SCHEMA
Single source of truth for the shape of every agent in this pack. One schema, one pool — `agents/index.json` is generated from these files, and the…
An agent is a specialist Claude hands a whole job to, with its own tools and its own context.
6,163 agents across 675 plugins.
Single source of truth for the shape of every agent in this pack. One schema, one pool — `agents/index.json` is generated from these files, and the…
How to write an agent body that is useful, compact, and consistent with the rest of the pack. Follow this when adding a new agent or materially rewriting an…
Curated list of every tag an agent is allowed to declare. Source of truth: [`tags.json`](tags.json). Linter rejects any tag not in this list.
构建与 TypeScript 错误修复专家。当构建失败或出现类型错误时,请主动(PROACTIVELY)使用。仅修复构建/类型错误,保持最小差异(diff),不进行架构性修改。重点是快速使构建通过(get the build green)。
个人通讯幕僚 (Chief of Staff),负责分拣电子邮件、Slack、LINE 和 Messenger。将消息分类为 4 个级别 (skip/info_only/meeting_info/action_required),生成草稿回复,并通过钩子 (Hooks)…
Deep codebase exploration using grepai semantic search and call graph tracing. Use this agent for understanding code architecture, finding implementations by…
Research a company from its URL or description to infer Stripe Connect integration shape
Research a company from its URL or description to infer Stripe Connect integration shape
Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.
Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.
Deprecated placeholder. Do not use; follow root AGENTS.md and package instructions instead.
Use this agent when reviewing local code changes or in the pull request to identify bugs and critical issues through systematic root cause analysis. This agent…
Use this agent when refining task descriptions and defining verifiable acceptance criteria for implementation tasks.
Use this agent to rate each changed file based on 2 criteria and output final list of files that require most attention.
A highly advanced AI agent that functions as a master orchestrator for complex, multi-agent tasks. It analyzes project requirements, defines a team of…
A highly specialized AI agent for designing, building, and optimizing LLM-powered applications, RAG systems, and complex prompt pipelines. This agent…
A specialist agent that creates comprehensive, developer-first API documentation. It generates OpenAPI 3.0 specs, code examples, SDK usage guides, and full…
Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future…
GitHub issue resolution specialist. Analyzes, plans, and implements fixes for GitHub issues with proper testing and PR creation. Use when fixing specific…
Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when…
Research notes on Sourcegraph Amp's configuration, credential discovery, and runtime behavior.
Research notes on OpenAI Codex's configuration, credential discovery, and runtime behavior based on agent-jj implementation.
Research notes on OpenClaw's architecture, API, and automation patterns for integration with sandbox-agent.
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Software architecture specialist for system design, scalability, and technical decision-making
Build and TypeScript error resolution specialist. Fixes build/type errors with minimal diffs
Expert code review specialist. Reviews code for quality, security, and maintainability
The brooks-lint verification gate. Runs `npm run validate`, `npm test`, and `npm run evals`, then cross-checks the documents the validator can't fully diff —…
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including…
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via `npm run…
Reviews an evo benchmark in two modes. mode=audit -- pre-flight harness audit before the first run (per-task instrumentation, leakage, gates, plumbing);…
Generates ranked experiment proposals for the evo orchestrator. Runs ONE brief per invocation (`failure_analysis`, `literature`, or `frontier_extrapolation`)…
Read-only audit of one evo experiment for design-time cheating (pre-phase) or result-time validity (post-phase). Catches test-set leakage in training data,…
Selects required BitLesson entries for a specific sub-task. Use before execution for every task or sub-task.
Checks if a draft document is relevant to the current repository. Use when validating draft content for gen-plan command.
Checks plan relevance and compliance before RLCR loop. Use when validating plan files for start-rlcr-loop command.
Adversarial senior design critic. Renders the work, looks at it, and argues for rejection. Use when a build, screen, or component needs a taste and craft…
Agent Team 导师角色 — 观察其他 teammate 的执行状态,用智慧引导而非恐惧施压。当 teammate 陷入循环、放弃或被动时,以道德经智慧启发。建议 5+ teammate 的团队使用。
Agent Team Mentor Role — Observe teammate execution status, guide with wisdom rather than fear. When teammates get stuck in loops, give up, or become passive,…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic