Agent skill

Spec Swarm

by HHU3637kr in HHU3637kr/skills

当用户要求以「Agent 主控 + 全程 spawn 子 Agent」的方式启动 R&K Flow 开发流程时使用: 当前 Agent 只做编排(账本、门禁代问、批次调度),七个角色的实质工作一律交子 Agent 执行。

No licenceAuto-check passedAgent Workflows

Install Spec Swarm

skills CLI
$ npx skills add HHU3637kr/skills --skill spec-swarm -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HHU3637kr/skills spec-swarm --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HHU3637kr/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/spec-swarm .claude/skills/spec-swarm && rm -rf skills-src

Use ~/.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/

Facts

Skill name
spec-swarm
GitHub stars
145
Token cost
~1.2k tokens
SKILL.md length
321 words
Files
2 (incl. references)
Skills in repo
37
Repo updated
First seen
Licence
None found

At a glance

当用户要求以「Agent 主控 + 全程 spawn 子 Agent」的方式启动 R&K Flow 开发流程时使用: 当前 Agent 只做编排(账本、门禁代问、批次调度),七个角色的实质工作一律交子 Agent 执行。

  • Works in 5 steps: 主控不干活:当前 Agent 是编排者。角色产物(explorer/… → execution 与 mode 正交:execution 决定谁执行,mode… → 账本与 AWR 控制面仍归… → …
  • Tasks that involve Multi-agent orchestration
  • SKILL.md covers 运行契约, 核心原则, execution 与 mode 正交 and 步骤 1:前置校验(三项,逐条实测), plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Spec Swarm is an agent skill from HHU3637kr/skills. 当用户要求以「Agent 主控 + 全程 spawn 子 Agent」的方式启动 R&K Flow 开发流程时使用: 当前 Agent 只做编排(账本、门禁代问、批次调度),七个角色的实质工作一律交子 Agent 执行。 典型信号:用户说"用 swarm 模式启动"/"蜂群模式"/"所有任务都 spawn 子 Agent 做"/"你只做主控不要自己写代码"。 本 Skill 只做前置校验、写入 execution 字段、声明编排硬约束,随后委派 spec-start 跑既有五阶段流程。 不要用于运行时不支持子 Agent 的环境(退回 spec-start 串行路径)、已有活跃 Spec 的小迭代(用 spec-update), 也不要用它替代 spec-start —— 流程本体、账本模板、门禁定义仍由 spec-start 唯一承载。

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/spawn-orchestration.md`).

It sits in Agent Workflows, covering Multi-agent orchestration.

When your agent uses it

  • Tasks that involve Multi-agent orchestration

Example prompts

  • “用 swarm 模式启动”
  • “所有任务都 spawn 子 Agent 做”
  • “你只做主控不要自己写代码”
  • “/spec-swarm”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 主控不干活:当前 Agent 是编排者。角色产物(explorer/ writer/ tester/ executor/ debugger/ reviewer/ ender/ 下的一切)一律由对应子 Agent 产出。主控自己写就是本模式的失败。
  2. execution 与 mode 正交:execution 决定谁执行,mode 决定谁验证。四种组合全部合法,见下。
  3. 账本与 AWR 控制面仍归 TeamLead:lead/team-context.md(或 .html)、rk-manifest.js 与 AWR 的任务认领/检查点提交职责仍由主控独占维护。子 Agent 并发执行时禁止直接修改 AWR Work 状态,避免并发覆盖与状态漂移。
  4. 门禁必须代问:子 Agent 没有 ask 工具(实测),无法触达用户。任何需要用户表态的节点都由主控代问。
  5. 流程不复制:五阶段、四门禁、账本模板、修复循环预算的唯一真相源是 spec-start。本 Skill 不重述,只补充编排约束。

What it can do on your machine

Read from SKILL.md and the folder at commit a2cccf6. 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 bash and yaml).

    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

Spec Swarm loads about 1.2k tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 96 tokens; SKILL.md has 321 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 321 words (~1,181 tokens).

name
spec-swarm
disable-model-invocation
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (references) in spec-swarm of HHU3637kr/skills.

  • SKILL.md
  • references/spawn-orchestration.md

Open the folder on GitHubat commit a2cccf6

Compare with similar skills

Spec Swarm 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.

Spec Swarm compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Spec Swarm this skillHHU3637kr/skills145—~1.2kAutomated safety check: PassNone
Orca CLIstablyai/orca89k2 repos~593Automated safety check: PassMIT
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
O2 Review Loopopenobserve/openobserve22k—~3.7kAutomated safety check: PassAGPL-3.0
Paseo Committeegetpaseo/paseo20k1 repos~496Automated safety check: PassCustom licence
Mission Control Agent APIbuilderz-labs/mission-control6.3k—~2.1kAutomated safety check: PassMIT

Similar skills

  • Orca CLI

    stablyai/orca

    Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser…

    89k GitHub starsUsed in 2 repos~593 tokens
    Agent WorkflowsAuto-check passed
  • 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.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed
  • 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.

    22k GitHub stars~3.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Paseo Committee

    getpaseo/paseo

    Forms a two-agent committee with contrasting profiles to analyze a stuck problem in parallel, reconcile their views and return a consensus plan without editing files.

    20k GitHub starsUsed in 1 repo~496 tokens
    Agent WorkflowsAuto-check passed
  • Mission Control Agent API

    builderz-labs/mission-control

    Teaches an agent to use the Mission Control dashboard API: register, send heartbeats, fetch assigned tasks, report progress and disconnect, with API key auth.

    6.3k GitHub stars~2.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Paseo Agent Handoff

    getpaseo/paseo

    Hands off the current task, including context, decisions and failed attempts, to a fresh agent through Paseo by writing a self-contained briefing prompt and launching that agent.

    20k GitHub starsUsed in 1 repo~606 tokens
    Agent WorkflowsAuto-check passed

More from HHU3637kr/skills

All 37 skills in this repo
  • Gif Sticker Maker

    HHU3637kr/skills

    Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions.

    145 GitHub starsUsed in 3 repos~1.3k tokens
    Auto-check passed
  • Agent Browser

    HHU3637kr/skills

    Headless browser automation for AI agents using agent-browser CLI.

    145 GitHub stars~1.9k tokensUpdated 18 days ago
    Auto-check passed
  • Darwin Skill

    HHU3637kr/skills

    Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch.

    145 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed
  • Token Efficiency

    HHU3637kr/skills

    Cross-platform token audit and optimization for AI coding agents (Cursor, Codex, Claude Code, Hermes, Windsurf, Cline, OpenClaw, Gemini CLI, Aider).

    145 GitHub stars~842 tokensUpdated 18 days ago
    Auto-check passed
  • Guizang Ppt Skill

    HHU3637kr/skills

    生成横向翻页网页 PPT(单 HTML 文件),含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格:① "电子杂志 × 电子墨水"(衬线 + 流体背景 + 暖色) ② "瑞士国际主义"(无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮)。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT,或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss…

    145 GitHub starsUsed in 1 repo~4.7k tokens
    Auto-check passed
  • Huashu Nuwa

    HHU3637kr/skills

    女娲造人:输入人名/主题/甚至只是模糊需求,自动深度调研→思维框架提炼→生成可运行的人物Skill. An agent skill from HHU3637kr/skills.

    145 GitHub starsUsed in 1 repo~4k tokens
    Auto-check passed

Categories

Questions about Spec Swarm

What does Spec Swarm do?

当用户要求以「Agent 主控 + 全程 spawn 子 Agent」的方式启动 R&K Flow 开发流程时使用: 当前 Agent 只做编排(账本、门禁代问、批次调度),七个角色的实质工作一律交子 Agent 执行。. Spec Swarm is an agent skill from HHU3637kr/skills.

When should I use Spec Swarm?

Spec Swarm fits situations like: tasks that involve Multi-agent orchestration.

How do I install Spec Swarm in Claude Code?

Run `npx skills add HHU3637kr/skills --skill spec-swarm -a claude-code`. Or copy the skill folder (spec-swarm in HHU3637kr/skills) into .claude/skills/spec-swarm in your project. Claude Code loads it when a task matches its description.

How do I install Spec Swarm in Codex?

Run `npx skills add HHU3637kr/skills --skill spec-swarm -a codex`. Or copy the skill folder (spec-swarm in HHU3637kr/skills) into .agents/skills/spec-swarm in your project. Codex loads it when a task matches its description.

Can I use Spec Swarm 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 HHU3637kr/skills --skill spec-swarm -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spec-swarm, .gemini/skills/spec-swarm, .github/skills/spec-swarm and .opencode/skills/spec-swarm in your project.

What does Spec Swarm need to run?

SKILL.md names no scripts, command-line tools or credentials: Spec Swarm is instructions for the agent only.

Does Spec Swarm 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 Spec Swarm 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 Spec Swarm use?

No licence was found for Spec Swarm or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Spec Swarm use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Spec Swarm?

Skills that share tags, products or a category with Spec Swarm: Orca CLI (stablyai/orca, 89k stars), Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars), O2 Review Loop (openobserve/openobserve, 22k stars) and Paseo Committee (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 Spec Swarm?

HHU3637kr (a GitHub user) maintains it in HHU3637kr/skills, which has 145 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on September 23, 2026.

Source: HHU3637kr/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.