Communitygithub.com

claude-devfleet

通过 Claude DevFleet 编排多智能体编码任务——规划项目、在隔离工作树中派发并行智能体、监控进度并读取结构化报告。适用于需要跨隔离工作树并行派发编码智能体并追踪其报告的场景。

claude-devfleet 是什么?

Claude DevFleet 是一个多智能体编排工具,让您能够并行派发多个 Claude Code 智能体执行编码任务。每个智能体在隔离的 git 工作树中运行,拥有完整的工具集。它通过 `plan_project` 工具将描述性提示自动分解为带有依赖链的“任务”有向无环图(DAG),智能体按依赖关系顺序执行,并自动合并更改。DevFleet 支持 HTTP (MCP) 集成,默认并发 3 个智能体(可通过 `DEVFLEET_MAX_AGENTS` 配置)。工作流包括:规划(AI 生成项目计划)、展示计划并获取用户批准、派发首个任务、智能体自动触发后续依赖任务、通过轮询或阻塞等待监控进度、最后通过 `get_report` 获取结构化报告来总结结果。该工具尤其适合并行实现功能、自动化测试和审查流程,且可以通过仪表盘跟踪资源使用情况。

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/ECC/tree/main/skills/claude-devfleet

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Claude DevFleet 多智能体编排

使用时机

当你需要派发多个 Claude Code 智能体并行处理编码任务时,使用本技能。每个智能体在隔离的 git 工作树中运行,并拥有完整的工具集。

设置

DevFleet 服务器是一个独立项目,未与 ECC 捆绑。请先从它的仓库安装并运行:https://github.com/LEC-AI/claude-devfleet

然后通过 MCP 连接正在运行的实例:

claude mcp add devfleet --transport http http://localhost:18801/mcp

首次使用前,请确认监听 18801 端口的进程是你安装的 DevFleet 二进制文件(参见 SECURITY.md 中关于 localhost MCP 服务器的内容)。

工作原理

用户 → "构建一个带认证和测试的 REST API"
  ↓
plan_project(prompt) → project_id + 任务 DAG
  ↓
向用户展示计划 → 获取批准
  ↓
dispatch_mission(M1) → 智能体 1 在工作树中启动
  ↓
M1 完成 → 自动合并 → 自动派发 M2 (depends_on M1)
  ↓
M2 完成 → 自动合并
  ↓
get_report(M2) → files_changed, what_done, errors, next_steps
  ↓
向用户报告

工具

工具用途
plan_project(prompt)AI 将描述分解为包含链式任务的项目
create_project(name, path?, description?)手动创建项目,返回 project_id
create_mission(project_id, title, prompt, depends_on?, auto_dispatch?)添加任务。depends_on 是任务 ID 字符串列表(例如 ["abc-123"])。设置 auto_dispatch=true 可在依赖满足时自动启动。
dispatch_mission(mission_id, model?, max_turns?)在任务上启动一个智能体
cancel_mission(mission_id)停止运行中的智能体
wait_for_mission(mission_id, timeout_seconds?)阻塞直到任务完成(参见下方说明)
get_mission_status(mission_id)检查任务进度(非阻塞)
get_report(mission_id)读取结构化报告(更改的文件、测试、错误、下一步)
get_dashboard()系统概览:运行中的智能体、统计信息、近期活动
list_projects()浏览所有项目
list_missions(project_id, status?)列出项目中的任务

关于 wait_for_mission 的说明: 该调用会阻塞对话长达 timeout_seconds(默认 600)。对于长时间运行的任务,建议改用 get_mission_status 每 30–60 秒轮询一次,以便用户能看到进度更新。

工作流:规划 → 派发 → 监控 → 报告

  1. 规划:调用 plan_project(prompt="...") → 返回 project_id 以及带有 depends_on 链和 auto_dispatch=true 的任务列表。
  2. 展示计划:向用户展示任务标题、类型和依赖链。
  3. 派发:对根任务(空 depends_on)调用 dispatch_mission(mission_id=<first_mission_id>)。其余任务会在其依赖完成时自动派发(因为 plan_project 为它们设置了 auto_dispatch=true)。
  4. 监控:调用 get_mission_status(mission_id=...) 或 get_dashboard() 检查进度。
  5. 报告:任务完成后调用 get_report(mission_id=...)。向用户分享关键信息。

并发

DevFleet 默认最多运行 3 个并发智能体(可通过 DEVFLEET_MAX_AGENTS 配置)。当所有槽位已满时,设置了 auto_dispatch=true 的任务会在任务监视器中排队,并在槽位释放时自动派发。使用 get_dashboard() 查看当前槽位使用情况。

示例

全自动:规划与启动

  1. plan_project(prompt="...") → 展示带有任务和依赖的计划。
  2. 派发第一个任务(具有空 depends_on 的任务)。
  3. 其余任务在依赖解决时自动派发(它们设置了 auto_dispatch=true)。
  4. 返回项目 ID 和任务数量,以便用户了解已启动的内容。
  5. 定期使用 get_mission_status 或 get_dashboard() 轮询,直到所有任务达到终止状态(completed、failed 或 cancelled)。
  6. 对每个终止状态的任务调用 get_report(mission_id=...) —— 总结成功之处,指出失败及其错误和下一步。

手动:逐步控制

  1. create_project(name="My Project") → 返回 project_id。
  2. 为第一个(根)任务执行 create_mission(project_id=project_id, title="...", prompt="...", auto_dispatch=true) → 捕获 root_mission_id。 为后续每个任务执行 create_mission(project_id=project_id, title="...", prompt="...", auto_dispatch=true, depends_on=["<root_mission_id>"])。
  3. 对第一个任务执行 dispatch_mission(mission_id=...) 以启动链。
  4. 完成后执行 get_report(mission_id=...)。

带审查的顺序执行

  1. create_project(name="...") → 获取 project_id。
  2. create_mission(project_id=project_id, title="实现功能", prompt="...") → 获取 impl_mission_id。
  3. dispatch_mission(mission_id=impl_mission_id),然后使用 get_mission_status 轮询直到完成。
  4. 执行 get_report(mission_id=impl_mission_id) 以审查结果。
  5. create_mission(project_id=project_id, title="审查", prompt="...", depends_on=[impl_mission_id], auto_dispatch=true) —— 由于依赖已满足,自动启动。

指南

  • 除非用户要求直接执行,否则务必在派发前向用户确认计划。
  • 报告状态时,应包含任务标题和 ID。
  • 如果某个任务失败,在重试前先读取其报告。
  • 在批量派发前,检查 get_dashboard() 以了解智能体槽位可用情况。
  • 任务依赖形成 DAG —— 不要创建循环依赖。
  • 每个智能体在隔离的 git 工作树中运行,并在完成时自动合并。如果发生合并冲突,更改会保留在智能体的工作树分支上,需要手动解决。
  • 手动创建任务时,如果希望它们在依赖完成时自动触发,务必设置 auto_dispatch=true。未设置此标志时,任务将保持在 draft 状态。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

affaan-m/ECC

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

affaan-m/fal-ai-media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

affaan-m/manim-video

日本語翻訳:このファイルは manim-video 用の日本語翻訳が必要です

affaan-m/remotion-video-creation

Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。

affaan-m/video-editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

agent-self-evaluation

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

agent-sort

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

ai-first-engineering

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when setting team process, review gates, or ownership rules for a codebase largely written by agents.

ai-regression-testing

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when adding regression coverage to AI-assisted code, or when the same model both wrote and reviewed a change.

android-clean-architecture

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when structuring modules, layers, or data flow in an Android or KMP project.

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

相关技能