Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill).
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
git clone https://github.com/titanwings/distilly && cp distilly/*.md ~/.claude/agents/1 items en este repositorio
Distill colleague, relationship, or celebrity source material into reusable Person Profiles for agents.
Resumen de Subagents
<div align="center"> <img src="docs/social-preview-distilly-v7.png" alt="Distilly — Distill how they think into Person Profiles for Agents" width="100%"> <br> # 🧬 Distilly **Formerly: Colleague Skill / colleague-skill.** ### Distill a person's experience, judgment, voice, and ways of working into a reusable Person Profile for AI agents and compatible bots. **Messages · documents · interviews · public sources → Distilly → Person Profile → Agent / Bot** [](LICENSE) [](https://python.org) [](https://agentskills.io) [](https://github.com/titanwings/distilly/stargazers) [](https://discord.gg/NVX66RxWZv) <br> <table> <tr><td align="left"> 🧑💼 Your colleague quit, your mentor graduated, your teammate transferred — taking their whole playbook and context with them?<br> 💞 Your family, old friends, partner drifting apart — and you want to hold on to the way it felt to be with them?<br> 🌟 Your favorite author, idol, thinker you'll never meet — but you want to know what they'd say about your question? </td></tr> </table> ### ✨ One project, many kinds of people. <br> Distilly is the person-modeling layer for agents. It turns the materials you provide into a portable, source-grounded Person Profile built from observable experience, decision patterns, expression, and ways of working; it does not claim to clone the person behind them. Colleagues · partners · family · old friends · idols · public figures · fictional characters — even yourself **Source material + your description → a source-grounded Person Profile → your Agent or compatible Bot** > A Person Profile is the reusable output. The current release packages each profile as an Agent Skill so supported hosts can install and invoke it. The canonical creator Skill is named `distilly`; install it in a `distilly` directory. The former name above remains for search continuity and project history. <br> [🆕 What Distilly does](#-what-distilly-does-today) · [📦 Data Sources](#-supported-data-sources) · [⚡ Install](#-install) · [🚀 Usage](#-usage) · [✨ Demo](#-demo) · [📝 Citation](#-citation) · [💬 Discord](https://discord.gg/NVX66RxWZv) [**Chinese**](docs/lang/README_ZH.md) · [**Spanish**](docs/lang/README_ES.md) · [**German**](docs/lang/README_DE.md) · [**Japanese**](docs/lang/README_JA.md) · [**Russian**](docs/lang/README_RU.md) · [**Portuguese**](docs/lang/README_PT.md) · [**Korean**](docs/lang/README_KO.md) </div> --- <div align="center"> ### 🎉 2026.08.13 Milestone — **the project has passed 20K ⭐!** Massive thanks to everyone who starred — we'll keep shipping, keep distilling. </div> > 🧬 **2026.08.24 Update** — The creator is now named **Distilly** end to end and documents native local Skill discovery for Claude Code, Hermes, OpenClaw, Codex, DeepSeek Harness, Pi, Grok Build, and OpenCode. Grok Bot is listed separately as a saved-Skill workflow preview. > 📝 **2026.06.01 Update** — **[The COLLEAGUE.SKILL technical report](https://arxiv.org/pdf/2605.31264) is now available**. The most rewarding part was not simply publishing a paper, but seeing the community grow the gallery to 215 skills contributed by 165 people, with more than 100,000 stars across the skill cards. The paper's Acknowledgements explicitly recognize every community contributor. > 🗺️ **2026.04.13** — **The Distilly Roadmap is live!** What began as Colleague Skill is growing beyond colleagues: distill people into Skills that Agents can reuse. 👉 **[Full Roadmap](ROADMAP.md)** · **[💬 Discord](https://discord.gg/NVX66RxWZv)** > 🌐 **2026.04.07** — Community gallery is live! Any skill / meta-skill can drive traffic directly to your own GitHub repo. No middleman. 👉 **[titanwings.github.io/colleague-skill-site](https://titanwings.github.io/colleague-skill-site/)** <div align="center"> Created by [@titanwings](https://github.com/titanwings) </div> --- ## 🆕 What Distilly does today ### 1️⃣ From Colleague Skill to Distilly The project is no longer limited to the colleague scenario. Its `distilly` creator builds source-grounded Person Profiles for three person families with one workflow, then packages each profile as an Agent Skill. ### 2️⃣ Three character families <table> <thead> <tr> <th width="33%" align="center">🧑💼 colleague</th> <th width="33%" align="center">💞 relationship</th> <th width="33%" align="center">🌟 celebrity</th> </tr> </thead> <tbody> <tr> <td align="center"><sub>Coworkers · mentors · teammates · up/downstream partners</sub></td> <td align="center"><sub>Exes · partners · parents · friends · close family</sub></td> <td align="center"><sub>Public figures · creators · public voices · fictional characters</sub></td> </tr> <tr> <td><sub>Builds a Work Skill + Persona from material-derived technical standards, workflows, expression, and workplace behavior. Supports Lark / DingTalk / Slack collection.</sub></td> <td><sub>Organizes material-derived expression patterns, emotional triggers, conflict patterns, and repair patterns into a reusable Persona Skill.</sub></td> <td><sub>Ships with a <b>six-dimension research toolchain</b> (subtitles → transcript cleanup → research merge → quality check) for organizing observable decisions, expression, and mental models.</sub></td> </tr> </tbody> </table> Each family has its own source-collection strategy, analysis dimensions, and Person Profile structure. ### 3️⃣ More Agent hosts The old version only ran in Claude Code. Distilly now supports native local Skill discovery across eight agent hosts. <table> <tr> <td align="center" width="25%"><a href="https://claude.ai/code"><picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/hosts/claude-code-wordmark-dark.svg"><img src="docs/assets/hosts/claude-code-wordmark-light.svg" alt="Claude Code" height="28"></picture></a></td> <td align="center" width="25%"><a href="https://github.com/NousResearch/hermes-agent"><img src="docs/assets/hosts/hermes-agent-wordmark.png" alt="Hermes Agent" height="32"></a></td> <td align="center" width="25%"><a href="https://github.com/openclaw/openclaw"><picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/hosts/openclaw-wordmark-dark.svg"><img src="docs/assets/hosts/openclaw-wordmark-light.svg" alt="OpenClaw" height="38"></picture></a></td> <td align="center" width="25%"><a href="https://github.com/openai/codex" title="Codex"><picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/hosts/codex-mark-dark.png"><img src="docs/assets/hosts/codex-mark-light.png" alt="Codex" height="64"></picture></a></td> </tr> <tr> <td align="center" width="25%"><a href="https://github.com/deepseek-ai/deepseek-harness"><picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/hosts/deepseek-wordmark-dark.svg"><img src="docs/assets/hosts/deepseek-wordmark-light.svg" alt="DeepSeek Harness" height="32"></picture></a></td> <td align="center" width="25%"><a href="https://pi.dev/docs/latest/skills"><img src="docs/assets/hosts/pi-mark.svg" alt="Pi coding agent" height="46"></a></td> <td align="center" width="25%"><a href="https://docs.x.ai/build/features/skills-plugins-marketplaces"><picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/hosts/grok-build-mark-dark.png"><img src="docs/assets/hosts/grok-build-mark-light.png" alt="Grok Build" height="46"></picture></a></td> <td align="center" width="25%"><a href="https://opencode.ai/docs/skills"><picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/hosts/opencode-wordmark-dark.svg"><img src="docs/assets/hosts/opencode-wordmark-light.svg" alt="OpenCode" height="32"></picture></a></td> </tr> </table> **Grok Bot preview:** Grok Bot supports saved/private Skills, but its official docs do not describe direct local `SKILL.md` imports. Distilly's workflow can be migrated manually into a saved Skill; direct repo installation is not yet verified. Each generated Person Profile is packaged as an Agent Skill and can be installed into any supported host. --- ## 📦 Supported Data Sources | Logo | Source | Messages | Docs / Wiki | Notes | |:----:|--------|:--------:|:-----------:|-------| | <img src="docs/assets/sources/lark-mark.png" alt="Lark" width="32" height="32"> | Lark (auto) | ✅ API | ✅ | Just enter a name, fully automatic | | <img src="docs/assets/sources/dingtalk-mark.jpg" alt="DingTalk" width="32" height="32"> | DingTalk (auto) | ⚠️ Browser | ✅ | DingTalk API doesn't support message history | | <img src="docs/assets/sources/slack-mark.png" alt="Slack" width="32" height="32"> | Slack (auto) | ✅ API | — | Requires admin to install Bot; free plan limited to 90 days | | <picture><source media="(prefers-color-scheme: dark)" srcset="docs/assets/sources/x-mark-dark.svg"><img src="docs/assets/sources/x-mark-light.svg" alt="X" width="32" height="32"></picture> | Public X posts | ✅ API | — | Optional, bounded celebrity research candidates through metered third-party service Xquik | | <img src="docs/assets/sources/wechat-mark.jpg" alt="WeChat" width="32" height="32"> | WeChat chat history | ✅ SQLite | — | Export first with WeChatMsg or PyWxDump | | 📄 | PDF / Images / Screenshots | — | ✅ | Manual upload | | <img src="docs/assets/sources/lark-mark.png" alt="Lark" width="32" height="32"> | Lark JSON export | ✅ | ✅ | Manual upload | | ✉️ | Email `.eml` / `.mbox` | ✅ | — | Manual upload | | 📝 | Markdown / direct paste | ✅ | ✅ | Manual input | --- ## ⚡ Install ### 🤖 For Agents Open any supported local Agent host and send: > Install Distilly from `https://github.com/titanwings/distilly`, then verify that this host
Lo que la gente pregunta sobre distilly
¿Qué es titanwings/distilly?
+
titanwings/distilly es subagents para el ecosistema de Claude AI. Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill(原同事 Skill). Tiene 24.3k estrellas en GitHub y su última actualización registrada es del 2026-09-02.
¿Cómo se instala distilly?
+
Puedes instalar distilly clonando el repositorio (https://github.com/titanwings/distilly) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar titanwings/distilly?
+
Nuestro agente de seguridad ha analizado titanwings/distilly y le ha asignado un Trust Score de 100/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene titanwings/distilly?
+
titanwings/distilly es mantenido por titanwings. La última actividad registrada en GitHub es del 2026-09-02, con 34 issues abiertos.
¿Hay alternativas a distilly?
+
Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.
Despliega distilly en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/titanwings-distilly)<a href="https://claudewave.com/repo/titanwings-distilly"><img src="https://claudewave.com/api/badge/titanwings-distilly" alt="Featured on ClaudeWave: titanwings/distilly" width="320" height="64" /></a>Más Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.