Scoutari

AI builder 的決策情報台。

瀏覽

  • 今日情報
  • Skill 榜單
  • AI 週報
  • 關於與編輯方針
  • RSS

主題

  • 模型發布
  • API 與價格
  • MCP 與 Skills
  • AI Coding
  • 中國模型
  • 開源模型
  • Agent
  • Infra / 成本
  • 值得試用
© 2026 Scoutari · scoutari.com摘要由 AI 輔助生成,並始終附上原文連結。
情報收藏週報設定
SScoutariAI Builder Intel · decision desk
Skill RadarSavedPersonalizeSubmit sourceLog inSign up
Sign up
Skill RadarSavedPersonalizeSubmit sourceLog in
Back to timeline

Mon, July 606:15ToolsAI codingAgents

Agency-Agents-ZH: 266 Plug-and-Play AI Expert Roles with 18 Tools

View originalOpen Claude Code

Decision Brief

What changedGitHub repo agency-agents-zh offers 266 plug-and-play AI expert roles supporting 18 tools across 20 departments, including 50 original agents tailored for the Chinese market.
Why it mattersDevelopers using Claude Code, Cursor, etc., can directly reuse role definitions and launch multi-expert collaboration with one command via agency-orchestrator, dramatically reducing the cost of building multi-agent systems.
Who should careAI coding tool users
Affected stackClaude CodeCursorCopilot
Builder actionUpdate Claude Code to the latest version
Source confidenceHigh · Official release / blog / repo

agency-agents-zh is a GitHub repository containing 266 plug-and-play AI expert roles that support 18 mainstream tools such as Hermes Agent, Claude Code, Cursor, and Copilot, covering 20 departments including engineering, design, marketing, and finance. The project notably includes 50 original agents designed for the Chinese market, applicable to platforms like Xiaohongshu, Douyin, WeChat, Feishu, and DingTalk. With the built-in orchestrator, agency-orchestrator, users can have multiple experts automatically collaborate on tasks based on a directed acyclic graph (DAG) with just one command. For workers who need to quickly integrate multi-role agents, such as developers, designers, or marketers, this project provides ready-to-use agent definitions without the need to write from scratch. The 50 China-market agents make localization smoother, while the DAG orchestration mechanism is ideal for handling complex workflows that require sequential or dependent tasks.

Summary basis: official / RSS sourceCompiled from the source scope noted above; the original remains authoritative.

Sources

  • Skill Radar(GitHub 趨勢)

    Trending hands-on MCP servers, agent skills, and AI-coding tools discovered from GitHub search momentum.

  • GitHub:jnMetaCode/agency-agents-zh

Related intel

  • planning-with-files: Persistent File-Based Planning for AI Coding Agents

    OthmanAdi/planning-with-files is a file-based persistent planning tool designed for AI coding agents and long-running agent tasks.

  • CodeGraph: Pre-indexed Code Knowledge Graph, Auto-Syncs Changes, Supports Multiple AI Agents

    CodeGraph is a pre-indexed code knowledge graph that auto-syncs on code changes and supports AI agents like Claude Code, Codex, and Gemini.

  • alirezarezvani/claude-skills releases 337 skills and plugins supporting 11 code agents

    GitHub trending project alirezarezvani/claude-skills offers 337 Claude Code skills, agent skills, and plugins covering engineering, marketing, and more, supporting 11 code agents including Claude Code, Codex, Gemini CLI, and Cursor.

  • Anthropic-Cybersecurity-Skills Releases 817 AI Agent Cybersecurity Skills

    GitHub trending project mukul975/Anthropic-Cybersecurity-Skills provides 817 structured cybersecurity skills mapped to six security frameworks, usable on 20+ AI platforms.