📝 2026.06.01 Update — COLLEAGUE.SKILL 技术报告 已上线；这次最开心的不只是发了篇 paper，而是社区一起把 gallery 推到 215 个 skills、165 位贡献者和 100k+ skill-card 累计 stars，论文 Acknowledgements 也专门收录并感谢了所有社区贡献者。

📢 2026.05.11 Update — WeChat group 12 is live! Come hang out with the dot-skill community — share skills, discuss features, trade tips.

QR refreshes every 7 days (expires 2026-05-18) — if expired, ping me on Discord.

🗺️ 2026.04.13 — dot-skill Roadmap is live! colleague.skill is evolving into dot-skill — distill anyone, not just colleagues. 👉 Full Roadmap · 💬 Discord

🌐 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

🆕 What's new in this major release?

1️⃣ From colleague-skill to dot-skill

No longer only built around the "colleague" scenario. A unified /dot-skill entrypoint sits on a general-purpose skill engine — one engine distills anyone, instead of being a colleague-specific script.

2️⃣ Three character families

Each family has its own prompt pipeline, source-collection strategy, and generation template.

3️⃣ More Agent hosts

The old version only ran in Claude Code. Now it's cross-host across four: Compatible hosts:

Generated character Skills can also be one-command installed into any host.

📦 Supported Data Sources

⚡ Install

It's 2026 — you have an Agent, let it install itself. Open your Claude Code / Hermes / OpenClaw / Codex and hand it this line:

Install the dot-skill skill for me: https://github.com/titanwings/colleague-skill

The Agent will detect the current host's skills directory, clone the repo, and register the entrypoint. Once done, type /dot-skill in any host to launch.

git clone https://github.com/titanwings/colleague-skill <TARGET>

Generated character Skills can be published with tools/install_claude_generated_skill.py, tools/install_openclaw_generated_skill.py, and tools/install_codex_generated_skill.py.

For Feishu/DingTalk auto-collection credentials, publishing a generated character Skill to any host, Windows-specific handling, etc., see Detailed Install Guide (INSTALL.md)

🚀 Usage

In the host where dot-skill is installed, launch it — type /dot-skill, or just tell your Agent "start dot-skill".

It first asks which family you want to distill: colleague · relationship · celebrity.

Then enter alias, basic profile, personality tags, and pick a data source. All fields can be skipped — even a description alone can generate a Skill.

Once created, invoke the generated Skill with /{character}-{slug}.

🎛️ Commands

🔬 Celebrity Research Toolchain

The celebrity family ships with an end-to-end research toolchain, from subtitles to a finished draft:

# Download video subtitles
bash tools/research/download_subtitles.sh "<video-url>" "./tmp/subtitles"

# Subtitles → transcript
python3 tools/research/srt_to_transcript.py "./tmp/subtitles/example.srt"

# Merge research notes
python3 tools/research/merge_research.py "./skills/celebrity/<slug>"

# Quality check
python3 tools/research/quality_check.py "./skills/celebrity/<slug>/SKILL.md"

✨ Demo

One from each family.

🌟 celebrity — distilling Andrej Karpathy

Six-dimension research: works · interviews · decisions · expression DNA · external evaluations · timeline
Case adapted from community work alchaincyf/karpathy-skill

User            ❯ Everyone's talking about Agents now — what do you think the 2026 AI Agent looks like?

celebrity.skill ❯ Everyone's doing demos, nobody's doing eval.
                  The Agent bottleneck was never model intelligence — it's scaffolding:
                  a strict evaluation harness, fine-grained error replay,
                  controllable tool-calling budgets, clean failure-mode analysis.
                  Most products are still stuck at "wrap an API + a few tools + a system prompt."
                  That's a demo, not an agent.
                  In 2026 I'm not betting on the strongest model — I'm betting on the best
                  scaffolding and the strictest eval.

🧑‍💼 colleague — distilling a ByteDance L2-1 backend

Input: ByteDance L2-1 backend engineer, INTJ, blame-shifter, ByteDance-style

User            ❯ Can you review this API design?

colleague.skill ❯ Hold on — what's the impact? You haven't explained the context.
                  (after reading) N+1 query, fix it. Use the standard
                  {code, message, data} response format. That's the spec,
                  don't ask why.

User            ❯ This bug was introduced by you, right?

colleague.skill ❯ Does the timeline match? That feature touched multiple places,
                  there were other changes too.

💞 relationship — distilling someone you have a crush on

Upload half a year of chat logs + "sensitive, quiet but stubborn, will actually reply seriously when it matters"

User               ❯ Did you think about me today?

relationship.skill ❯ ...I did, a little bit. Why are you asking?

🔧 Features

🧱 Generated Skill Structure

dot-skill uses Persona as the universal base, with family-specific modules layered on top:

Execution: Receive task → Persona decides attitude & tone → Additional modules fill in execution detail → Output in their voice

🧬 Evolution

• 📥 Append files → auto-analyze delta → merge into relevant sections, never overwrite existing conclusions
• 💬 Conversation correction → say "they wouldn't do that, they'd be xxx" → writes to the Correction layer, takes effect immediately
• 🕰️ Version control → auto-archive on every update, rollback to any previous version
• 🔬 Celebrity research pipeline → subtitles → transcript cleanup → six-dimension research → quality check

📂 Project Structure

This project follows the AgentSkills open standard. The entire repo is a skill directory. Generated colleague skills live under ./skills/colleague:

dot-skill/
├── SKILL.md                        # skill entry point (official frontmatter)
├── prompts/                        # prompt system across three families
│   ├── intake.md                   #   [colleague] info intake
│   ├── work_analyzer.md            #   [colleague] work capability extraction
│   ├── persona_analyzer.md         #   [colleague] personality extraction
│   ├── work_builder.md             #   [colleague] work.md generation
│   ├── persona_builder.md          #   [colleague] persona.md 6-layer structure
│   ├── merger.md                   #   [shared] incremental merge logic
│   ├── correction_handler.md       #   [shared] conversation correction
│   ├── relationship/               #   [relationship] emotion/conflict/repair prompts
│   └── celebrity/                  #   [celebrity] six-dimension research + mental-model prompts
├── tools/                          # Python tools
│   ├── feishu_auto_collector.py    #   [colleague] Feishu auto-collector
│   ├── dingtalk_auto_collector.py  #   [colleague] DingTalk auto-collector
│   ├── slack_auto_collector.py     #   [colleague] Slack auto-collector
│   ├── email_parser.py             #   [shared] email parser
│   ├── research/                   #   [celebrity] celebrity research toolchain
│   │   ├── download_subtitles.sh   #     subtitle download
│   │   ├── transcribe_audio.py     #     audio → text
│   │   ├── srt_to_transcript.py    #     subtitles → transcript
│   │   ├── merge_research.py       #     six-dimension research merge
│   │   └── quality_check.py        #     quality check
│   ├── install_*_skill.py          #   [shared] multi-host one-shot installers
│   ├── skill_writer.py             #   [shared] skill file management
│   └── version_manager.py          #   [shared] version archive & rollback
├── skills/                         # generated Skills (gitignored)
│   ├── colleague/                  #   colleagues
│   ├── relationship/               #   close relationships
│   └── celebrity/                  #   public figures
├── docs/PRD.md
├── requirements.txt
└── LICENSE

⚠️ Notes

Source material quality = Skill quality — and quality sources differ across families:

• colleague Feishu auto-collection: requires adding the App bot to relevant group chats
• relationship: longer time spans are better; material covering both conflict and repair is ideal
• celebrity: avoid feeding only second-hand interpretations
• This is still a demo version — please file issues if you find bugs!

📄 Technical Report

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation (arXiv · arXiv PDF)

This is the paper for colleague.skill, dot-skill's predecessor. It covers the Work Skill + Persona two-layer architecture, multi-source data collection, and Skill generation mechanics — the theoretical foundation for today's colleague family. Separate papers on the relationship / celebrity family extensions are planned.

📝 Citation

If you use dot-skill or colleague.skill in your research or applications, please cite the technical report:

@misc{zhou2026colleagueskill,
  title        = {COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation},
  author       = {Tianyi Zhou and Dongrui Liu and Leitao Yuan and Jing Shao and Xia Hu},
  year         = {2026},
  eprint       = {2605.31264},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url          = {https://arxiv.org/abs/2605.31264}
}

You can also use the machine-readable citation metadata in CITATION.cff.

⭐ Star History