jnMetaCode/agency-agents-zh

🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。

What it solves

It provides a comprehensive library of pre-defined AI expert roles to replace generic prompts. Instead of simply telling an AI "you are an expert," this project defines specific identities, thinking processes, operational rules, and required deliverables for 277 different professional roles across 20 departments, enabling more precise and professional AI outputs.

How it works

The project consists of a vast collection of Markdown files, each serving as a detailed persona definition for a specific AI agent. These definitions can be integrated into various AI programming tools (like Claude Code, Cursor, or Copilot) via installation scripts or manually copied. For advanced users, it integrates with the Agency Orchestrator to allow multiple AI experts to automatically form teams and collaborate on complex tasks.

Who it’s for

  • AI Power Users: Individuals looking to maximize the utility of LLMs for professional tasks.
  • Developers: Those using AI coding assistants who want specialized roles (e.g., Security Engineer, Backend Architect) to audit or build their code.
  • Entrepreneurs/Solopreneurs: People running "one-person companies" who need a virtual executive team (CEO, CTO, CMO, etc.) to strategize and execute.
  • Digital Marketers: Professionals needing specialized strategies for platforms like Xiaohongshu, Douyin, and WeChat.

Highlights

  • Massive Role Library: 277 plug-and-play expert roles covering 20 departments.
  • Localized Expertise: Includes 64 original agents specifically designed for the Chinese market (e.g., platforms like Bilibili, Feishu, and DingTalk).
  • Broad Tool Support: Compatible with over 20 AI programming tools including Claude Code, Cursor, Copilot, and OpenClaw.
  • Structured Personas: Each agent defines not just a role, but a specific professional workflow and set of deliverables.

Related

  • Project
    jnMetaCode/agency-orchestrator

    Agency Orchestrator is an npm‑based tool (CLI + web UI) that automatically composes and runs multi‑agent AI workflows from a single sentence or a tiny YAML file. It ships 276 pre‑built Chinese (and 191 English) role definitions, supports 15 LLM providers (many key‑less), builds a DAG for parallel execution, validates outputs, and produces shareable HTML reports. Ideal for solo entrepreneurs, product analysts, and developers who want an "AI team" without writing code.

  • Project
    addyosmani/agent-skills

    Agent Skills is a library of 25 Markdown‑based engineering workflows (spec, plan, build, test, review, ship, etc.) that can be installed into many AI coding agents via a simple CLI. It provides slash commands, auto‑build mode, specialist personas, and reference checklists to make AI‑generated code follow senior‑engineer best practices across the entire development lifecycle.

  • Project
    momozi1996/awesome-ai-persona-skills

    A public collection of over 100 ready‑to‑import AI “persona skills” (prompt templates) for agents, covering writers, celebrities, historic texts, social‑media influencers, and multi‑agent teams. Compatible with OpenClaw/StepClaw and the nuwa‑skill format, it lets developers instantly give LLMs a distinct voice or run collaborative agent crews.

  • Project
    bcurts/agentchattr

    agentchattr is a cross‑platform local chat server that lets you and multiple AI coding agents converse in real‑time. By @‑mentioning an agent in the web UI, the server injects a prompt into the agent’s terminal (via MCP), the agent reads the chat and replies automatically, enabling hands‑free coordination, multi‑agent workflows, jobs, rules, sessions, and a rich UI with channels, pins, decision cards, scheduling, voice typing, and more.

  • Project
    bojieli/ai-agent-book

    AI‑Agent‑Book is a multilingual open‑source textbook on building LLM‑based AI agents, paired with 109 runnable Python experiments covering everything from prompt engineering to multi‑agent collaboration.