debugger
Diagnoses ComfyUI workflow failures by analyzing logs, history, and node definitions
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
689 agents across 675 plugins.
Diagnoses ComfyUI workflow failures by analyzing logs, history, and node definitions
Analyzes ComfyUI workflows for performance issues and suggests optimizations
Expert code reviewer covering QA, architecture compliance, performance, security, and plan compliance. Use after code changes (ad-hoc or plan) to verify…
Expert plan reviewer covering structure, ordering, completeness, QA adequacy, architecture compliance, performance safety, and security across the entire plan.…
Specialized agent for bunqueue tasks — setting up queues, workers, flows, cron jobs, debugging job processing issues, configuring DLQ/retry/rate-limiting, and…
Critical code quality inspector that challenges assumptions. MUST BE INVOKED before every git commit and git push. Demands proof via actual tests, identifies…
Analyzes listed user-provided art/audio asset candidates and writes assets/manifest.json. Read-only on game code.
Produces one assigned visual asset production unit for the asset stage. Generates sources, runs asset tools, writes scoped outputs, and reports validated Asset…
Decomposes a confirmed GDD + ROADMAP into the current tag's artifact set — PLAN.md, STRUCTURE.md, SCENES.md, DESIGN.md, TOC.md, plus appends new rows to the…
Use this agent when the user needs strategic architecture analysis, design tradeoffs, or read-only debugging — high-stakes decisions where vague advice is…
Use this agent when dealing with HR and People Operations activities. This includes recruiting pipeline management, performance reviews, onboarding plans, org…
Use this agent when the user needs help managing projects — creating new projects, reviewing project status, updating project documentation, breaking down…
Meta-reviewer and loop-breaker. Governs both phases (pre-PR and on-PR review), enforces the gates and cycle limits, and decides continue/approve/escalate so…
Implements the planned change on a feature branch and addresses PR review comments. Handles single-repo and coordinated multi-service changes; keeps changes…
Turns a feature request into a concrete spec and execution plan. Identifies which repo(s)/microservices are affected (one or many), the cross-service contract…
Agent for running E2E tests on web applications. Navigates pages, fills forms, clicks buttons, and verifies results.
Agent for browsing and extracting structured content from web pages. Navigates pages, handles pagination, and returns structured data.
Read-only spec-integrity auditor that runs after every issue has merged. Walks the approved PRD requirement by requirement, maps each to the evidence it can…
Read-only senior code reviewer that reviews one completed Foreman issue's diff against its plan/requirements and the repo's conventions — from a fresh context…
Read-only grader that reviews a completed Foreman issue against its acceptance criteria, the referenced PRD sections, and the saved evidence — from a fresh…
Uses Zapier MCP to discover, enable, audit, and execute app actions safely and efficiently while following Zapier's read/write confirmation lifecycle.
Monitors ABM program performance, intent signals, and funnel conversion to prioritize next actions.
Designs multi-threaded account-based programs with aligned offers, plays,
Synthesizes usage, support, and sentiment signals into actionable account health insights.
You are a senior hardware design reviewer with deep experience in embedded systems, power electronics, RF, and production engineering.
辩论模式正方Agent,负责提出并捍卫方案或观点,在结构化辩论的Round 1陈述方案、Round 3回应质疑,擅长逻辑论证、证据支撑和方案迭代
辩论模式反方Agent,负责在结构化辩论的Round 2中系统性挑战方案,寻找风险、缺陷和替代方案,像红队一样思考,但始终提供建设性改进建议
AI/ML工程师,负责模型集成、提示工程、RAG管道、Agent工作流设计和AI功能开发,交付高质量的智能化功能模块
Analyzes web content and browser behavior using Chrome DevTools Protocol. Use when you need to inspect cached browser content, analyze DOM structure, or…
Sibyl Research System heavy-reasoning agent. Used for deep analysis tasks: synthesis, supervision, editing, critical review, and reflection.
Sibyl Research System lightweight agent. Used for quick evaluation tasks: debate roles (optimist, skeptic, strategist), section critique, and cross-critique.
Sibyl Research System standard agent. Used for literature research, planning, experiment design, and idea generation.
Autonomous UniFi network management agent. Use when the user needs to manage UniFi infrastructure: devices, networks, WiFi, firewall, clients, topology, DHCP…
You are the Brand Designer. You create visual and motion assets that bring the brand to life. Every asset you produce is consistent with the brand guidelines -…
Session supervisor agent that monitors Claude Code sessions via claudectl, identifies health issues, and recommends actions. Use when the user wants a…
公司 CFO(Patrick Campbell 思维模型)。当需要定价策略设计、财务模型搭建、单位经济分析、成本控制、收入指标追踪、变现路径规划时使用。
公司逆向思考顾问(Charlie Munger 思维模型)。当需要质疑新想法的可行性、识别计划中的致命缺陷、防止集体幻觉、进行反向论证、做 pre-mortem 分析时使用。任何重大决策前必须咨询。
Verbatim plan-to-beads converter using the `bd` CLI. Copies full implementation code, requirements, and exit criteria directly into each bead. Each bead is…
Architectural Bug Investigation Agent. Deep investigation with line-by-line code analysis, produces fix plans with exact code changes, regression prevention,…
Architectural Code Quality Agent (LSP-Powered) - Creates comprehensive architectural improvement plans suitable for loop or swarm executors (/implement-loop,…
Internal per-job worker for JobPilot apply/score loops. The auto-apply, apply, resume, search, and upwork-search skills delegate ONE job to it; it does the…
Internal per-contact worker for the JobPilot networking skill. Given one target (a job/company or free-text criteria) plus channel config, it discovers a…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic