agents
Skill0 starsChanged 6 months agoMITView on GitHub
Lists all luban-distilled expert agents currently installed in this project. Renders a structured roster grouped by domain family, showing slash command, display name, sub-specialty, stage, and vibes_risk for each. Activates when the user asks "which agents do I have", "list my experts", "show available agents", "what luban agents are loaded", "/agents", or similar discovery queries. Does not activate for general "list skills" queries (that's Claude Code's built-in `/` palette), only for luban-distilled expert personas.
43 other projects use a version of this.
Adopted by
Most recently taken up by
- boadij/pi-herdsmantheir own version, first seen Nov 13, 2026
- akillness/jeo-skillstheir own version, first seen Nov 13, 2026
- calesthio/OpenMontagetheir own version, first seen Nov 9, 2026
- agentprocess/agentprocesstheir own version, first seen Nov 8, 2026
- OpenMontageInc/OpenMontagetheir own version, first seen Nov 8, 2026
- claude-world/director-mode-litetheir own version, first seen Nov 1, 2026
Used with
Projects with it also use realtime, speech-engine and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
hkarpinenSkillrealtime
Real-time communication patterns for web applications — WebSockets, Server-Sent Events (SSE), transport selection, scaling persistent connections, and reverse proxy configuration. Use when implementing live updates (vote counts, new replies, typing indicators, notifications), choosing a transport, designing real-time event flows, or wiring real-time into a multi-context system. Stack agnostic — applies to any backend and frontend. Does NOT cover message broker configuration or domain event design.
Also in 5 projects that use this
RobStrayerSkillspeech-engine
Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints, interruption-aware streaming responses, or voice-enabled chat agents that connect developer-owned server logic to ElevenLabs speech-to-text and text-to-speech.
Also in 3 projects that use this
RobStrayerSkillvoice-isolator
Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API. Use when cleaning up noisy recordings, removing music or background ambience from dialogue, isolating speech from field recordings, preparing audio for transcription, extracting vocals, or any "denoise / clean up / isolate voice" task.
Also in 3 projects that use this
wlzhSkillvoice-changer
音频变声处理工具 - 使用 RVC AI 模型进行真实的声音转换,支持视频直接输入
Also in 3 projects that use this
perso-aiSkilldubbing
Auto-dub (voice-translate) videos into other languages, with lip-sync (Perso AI Dubbing).
Also in 3 projects that use this
awesome-genmediaSkilltext-to-speech
Convert text to natural-sounding speech using each::sense AI. Generate realistic voice audio from any text in 32 languages with control over voice, speed, emotion, and style. Powered by elevenlabs-tts for studio-quality output. Use for: narration, audiobooks, accessibility, announcements, IVR systems, e-learning, localization. Triggers: text to speech, tts, read aloud, convert to speech, speak text, voice output, ai speech, synthesize speech, read text, audio from text, narrate text
Also in 4 projects that use this
Other versions43 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 43
- calesthio/OpenMontage★ 81ksame name
- OpenMontageInc/OpenMontage★ 81ksame name
- mex-memory/mex★ 1.8ksame name
- theDakshJaitly/mex★ 1.8ksame name
- elevenlabs/skills★ 568same name
- butterbase-ai/butterbase-plugin★ 535same name
- butterbase-ai/butterbase-skills★ 535same name
- tadaspetra/loop★ 297same name
- aws-samples/sample-well-architected-skills-and-steering★ 268same name
- boadij/pi-herdsman★ 233same name
33 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- ai-pmSkill
- content-ops-directorSkill
- game-art-directorSkill
- luban-skillSkill
- ux-research-directorSkill
The file
Files
/agents — Luban Agent Roster
浏览本项目所有 luban-distilled expert agents 的入口。读
.claude/skills/INDEX.md,按 family 渲染。
何时使用本 skill
- 当用户问 "我装了哪些 agent / 专家"、"列一下 luban 蒸馏的角色"、"/agents"
- 当用户问 "有没有 X 领域的 agent" —— 渲染清单后辅助匹配
- 当用户首次进入项目想了解可用专家全集
何时不使用
- 用户问 "Claude Code 装了哪些 skill" —— 那是
/浮动面板的事,不是本 skill 范围 - 用户问 luban-skill 本身怎么用 —— 跳到 luban-skill
- 用户已经在跟某个具体 agent 对话 —— 不要打断,由用户主动召唤本 skill 才介入
Workflow
- 读取 INDEX.md —— 位于
.claude/skills/INDEX.md(项目根相对路径)- 不存在 → 友好告知 "尚未蒸馏任何角色,运行
/luban-skill创建第一个"
- 不存在 → 友好告知 "尚未蒸馏任何角色,运行
- 解析表格 —— 提取 slug / display name / family / sub-specialty / stage / vibes_risk
- 按 family 分组渲染 —— 只渲染已有角色的 family。空 family 不显示、不预设、不暗示"建议补充"
- 跨族角色(如
product + engineering)按主属族分组,不重复出现 - family 排序按 INDEX.md "By family" 段的实际顺序
- 跨族角色(如
- 每条 entry 格式:
/<slug> · <Display name> · <sub-specialty 简化> · [<stage>, vibes_risk: <risk>] - 末尾给操作提示 —— 仅 3 条,不附"建议补充哪些 family":
- "调用某个 agent:直接输入
/<slug>或在对话中明确召唤" - "查看某 agent 的详细身份:读
.claude/skills/<slug>/SOUL.md§1-§5" - "蒸馏新 agent:
/luban-skill 生成 <领域>"
- "调用某个 agent:直接输入
⚠️ 不要做的事:
- 不要列空 family 槽("Family 1 (Legal): (空 — 待生成)")—— 5 family 是分类逻辑参考,不是用户清单
- 不要在末尾添加"覆盖空白 / 蒸馏建议 / 推荐补充"—— 这是 preset push,违反 lazy organization 原则
- 不要按某种"完整度"评价当前 roster——angent 数量取决于用户实际需要,不是越多越好
输出示例(仅 1 个角色时)
你当前装载的 luban 蒸馏角色(共 1 个):
┌─ Family 4 (Product / Growth / Design) ──────────────────────────┐
│ /ai-pm Mira the PM AI PM (agent infra) [0→1, medium] │
└─────────────────────────────────────────────────────────────────┘
调用:直接 `/<slug>` 或对话中召唤 display name
详情:读 .claude/skills/<slug>/SOUL.md §1-§5
新增:/luban-skill 生成 <领域>随用户后续生成更多角色,新 family 会自动新增(INDEX.md 按 luban-skill 协议自动维护)。本 skill 只反映 INDEX.md 当前状态。
与 luban-skill 的边界
- luban-skill 是元工具,生成 角色
- agents 是 meta-skill,列举 已生成的角色
- 两者协同:用户用 luban-skill 蒸馏角色 → INDEX.md 自动更新 → agents 浮动面板显示新角色
Honest limits
- 本 skill 只列 luban-distilled 角色 —— 不显示其他类型的 Claude Code skill(那是
/面板的事) - INDEX.md 若被手动破坏 / 格式不规范,本 skill 渲染会降级为"裸 dump 文件内容",不做容错修复
- 不替你选用哪个 agent —— 选哪个让用户自己看 description / SOUL.md 决定
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

