checker
AgentRun one parent-scoped focused validation command. Do not edit source or broaden into a full suite.
11,388 agents. Claude Code subagents shipped in plugins found in public marketplaces and GitHub repositories. Each works in Claude Code and Cursor.
Run one parent-scoped focused validation command. Do not edit source or broaden into a full suite.
Answer one parent-stated question using read-only repository evidence. Do not edit, format, build, test, or run commands whose…
Reviews code for quality, security, and project conventions. Use after completing features or before commits.
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
PromptScript language expert. Helps with syntax, compilation issues, and migrations.
Multi-phase code quality review producing severity-ranked findings with file:line references and fix recommendations.
- Repository: https://github.com/mattpocock/skills - Pinned commit: `49dd158d1076134a641b33efb035946536778336`. - Adapted source:…
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Compare two outputs WITHOUT knowing which skill produced them.
Evaluate expectations against an execution transcript and outputs.
PaperFit code surgeon agent for academic LaTeX layout tasks.
PaperFit layout detective agent for academic LaTeX layout tasks.
PaperFit orchestrator agent for academic LaTeX layout tasks.
构建和 TypeScript 错误解决专家。当构建失败或出现类型错误时主动使用。仅以最小差异修复构建/类型错误,不做架构编辑。专注于快速让构建通过。
专业代码审查专家。主动审查代码的质量、安全性和可维护性。在编写或修改代码后立即使用。所有代码更改必须使用。
1-2ファイル surgical 編集。typo修正、単関数書換、機械的rename、コメント削除、フォーマット保持微調整。 3ファイル以上は強制拒否。原始人diff receipt 返却。スコープ明確時に使用、新機能/新ファイル/cross-file…
読取専用コードロケーター。「Xはどこで定義?」「Yを呼んでるのは?」「Zの全用法」「ディレクトリ構造」に file:line 表で返却。出力は原始人圧縮 → 主スレッドの消費トークンが vanilla Explore 比で約60%減。 修正提案は拒否。
Diff/branch/file レビュアー。1指摘1行、severity タグ付、賞賛なし、スコープ越境なし。 出力形式: `path:line: <emoji> <severity>: <問題>. <修正>.`。 「PR レビューして」「diff…
showtime crew. Dispatched by the showtime skill, not for general requests. Use when a video job needs a brand kit extracted from…
showtime crew. Dispatched by the showtime skill, not for general requests. Use when a video job needs a brand kit extracted from…
showtime crew. Dispatched by the showtime skill, not for general requests. Use in studio or publish-bound video jobs with an open…
Use this agent to write educational content for the Teaching Claude Code project. Triggers when the user asks to create, draft,…
Backend implementation specialist. Use when the task involves APIs, server-side logic, database operations, authentication, data…
Frontend implementation specialist. Use when the task involves UI components, pages, layouts, styling, animations, client-side…
Produces ONE phase's design artifact — DESIGN.md tokens, a JOURNEY.md page spec, or a rendered mock — honoring the…
Independent, execution-grounded cross-pillar critique of a rendered design surface against its done-when requirements.…
**Weight:** 25% of composite Trade Score **Output:** fundamental_score (0-100), key_metrics, valuation_assessment,…
**Weight:** 15% of composite Trade Score **Output:** risk_score (0-100), max_drawdown_estimate, position_size_recommendation,…
**Weight:** 20% of composite Trade Score **Output:** sentiment_score (0-100), news_summary, analyst_target,…
后端开发工人。只在后端目录里开发,接口实现一律以 CONTRACT.md 指向的机器契约为准(只读,不许改),并为接口写"返回必须符合契约"的校验测试(provider verification)。可在单会话里被 contract-director…
契约拥有者 / 集成对账者。唯一拥有并维护 CONTRACT.md(端与端的数据接口契约),先定契约,最后做集成对账。支持单会话多…
Use this agent for read-only documentation audits. General requests such as 审计现有文档 or 检查文档治理漂移 use docs-audit; explicit…
Specializes in architecting AI-powered applications on Vercel — choosing between AI SDK patterns, configuring providers, building…
Specializes in Vercel deployment strategies, CI/CD pipelines, preview URLs, production promotions, rollbacks, environment…
Specializes in optimizing Vercel application performance — Core Web Vitals, rendering strategies, caching, image optimization,…
Audits DashClaw's drift-prone hardcoded counts and version stamps — SDK method counts (Node/Python), MCP tool/resource counts,…
Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the failures plus a…
Read-only security reviewer specialized for the DashClaw stack (Next.js 16 App Router, Neon/Postgres via repositories, API-key…
Part of the Aptos Verification Protocol skill. Read `SKILL.md` for the core workflow first.
L1 mode - deep analysis of consensus safety/liveness invariants, non-determinism sources, Byzantine-scenario reasoning, and…
Zero-state return, dust analysis, boundary conditions with real constants
You are a focused codebase exploration agent with access to a tree-sitter-indexed codebase. Your job is to answer a specific…
Active Directory discovery subagent for red-run. Performs AD enumeration, BloodHound collection, LDAP queries, and attack surface…
Active Directory exploitation subagent for red-run. Executes one AD technique skill per invocation as directed by the…
Credential cracking subagent for red-run. Performs offline hash cracking and encrypted file cracking using hashcat and john as…
Generic Analyzer agent. Dispatched with a role prompt specifying which skill to follow, what to read, what to produce, and where…
Generic sanitizer worker agent. Reads raw specs and rewrites them as clean behavioral specs. Loads sanitization and provenance…
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
AI safety and security auditor for LLM systems. Red teaming, prompt injection, jailbreak testing, guardrail validation, and OWASP…
Backend architect: REST/GraphQL APIs, database schemas, microservice boundaries, distributed systems, clean architecture.
Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas…
Spatial positioning specialist for Obsidian Canvas. Computes optimal node positions using layout algorithms (dagre, grid, radial,…
Media asset dispatcher for canvas generation. Generates images via /banana (Gemini), SVG diagrams via /svg, and GIFs via gif…
Specialized agent for comprehensive code security reviews
Senior backend TypeScript architect specializing in Bun/Node.js runtime, API design, database optimization, and scalable server…
Expert at exploring and understanding legacy and unfamiliar codebases. Maps dependencies, identifies patterns, and creates…
Kubernetes architect specializing in cluster design, manifests, Helm charts, GitOps workflows, security policies, and production…
Match the right skills, tools, and capability packages for a Meta_Kim agent or workflow.
Orchestrate evolution writeback for Meta_Kim — aggregate signals, coordinate writeback through Warden's gate, and prevent…
Design workflow orchestration, business-flow blueprints, stage sequencing, and rhythm control for Meta_Kim systems.
Senior backend TypeScript architect specializing in Bun/Node.js runtime, API design, database optimization, and scalable server…
Expert at exploring and understanding legacy and unfamiliar codebases. Maps dependencies, identifies patterns, and creates…
Kubernetes architect specializing in cluster design, manifests, Helm charts, GitOps workflows, security policies, and production…
Sibyl Research System heavy-reasoning agent. Used for deep analysis tasks: synthesis, supervision, editing, critical review, and…
Sibyl Research System lightweight agent. Used for quick evaluation tasks: debate roles (optimist, skeptic, strategist), section…
Sibyl Research System standard agent. Used for literature research, planning, experiment design, and idea generation.
Dispatched when a round is in audit_in_progress state. Produces a verdict file at the project's audits_dir following the…
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round.…
Use when execute-round's Phase 3 inline CR step reviews a dev-body diff for code quality, correctness, test coverage, and mandate…
You are an audience research and targeting specialist. You research the target business and build detailed audience personas with…
You are a media buying and budget allocation specialist. You design the optimal budget distribution across platforms, funnel…
You are a competitive advertising intelligence specialist. You analyze competitor advertising strategies, identify messaging…
You are an AWS Well-Architected Framework specialist. Follow these principles strictly.
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause…
PYA specialist spawned by the /pya orchestrator. Audits AI agent and LLM surfaces in an untrusted repository: Claude Code,…
PYA specialist spawned by the /pya orchestrator. Finds security smells typical of AI-generated code in an untrusted repository:…
PYA specialist spawned by the /pya orchestrator. Verifies authentication and authorization on every data access path of an…
Master offer-building orchestrator inspired by Alex Hormozi's frameworks. Captures raw ideas, notes, or existing offers from the…
Internal subagent. Called by hormozi-orchestrator only. Executes market research, micro-niche scoring, pain extraction, and…
Internal subagent. Called by hormozi-orchestrator only. Builds a Grand Slam Offer and generates positioning angles. Applies…
Activate the Super Dev pipeline for research-first, commercial-grade project delivery. Use when user says /super-dev or…
Manage and diagnose UniFi Network infrastructure with unifly. Use for network provisioning, firewall audits, switch port…
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Compare two outputs WITHOUT knowing which skill produced them.
Evaluate expectations against an execution transcript and outputs.
Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise…
Runs a task as a bounded loop backed by SuperLocalMemory: iterate until an INDEPENDENT gate passes — never the agent's own claim.…
Advises the main agent on using SuperLocalMemory well — when to call session_init, remember, recall, and search; how to phrase…
../../.agents/agents/code-architecture-reviewer.md
Adversarial code reviewer focusing on quality, maintainability, and best practices. Use PROACTIVELY after code changes, before…
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.