|
🧑💼 Your colleague quit, your mentor graduated, your teammate transferred — taking their whole playbook and context with them? |
Upgraded from colleague.skill to dot-skill — not just colleagues, anyone can be distilled into a Skill
Colleagues · partners · family · old friends · idols · public figures · fictional characters — even yourself
Source material + your description → an AI Skill that genuinely thinks like them Thinks in their frame, speaks in their voice
🆕 What's new · 📦 Data Sources · ⚡ Install · 🚀 Usage · ✨ Demo · 💬 Discord
Massive thanks to everyone who starred — we'll keep shipping, keep distilling.
📢 2026.04.19 Update — WeChat group 5 is live! Come hang out with the dot-skill community — share skills, discuss features, trade tips.
QR refreshes every 7 days (expires 2026-04-24) — 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
Created by @titanwings · Powered by Shanghai AI Lab · AI Safety Center
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.
| 🧑💼 colleague | 💞 relationship | 🌟 celebrity |
|---|---|---|
| Coworkers · mentors · teammates · up/downstream partners | Exes · partners · parents · friends · close family | Public figures · creators · public voices · fictional characters |
| Work Skill + Persona two-layer architecture — learns both their technical standards and workflows, and their manner of speaking and workplace posture. Supports Feishu / DingTalk / Slack auto-collection. | 🆕 Photo-sharing feature coming soon — your distilled relationship won't just reply to messages; it'll send photos and share slices of its day, the way a real person would. | Ships with a complete six-dimension research toolchain (subtitles → transcript cleanup → research merge → quality check). Not mimicking tone — reproducing their mental models and decision frameworks. |
Each family has its own prompt pipeline, source-collection strategy, and generation template.
The old version only ran in Claude Code. Now it's cross-host across four:
| Host | Description |
|---|---|
| 🟣 Claude Code | Native slash-command support |
| 🟠 Hermes Agent | One-command install, /dot-skill works directly |
| 🔵 OpenClaw | Fully compatible |
| ⚫ Codex | Invoke by skill name |
Generated character Skills can also be one-command installed into any host.
| Source | Messages | Docs / Wiki | Spreadsheets | Notes |
|---|---|---|---|---|
| 🟢 Feishu (auto) | ✅ API | ✅ | ✅ | Just enter a name, fully automatic |
| 🟡 DingTalk (auto) | ✅ | ✅ | DingTalk API doesn't support message history | |
| 🟣 Slack (auto) | ✅ API | — | — | Requires admin to install Bot; free plan limited to 90 days |
| 💬 WeChat chat history | ✅ SQLite | — | — | Export first with WeChatMsg / PyWxDump / 留痕 |
| 📄 PDF / Images / Screenshots | — | ✅ | — | Manual upload |
| 📦 Feishu JSON export | ✅ | ✅ | — | Manual upload |
✉️ Email .eml / .mbox |
✅ | — | — | Manual upload |
| 📝 Markdown / direct paste | ✅ | ✅ | — | Manual input |
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.
🛠️ Want to install it yourself? Click for paths
git clone https://github.com/titanwings/colleague-skill <TARGET>| Host | <TARGET> path |
|---|---|
| Claude Code | ~/.claude/skills/dot-skill |
| OpenClaw | ~/.openclaw/workspace/skills/dot-skill |
| Codex | ~/.codex/skills/dot-skill |
| Hermes | After clone, run python3 tools/install_hermes_skill.py --force |
For Feishu/DingTalk auto-collection credentials, publishing a generated character Skill to any host, Windows-specific handling, etc., see Detailed Install Guide (INSTALL.md)
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}.
| Command | Description |
|---|---|
/dot-skill |
Canonical unified entrypoint |
/{character}-{slug} |
Invoke full Skill (Persona + Work) |
/{character}-{slug}-work |
Work capabilities only |
/{character}-{slug}-persona |
Persona only |
python3 tools/skill_writer.py --action list ... |
List generated Skills across all three families |
python3 tools/version_manager.py --action rollback ... |
Roll back a Skill version |
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"One from each family.
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.
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.
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?
📚 More real-world cases in the community gallery — 100+ skills and counting
dot-skill uses Persona as the universal base, with family-specific modules layered on top:
| Family | Persona Content | Additional Modules |
|---|---|---|
| 🧑💼 colleague | 6-layer personality: hard rules → identity → expression → decisions → interpersonal → Correction | ➕ Work Skill: scope, workflow, output preferences, experience knowledge base |
| 💞 relationship | Expression DNA · emotional triggers · conflict pattern · repair pattern | — |
| 🌟 celebrity | Mental models · decision heuristics · expression DNA · external-evaluation contrast | ➕ Six-dimension research dossier (works / interviews / decisions / timeline...) |
Execution: Receive task → Persona decides attitude & tone → Additional modules fill in execution detail → Output in their voice
- 📥 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
This project follows the AgentSkills open standard. The entire repo is a skill directory:
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
Source material quality = Skill quality — and quality sources differ across families:
| Family | Source priority (high → low) |
|---|---|
| 🧑💼 colleague | Their own long-form writing (design docs / review comments) › decision-making replies › casual group chat |
| 💞 relationship | Complete chat history › letters / social posts / diaries › third-party descriptions |
| 🌟 celebrity | First-person books / blogs / long interviews › decision records (launches, commits, Q&A) › third-party commentary |
- 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!
Colleague.Skill: Automated AI Skill Generation via Expert Knowledge Distillation
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
colleaguefamily. Separate papers on the relationship / celebrity family extensions are planned.
MIT License © titanwings
Made with 🧬 for everyone who wants to distill a person into a skill.