Review sprint implementation for completeness, quality, security, and architecture alignment. Either approve (write "All...

Use when reviewing code changes, checking PRs, or evaluating code quality.

Review code for quality, maintainability, and correctness. Use when reviewing pull requests, evaluating code changes, or...

Conducts systematic code review with quality checks, architectural verification, and actionable feedback. Use when revie...

Compatibility alias for legacy reviewing-code routes. Delegate to the canonical local `code-reviewer` payload while pres...

ベースブランチに対する変更差分をもとにコードレビューを実施します。ベースブランチを指示として含めることができます。含めない場合は main をベースブランチとしてレビューを行います。

Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs,...

Analyzes code for bugs, security vulnerabilities, performance issues, and style violations. Use when the user asks for a...

Provides concise, focused code reviews matching exact task complexity requirements. Use when reviewing code quality, sec...

Performs systematic code review checking for correctness, maintainability, security, and best practices. Activates when...

Use this skill when reviewing pull requests, branch changes, or code diffs. Triggers on "review this PR", "review my cha...

Automated tooling and detection patterns for JavaScript/TypeScript code quality review

Analyze code complexity and maintainability including cyclomatic complexity, function length, nesting depth, and cogniti...

Review component architecture for React 19 best practices including size, composition, Server/Client boundaries, and ant...

Reviews C++ desktop code for memory safety, framework anti-patterns, build system issues, and thread safety. Use when re...

Review data engineering pull requests with a data-specific checklist — idempotency, correct grain, incremental logic, co...

Automated tooling and detection patterns for analyzing npm dependencies, unused packages, and dead code. Provides tool c...

Use when reviewing design documents, technical specifications, architecture docs, RFCs, ADRs, or API designs for complet...

Reviews and generates .NET/C# code following Microsoft conventions and modern patterns.Use when reviewing C# files, writ...

Automated tooling and detection patterns for identifying duplicate and copy-pasted code in JavaScript/TypeScript project...

Review a change to the ffmpeg-skill repository for the failures its own contract makes possible — a claim in a result do...

Used by the Reviewer agent during Phase 9 (DesignVerify) and Phase 11 (Quality) to evaluate frontend code. Assesses visu...

Provides concise, focused Go code reviews matching exact task complexity requirements. Use when reviewing Go code qualit...

Review React hook usage for React 19 compliance and best practices

Use when reviewing implementation plans before execution, especially plans derived from design documents

Tracks implementation progress against specs or plans with completion percentages. Use when monitoring multi-step implem...

Handles re-reviews after new commits. Use when a PR already has review comments or when responding to developer changes.

Use 30/60/90 days after launch - reviews actual vs predicted outcomes, analyzes failures, extracts lessons, and improves...

Use when reviewing code or PRs in the llama-stack repository (llamastack/llama-stack on GitHub). Provides specialized kn...

Review code for Next.js 16 compliance - security patterns, caching, breaking changes. Use when reviewing Next.js code, p...

Audit notes for quality issues. Use when asked to "review notes", "check content quality", "audit my knowledge base", or...

Review Zod schemas for correctness, performance, and v4 best practices

Review React 19 performance patterns including memoization, re-renders, and bundle size. Use when reviewing performance...

Use when reviewing an AI-generated implementation plan before execution, when handed a plan to approve, or when checking...

Review Claude Code plugin marketplace configurations against official best practices. Use when analyzing marketplace.jso...

Use when reviewing pull requests with comprehensive code analysis, incremental or full review options, and constructive...

Structures comparison with prior imaging studies to identify interval changes and trends. Use when comparing imaging stu...

Review Prisma code for common violations, security issues, and performance anti-patterns found in AI coding agent stress...

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises.

Use when user wants to assess progress toward an open-ended goal by reading and summarizing all iteration journals

Use when the user wants to read, analyze, or respond to GitHub pull request reviews and comments

Pull request workflow and review expertise. Auto-invokes when PRs, code review, merge, or pull request operations are me...