11,388 agents. Claude Code subagents shipped in plugins found in public marketplaces and GitHub repositories. Each works in Claude Code and Cursor.
Read one arXiv paper in depth, write its wiki note, and emit a deep-lit result JSON.
Check whether the system environment satisfies prerequisites for running the research system.
Audit the latest experiment round's key conclusions, execution consistency, and scientific validity.
Use this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes…
Background agent for cross-iteration memory consolidation. Runs after each iteration to extract learnings and update…
Use this agent when scores converge suspiciously fast, evaluator quality is questionable, or the agent reaches high scores in few…
Du erstellst den **Entwurf** auf Basis der Quellen, die der Researcher geliefert hat. Du argumentierst, subsumierst, ziehst…
Du bist die **Recherche-Stufe** in der Researcher → Drafter → Reviewer-Pipeline. Deine einzige Aufgabe ist, **Quellen zu finden…
Du bist die **Qualitäts- und Risikostufe** vor Auslieferung an den Mandantenanwalt oder die zuständige Behörde / das…
Implements a single fable-bench packet from a brief. Sonnet 5, builds with the six fable skills loaded. Use for bench/…
Reviews code diffs against section plans. Used by /deep-implement for section review.
System designer. Use for technical design, API contracts, data modeling, and trade-off analysis before implementation.
AI content factory agent. Research, write, audit, SEO-optimize, and publish articles at scale. For marketers and content creators.
Implementation specialist. Use for writing production code, refactoring, and TDD-driven feature work.
Use this agent when an MSP technician or security lead needs a complete, read-only access review of one client's 1Password…
Use this agent when an MSP technician or BCDR lead needs a cross-customer Acronis Cyber Protect Cloud backup health review -…
Use this agent for Auvik alert-related questions - what's open, what matters, what to dismiss, what to escalate. Trigger for:…
GameForge Accessibility Specialist (Kael Oduya) with project memory, for an independent review or deliverable on motor, visual,…
GameForge Art Director (Sable Mori) with project memory, for an independent review or deliverable on visual style, art bible,…
GameForge Audio Director (Kael Resonance) with project memory, for an independent review or deliverable on music, SFX, adaptive…
Use this agent for read-only PRD-quality review. Checks acceptance-criteria specificity, scope drift detection, and completeness…
Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency…
Use this agent for feature implementation, API development, refactoring, and general code changes. Handles backend logic, API…
Runs Agentic SEO Autoresearch experiment loops for skills, fixtures, regressions, and keep/reject decisions.
Analyzes backlinks and referring domains using configured providers, with freshness and confidence notes.
Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatible links.
Compresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.
Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient…
Preprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.
Technical designer. Use proactively when a change touches data models, schemas, API contracts or layer boundaries; produces the…
Implementer. MUST BE USED for every code change once the design or plan is settled, including new files, features, business…
Critical analyst. Use proactively to clarify requirements, user stories and acceptance criteria, challenge assumptions, weigh…
Audits a generated or existing WordPress block theme for FSE correctness, theme.json validity, accessibility, i18n, and the…
System architecture specialist for design decisions, ADR creation, and scalability assessment. Use PROACTIVELY when designing new…
Analyzes build/compile errors and provides minimal targeted fixes. Use PROACTIVELY when build fails, type errors occur, or…
Performs deep code review checking architecture compliance, code quality, and security issues. Use PROACTIVELY after writing or…
Detects and analyzes system threats, malware, and security vulnerabilities on Windows systems. Use for system scanning, browser…
Autonomous financial analyst powered by EODHD market data. Performs multi-source equity research — fundamentals, valuation,…
Use this agent for anything Stitch-related: ideating designs through conversation, generating UI screens from text,…
Challenges a legal position by finding weaknesses, counter-precedents, and opposing arguments under Swiss law
Builds the strongest possible case in favor of a legal position using Swiss law precedents, statutory provisions, and doctrine
Pure planner for the briefing flow: classifies the query, selects the specialist panel, and (given Q&A history) builds the…
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause…
@AX 어노테이션 전문가. Phase 2.5에서 자동 실행. NOTE/WARN/ANCHOR/TODO 태그를 코드에 추가. [AUTO] 접두사 필수.
시스템 아키텍처 설계 전문가. DB 스키마, API 명세, 컴포넌트 구조 설계. Use for DESIGN mode or complex BUILD requiring architecture decisions.
체계적 디버깅 전문가. 5-WHY 근본 원인 분석 + 4단계 디버그 프로세스. Use for DEBUG mode or complex FIX requiring root cause investigation.
The owner's dedicated Fable 5 agent, grounded in the market-ready Fable 5 Brain at <path-to-your-fable-5-brain-vault> (Brainstein…
Verifies that this repo's agent-facing surface - skill-doc instructions, slash-command frontmatter, and plugin manifests -…
Ensures documentation completeness and manifest correctness for changes that affect user-facing or structural aspects of the…
Hunts for swallowed errors, silent failures, and broken error propagation chains in changed code.
AI feature implementation specialist. Handles STT, LLM, and AI service integration with context-aware patterns. Auto-discovers…
Architecture decision specialist for /implement command. Analyzes PRD to determine optimal architecture (MSA vs Monolithic) based…
Backend enhancement helper. Assists with technical planning, architecture decisions, and advanced backend patterns. Use when…
Renders multi-slide carousels from HTML/CSS templates using Playwright. Handles slide content injection, brand styling, and PDF…
Enforces brand compliance rules — banned phrases, required disclaimers, image rules, data claim verification, and…
Adapts social media copy per platform — character limits, hashtags, CTAs, tone shifts, and bilingual formatting. Handles…
Designs API contracts using OpenAPI in the contract component. Generates types consumed by server and webapp.
Implements backend services using Node.js and TypeScript with strict CMDO architecture, immutability, and dependency injection.
Reviews database schema and queries for performance. Read-only advisory role invoked during review phase or explicitly for…
Compound V builder for one run. Starts from a clean context with the run id, the approved spec and the user's request; does the…
Compound V executable reviewer, used when Codex is not the configured reviewer. It works in an isolated checkout of the exact…
Read-only lookup over this project's own Compound V record (docs/compound-v/ specs, plans, pre-flights, runs, architecture). Use…
Analyzes extracted session messages across 8 behavioral dimensions to produce a scored developer profile with confidence levels…
Explores codebase and writes structured analysis documents. Spawned by map-environment with a focus area (tech, arch, quality,…
Verifies cross-phase integration and E2E flows. Checks that phases connect properly and user workflows complete end-to-end.
Strategic risk reviewer — delivers a verdict, ranked risks, and ordered
Sole mutator role — applies and verifies code, test, doc, and infra changes.
Read-only adversarial evaluator — reviews, audits, or evaluates existing plans.
Persistent agent that maintains the Business Model Canvas and financial model as living documents reflecting current validated…
Persistent agent that monitors all open change requests weekly. Ensures changes proceed through correct approval, blocks…
Activate for: chief of staff, orchestration agent, digital chief of staff, daily digest delivery, morning brief, executive…
Evaluate whether a dependency should be kept or decomposed. Use during dependency decomposition (phase 3) to assess each library…
Implement or replace a dependency in the yoink package directory based on a decomposition evaluation. Use during dependency…
Search reference test suite for tests relevant to a target function. Use during test curation (phase 2) to discover existing…
Use when: astro.config.* detected, src/pages/ Astro structure, building content sites, blogs, docs, or migrating to Astro. Do NOT…
Use when: new features, component creation, major changes, adding functionality — triggers BEFORE Analyze phase. Do NOT use for:…
Use when: /map command, finding skills/agents, understanding ecosystem layout. Do NOT use for: code generation, debugging, file…
Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.
Drafts one passage of a writer's book (a scene, section, beat or short chapter) in the writer's own voice, in a fresh context.…
Files openwriter documents the user marked for sorting via the sidebar. Dispatch when SORT_STATUS appears in MCP init…
Analyzes a Symfony project (6.4 LTS, 7.x, 8.x) for hexagonal architecture compliance, detects installed Symfony/PHP/Doctrine…
Reviews Symfony code changes (6.4 LTS, 7.x, 8.x) against hexagonal architecture rules: dependency rule, ports/adapters, CQRS,…
This agent should be used when the user needs to design how a specific feature should be implemented within an existing codebase,…
This agent should be used when the arn-code-batch-planning skill needs to pre-generate draft feature specifications for multiple…
This agent should be used when the arn-code-batch-merge skill needs to analyze multiple open batch PRs for cross-cutting issues…
Hand off a well-specified coding task to the Cursor CLI (`cursor-agent`) via `/cursor:delegate`. Use for small-to-medium,…
Video analysis specialist agent for deep inspection and quality assessment. Performs comprehensive FFprobe analysis,…
Encoding specialist agent for complex multi-step video transcoding pipelines. Handles batch processing, multi-pass encoding,…
Production pipeline specialist agent for complex multi-step video creation workflows. Orchestrates the full shortform pipeline…
Fresh-context PROJECT.md alignment classifier - classifies a proposed change and cites the governing clause (verdict-only agent)
Automation quality tester — evaluates whether autonomous-dev's hooks, pipeline, and enforcement are working correctly. Use…
Semantic documentation drift detector and CHANGELOG automation
Use this agent for an independent second-pass audit of NEWLY GENERATED Metin2 UI code (uiscript dicts, root ui*.py classes,…
Adversarial verifier. Use PROACTIVELY before claiming a nontrivial change is done, fixed, or passing — give it the claim plus the…
Specialist agent for Helius + Solana integrations — queries live blockchain data, sends transactions via Sender, sets up…
Scores a codebase against the /assess 0-8 layered contract model, reading the deterministic run-context.json and assigning…
Critical analysis through mechanistic causal reasoning and proportionality testing. Challenges both over-complex and over-simple…
Synthesizes perspectives from other thinking hats into coherent conclusions and actionable recommendations.
Primary session agent for this project. Triages each request and routes it to the right skills; coordinates non-trivial work end…
Deep research from web, academic and industry sources to build the knowledge base for content.
Verifies claims, statistics and citations for accuracy before drafting.
Drafts content from the research and brief, setting structure and narrative flow.
Forwards a coding/diagnosis/research/recording/scraping/conversion/design-review/code-review/one-shot-ask request to the Google…
Strictly non-mutating commitment-boundary advisor. Reads repository state through read-only tools and returns a verdict with…
Independent read-only reviewer for ONE frozen Candidate Artifact. Input is a checkoutPath, runId, protocolVersion, and the review…
Second-opinion advisor running Claude's most capable model (Fable 5.1). Consult at commitment boundaries — before architectural…
© 2026 Flowy
Built for Claude Code · Not affiliated with Anthropic
Logos are trademarks of their owners.