Home / yan-labs / yan-skills · agent-fleet/SKILL.md · GitHub

agent-fleet skillA

agent-fleet is agent-read markdown (skill) from yan-labs/yan-skills: 通用多模型子任务执行工具。用户想把一个任务派给别的模型(Gemini、DeepSeek、Kimi/Moonshot,或任何 Anthropic 兼容端点)去跑,尤其是想同时并行跑好几个不同模型的任务("同时起一个 Gemini 写文案的任务和一个 DeepSeek 做调研的任务""这个用 Kimi 跑""帮我用 DeepSeek 头脑风暴一下""开几个后台任务分别用不同模型跑")时使用。底层用 Claude Agent SDK 驱动一个 bypassPermissions 的自主 Agent(能读写文件、跑 bash、多轮工具调用直到任务完成),纯本地执行,不经过任何 Kollab 基础设施,模型接的是用户自己配置的第三方 API key。.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# agent-fleet

把一个任务派给别的模型去跑,而不是自己动手。核心命令:

```bash
cd agent-fleet

# 单个任务
node bin/agent-fleet.mjs run --model <友好名字> --prompt "<任务描述>" [--cwd <目录>] [--json]

# 一次并发跑一批不同模型的任务
node bin/agent-fleet.mjs run-many --config batch.json [--json]

# 看有哪些模型可用、密钥配没配
node bin/agent-fleet.mjs list-models
```

`<友好名字>` 来自 [`models.config.json`](./models.config.json),当前预置:`deepseek-v4-pro`、
`deepseek-v4-flash`、`kimi`、`gemini`(Gemini 没有官方 Anthropic 兼容端点,需要用户自己填一个网关
地址才能用,不填直接报错,不会假装能跑),以及 `kollab-gateway` 系列(走 Kollab 自己的公开 LLM
网关,用账号自助生成的 `kollab_live_*` key,不用等第三方审批,即用即验证过):
`kollab-gateway`(默认 `gemini-3.8-flash`)、`kollab-gateway-copy`(文案/创意,同样是
`gemini-3.8-flash`)、`kollab-gateway-research`(调研摘要,`grok-4.6`)、`kollab-gateway-bulk`
(批量机械任务,`gemini-3.5-flash-lite`)。

**用户想同时跑多个不同模型的任务时**,优先用 `run-many` 一次性提交(内部真正并发跑完),而不是
自己手写多次串行调用,或者对每个模型分别开一个后台 shell 进程——除非用户明确要求那种交互方式。

**按任务类型选模型**:批量文案/创意 → `kollab-gateway-copy`(或有 DeepSeek key 时用
`deepseek-v4-flash`);批量翻译/格式转换 → `kollab-gateway-bulk`(或 `deepseek-v4-flash`);
简单调研摘要 → `kollab-gateway-research`(或有 Moonshot key 时用自带联网搜索的 `kimi`);
高质量单次产出(长文案定稿、复杂推理)→ `deepseek-v4-pro`;**多轮工具调用容错要求高的任务不要
…

Read the whole file at its exact version.

How to install

Latest version
mdr add yan-labs/yan-skills/agent-fleet@git:20260922.7a67fde
Exact content
mdr add yan-labs/yan-skills/agent-fleet@sha256:ae94ff9959e28406

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_iyp6doflncei6si2.svg)](https://markdownregistry.com/a/art_iyp6doflncei6si2)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260922.7a67fde latest2026-09-22 7a67fde 4,097 BA view · diff
git:20260921.5866ebb2026-09-21 5866ebb 2,800 BA view · diff
git:20260921.9a8ca922026-09-21 9a8ca92 2,117 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4097 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

yan-labs/yan-skills · 203 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_iyp6doflncei6si2
GET https://markdownregistry.com/api/v1/resolve?ref=yan-labs/yan-skills/agent-fleet
GET https://markdownregistry.com/api/v1/blob/ae94ff9959e284066e09b0b3a416f8539bddd14e04a7ce9ad9e4c1ce4c53bf2e

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from yan-labs/yan-skills

agent-fleet skill
yan-labs/yan-skills · agent-fleet/skill/SKILL.md · 把机械化、大批量、对模型能力要求不高的子任务派给第三方模型(DeepSeek、Kimi/Moonshot,以及用户自备网关接入的 Gemini 或任何 Anthropic 兼容端点)去跑,省下 Claude 自己的 token…
git:20260923.16c2bb7 · audit A · 203 stars
autopilot skill
yan-labs/yan-skills · autopilot/SKILL.md · 接收一句模糊指令,自动调查、分类、拆解为 XML 阶段计划、选 skill、定完成判定, 然后以无人值守模式通过 loop/goal + agent-mode 完整执行到底—— 包括自动部署、自动 E2E 测试、自动代码…
git:20260912.2c2f140 · audit A · 203 stars
backlink skill
yan-labs/yan-skills · backlink/SKILL.md · OpenCLI-first backlink discovery, profile analysis, opportunity qualification, safe browser-assisted form filling…
git:20260913.4f244b1 · audit B · 203 stars
codex skill
yan-labs/yan-skills · codex/SKILL.md · **Generate images** with Codex's built-in OpenAI image-generation tool — route every "生成图片 / 配图 / 插图 / image gen / 画一张…
git:20260822.e230bea · audit A · 203 stars
game-opportunity skill
yan-labs/yan-skills · game-opportunity/SKILL.md · Rankup 的小游戏机会专项 Skill。用于监测游戏平台 sitemap、发现 24 小时游戏新词、建立多语言关键词需求簇、核对 KD/SERP/近 7 天趋势/独立需求/可玩供给并生成每日决策报告;通用规则和脚本随 Rankup…
git:20260921.28c4148 · audit A · 203 stars
imagegen skill
yan-labs/yan-skills · imagegen/SKILL.md · 生成网站与内容所需的一切视觉素材——用户说 生成图片、配图、插图、画一张、出一套图、logo、吉祥物、封面、海报、og 图、分享图、favicon…
v1.0.0 · audit A · 203 stars
opencli skill
yan-labs/yan-skills · opencli/SKILL.md · 用 OpenCLI 驱动用户本机那个真实的、已登录的 Chrome,或调用它的 160+ 站点 adapter。任何需要登录态的页面操作都从这里开始——读登录后的后台、抓没有 API…
v1.5.0 · audit A · 203 stars
rankup skill
yan-labs/yan-skills · rankup/SKILL.md · 网站从零到一与长期增长的总控 Skill。用于新建网站、SaaS、工具站或内容站,规划或初始化 TanStack Start Monorepo,使用 Cloudflare Workers、D1、R2 部署全栈应用,接入支付,执行…
v3.16.1 · audit A · 203 stars
skill-link-check skill
yan-labs/yan-skills · skill-link-check/SKILL.md · Audit project and global .agents/skills and .claude/skills layouts. Verify that .agents/skills contains the real source…
git:20260801.45daefe · audit A · 203 stars
skillsmp skill
yan-labs/yan-skills · skillsmp/SKILL.md · 在 SkillsMP(1.6M+ 公开 SKILL.md 的索引,覆盖 Claude Code / Codex / ChatGPT)里搜 Agent Skill,按关键词、分类、职业、语言过滤,并专门挖那些「写得好但没人知道」的冷门…
git:20260830.f8ac2dd · audit A · 203 stars

Every file in yan-labs/yan-skills

Other files named agent-fleet

agent-fleet skill
yan-labs/yan-skills · agent-fleet/skill/SKILL.md · 把机械化、大批量、对模型能力要求不高的子任务派给第三方模型(DeepSeek、Kimi/Moonshot,以及用户自备网关接入的 Gemini 或任何 Anthropic 兼容端点)去跑,省下 Claude 自己的 token…
git:20260923.16c2bb7 · audit A · 203 stars
agent-fleet skill
infinite-system/ivue · .claude/skills/agent-fleet/SKILL.md · Run a fleet of research/writer agents (codex sol/terra/luna at 1M context, claude opus) invar-conductor style from this…
git:20260905.751edee · audit A · 12 stars

Browse by kind, by grade A, or by owner.