Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
“当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用”
Install Dispatching Parallel Agents
$ npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jnMetaCode/superpowers-zh dispatching-parallel-agents --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dispatching-parallel-agents .claude/skills/dispatching-parallel-agents && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "dispatching-parallel-agents" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/dispatching-parallel-agents into .claude/skills/dispatching-parallel-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dispatching-parallel-agents", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/dispatching-parallel-agentsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jnMetaCode/superpowers-zh dispatching-parallel-agents --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/dispatching-parallel-agents .agents/skills/dispatching-parallel-agents && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dispatching-parallel-agents" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/dispatching-parallel-agents into .agents/skills/dispatching-parallel-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dispatching-parallel-agents", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jnMetaCode/superpowers-zh dispatching-parallel-agents --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/dispatching-parallel-agents .cursor/skills/dispatching-parallel-agents && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "dispatching-parallel-agents" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/dispatching-parallel-agents into .cursor/skills/dispatching-parallel-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dispatching-parallel-agents", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jnMetaCode/superpowers-zh.git --path skills/dispatching-parallel-agents--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jnMetaCode/superpowers-zh dispatching-parallel-agents --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/dispatching-parallel-agents .gemini/skills/dispatching-parallel-agents && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "dispatching-parallel-agents" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/dispatching-parallel-agents into .gemini/skills/dispatching-parallel-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dispatching-parallel-agents", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jnMetaCode/superpowers-zh dispatching-parallel-agentsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/dispatching-parallel-agents .github/skills/dispatching-parallel-agents && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "dispatching-parallel-agents" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/dispatching-parallel-agents into .github/skills/dispatching-parallel-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dispatching-parallel-agents", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jnMetaCode/superpowers-zh dispatching-parallel-agents --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/dispatching-parallel-agents .opencode/skills/dispatching-parallel-agents && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "dispatching-parallel-agents" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/dispatching-parallel-agents into .opencode/skills/dispatching-parallel-agents/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dispatching-parallel-agents", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
dispatching-parallel-agents- GitHub stars
- 8.3k
- Token cost
- ~778 tokens
- SKILL.md length
- 138 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
- Works in 4 steps: 识别独立的问题域 → 创建聚焦的智能体任务 → 并行分派 → …
- SKILL.md covers 概述, 何时使用, 模式 and 智能体提示词结构, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
Dispatching Parallel Agents is a skill in jnMetaCode/superpowers-zh (8.3k stars). Its SKILL.md is about 778 tokens. Licence: MIT.
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit fe34019. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are dot, typescript and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Dispatching Parallel Agents loads about 778 tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 138 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jnMetaCode/superpowers-zh at commit fe34019, republished under its MIT licence (© jnMetaCode). 138 words, ~778 tokens.
Download SKILL.mdSave it as
.claude/skills/dispatching-parallel-agents/SKILL.md (or your agent's skills folder).- name
- dispatching-parallel-agents
- description
- 当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用
- version
- 1.0.0
- license
- MIT
并行分派智能体
概述
你将任务委派给具有隔离上下文的专用智能体。通过精心设计它们的指令和上下文，确保它们专注并成功完成任务。它们不应继承你的会话上下文或历史记录——你要精确构造它们所需的一切。这样也能为你自己保留用于协调工作的上下文。
当你遇到多个不相关的失败（不同的测试文件、不同的子系统、不同的 bug），逐一排查会浪费时间。每个排查都是独立的，可以并行进行。
核心原则： 每个独立问题域分派一个智能体，让它们并发工作。
何时使用
digraph when_to_use {
"存在多个失败?" [shape=diamond];
"它们是否独立?" [shape=diamond];
"单个智能体排查所有问题" [shape=box];
"每个问题域一个智能体" [shape=box];
"能否并行工作?" [shape=diamond];
"顺序执行智能体" [shape=box];
"并行分派" [shape=box];
"存在多个失败?" -> "它们是否独立?" [label="是"];
"它们是否独立?" -> "单个智能体排查所有问题" [label="否 - 有关联"];
"它们是否独立?" -> "能否并行工作?" [label="是"];
"能否并行工作?" -> "并行分派" [label="是"];
"能否并行工作?" -> "顺序执行智能体" [label="否 - 有共享状态"];
}适用场景：
- 3 个以上测试文件因不同根因失败
- 多个子系统独立出现故障
- 每个问题无需其他问题的上下文即可理解
- 排查之间无共享状态
不适用场景：
- 失败是相关的（修复一个可能修复其他的）
- 需要理解完整的系统状态
- 智能体之间会互相干扰
模式
1. 识别独立的问题域
按故障分组：
- 文件 A 测试：工具审批流程
- 文件 B 测试：批量完成行为
- 文件 C 测试：中止功能
每个问题域是独立的——修复工具审批不会影响中止测试。
2. 创建聚焦的智能体任务
每个智能体获得：
- 明确范围： 一个测试文件或子系统
- 清晰目标： 让这些测试通过
- 约束条件： 不修改其他代码
- 预期输出： 你发现和修复内容的总结
3. 并行分派
// 在 Claude Code / AI 环境中
Task("修复 agent-tool-abort.test.ts 的失败")
Task("修复 batch-completion-behavior.test.ts 的失败")
Task("修复 tool-approval-race-conditions.test.ts 的失败")
// 三个任务并发运行4. 审查与集成
当智能体返回时：
- 阅读每个总结
- 验证修复之间没有冲突
- 运行完整测试套件
- 集成所有更改
智能体提示词结构
好的智能体提示词应该是：
- 聚焦的 - 一个清晰的问题域
- 自包含的 - 包含理解问题所需的所有上下文
- 明确输出要求 - 智能体应该返回什么？
修复 src/agents/agent-tool-abort.test.ts 中 3 个失败的测试：
1. "should abort tool with partial output capture" - 期望消息中包含 'interrupted at'
2. "should handle mixed completed and aborted tools" - 快速工具被中止而非完成
3. "should properly track pendingToolCount" - 期望 3 个结果但得到 0 个
这些是时序/竞态条件问题。你的任务：
1. 阅读测试文件，理解每个测试验证的内容
2. 找到根因——是时序问题还是实际 bug？
3. 修复方式：
- 用基于事件的等待替换任意超时
- 如果发现中止实现中的 bug 则修复
- 如果测试的是已变更的行为则调整测试期望
不要只是增加超时时间——找到真正的问题。
返回：你发现了什么以及修复了什么的总结。常见错误
错误做法：太宽泛： "修复所有测试" - 智能体会迷失方向 正确做法：具体明确： "修复 agent-tool-abort.test.ts" - 聚焦的范围
错误做法：无上下文： "修复竞态条件" - 智能体不知道在哪里 正确做法：提供上下文： 粘贴错误信息和测试名称
错误做法：无约束： 智能体可能会重构所有代码 正确做法：设置约束： "不要修改生产代码" 或 "只修复测试"
错误做法：模糊的输出要求： "修好它" - 你不知道改了什么 正确做法：明确要求： "返回根因和修改内容的总结"
不适用的场景
关联性失败： 修复一个可能修复其他的——先一起排查 需要完整上下文： 理解问题需要看到整个系统 探索性调试： 你还不知道什么坏了 共享状态： 智能体会互相干扰（编辑同一文件、使用同一资源）
实际案例
场景： 大规模重构后，3 个文件中出现 6 个测试失败
失败情况：
- agent-tool-abort.test.ts：3 个失败（时序问题）
- batch-completion-behavior.test.ts：2 个失败（工具未执行）
- tool-approval-race-conditions.test.ts：1 个失败（执行计数 = 0）
决策： 独立的问题域——中止逻辑、批量完成、竞态条件各自独立
分派：
智能体 1 → 修复 agent-tool-abort.test.ts
智能体 2 → 修复 batch-completion-behavior.test.ts
智能体 3 → 修复 tool-approval-race-conditions.test.ts结果：
- 智能体 1：用基于事件的等待替换了超时
- 智能体 2：修复了事件结构 bug（threadId 位置不对）
- 智能体 3：添加了等待异步工具执行完成的逻辑
集成： 所有修复互相独立，无冲突，完整测试套件全部通过
验证
智能体返回后：
- 审查每个总结 - 理解改了什么
- 检查冲突 - 智能体是否编辑了同一段代码？
- 运行完整套件 - 验证所有修复协同工作
- 抽查 - 智能体可能犯系统性错误
© jnMetaCode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/dispatching-parallel-agents of jnMetaCode/superpowers-zh.
Open the folder on GitHubat commit fe34019
Compare with similar skills
Dispatching Parallel Agents next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Dispatching Parallel Agents this skilljnMetaCode/superpowers-zh | 8.3k | — | ~778 | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 40 repos | ~1.5k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence | |
| Task Observerrebelytics/one-skill-to-rule-them-all | 3.2k | 1 repos | ~12k | Automated safety check: Pass | CC-BY-4.0 |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
O2 Review Loop
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
More from jnMetaCode/superpowers-zh
All 21 skills in this repoBrainstorming Before Building
jnMetaCode/superpowers-zh
Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.
Git Worktree Isolation
jnMetaCode/superpowers-zh
Sets up an isolated workspace before feature work or plan execution, preferring native worktree tools and falling back to git worktree, with instructions in Chinese.
Inline Plan Execution
jnMetaCode/superpowers-zh
Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end.
Agency Orchestrator Workflow Runner
jnMetaCode/superpowers-zh
Runs agency-orchestrator YAML workflows inside the current agent session, with the session's own model playing each role in turn and no API key needed.
Chinese Code Review Etiquette
jnMetaCode/superpowers-zh
Gives Chinese-language templates and priority labels for code review feedback, plus guidance on bilingual comments, commit messages and common team anti-patterns.
Chinese Commit Conventions
jnMetaCode/superpowers-zh
Reference for Chinese-language git commits and changelogs: Conventional Commits adapted for Chinese teams, with templates, breaking-change notes and issue links for several platforms.
Related
Categories
Questions about Dispatching Parallel Agents
How do I install Dispatching Parallel Agents in Claude Code?
Run `npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a claude-code`. Or copy the skill folder (skills/dispatching-parallel-agents in jnMetaCode/superpowers-zh) into .claude/skills/dispatching-parallel-agents in your project. Claude Code loads it when a task matches its description.
How do I install Dispatching Parallel Agents in Codex?
Run `npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a codex`. Or copy the skill folder (skills/dispatching-parallel-agents in jnMetaCode/superpowers-zh) into .agents/skills/dispatching-parallel-agents in your project. Codex loads it when a task matches its description.
Can I use Dispatching Parallel Agents in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jnMetaCode/superpowers-zh --skill dispatching-parallel-agents -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dispatching-parallel-agents, .gemini/skills/dispatching-parallel-agents, .github/skills/dispatching-parallel-agents and .opencode/skills/dispatching-parallel-agents in your project.
What does Dispatching Parallel Agents need to run?
SKILL.md names no scripts, command-line tools or credentials: Dispatching Parallel Agents is instructions for the agent only.
Does Dispatching Parallel Agents access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Dispatching Parallel Agents safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Dispatching Parallel Agents use?
Dispatching Parallel Agents is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Dispatching Parallel Agents use?
About 778 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Dispatching Parallel Agents?
Skills that share tags, products or a category with Dispatching Parallel Agents: Claude Code Agent Development (anthropics/claude-plugins-official, 37k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dispatching Parallel Agents?
jnMetaCode (a GitHub user) maintains it in jnMetaCode/superpowers-zh, which has 8,265 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 4, 2026.
Source: jnMetaCode/superpowers-zh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.