# colleague-skill **Repository Path**: droidphone/colleague-skill ## Basic Information - **Project Name**: colleague-skill - **Description**: No description available - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: dot-skill - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2026-04-26 - **Last Updated**: 2026-04-26 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README
# 🧬 dot-skillοΌˆεŒδΊ‹.skillοΌ‰ ### *"You folks building LLMs are all code-sages! Flesh is weak! Ascend to cyberspace!"* [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE) [![Python 3.9+](https://img.shields.io/badge/Python-3.9%2B-blue.svg)](https://python.org) [![AgentSkills](https://img.shields.io/badge/AgentSkills-Standard-green)](https://agentskills.io) [![Stars](https://img.shields.io/github/stars/titanwings/colleague-skill?style=social)](https://github.com/titanwings/colleague-skill/stargazers) [![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-blueviolet)](https://claude.ai/code) [![Hermes](https://img.shields.io/badge/Hermes-Skill-orange)](https://github.com/titanwings/colleague-skill) [![OpenClaw](https://img.shields.io/badge/OpenClaw-Skill-teal)](https://github.com/titanwings/colleague-skill) [![Codex](https://img.shields.io/badge/Codex-Skill-black)](https://github.com/titanwings/colleague-skill) [![Discord](https://img.shields.io/badge/Discord-Join%20Community-5865F2?logo=discord&logoColor=white)](https://discord.gg/aRjmJBdK)
πŸ§‘β€πŸ’Ό  Your colleague quit, your mentor graduated, your teammate transferred β€” taking their whole playbook and context with them?
πŸ’ž  Your family, old friends, partner drifting apart β€” and you want to hold on to the way it felt to be with them?
🌟  Your favorite author, idol, thinker you'll never meet β€” but you want to know what they'd say about your question?
### ✨ dot-skill solves all three.
Upgraded from **colleague.skill** to **dot-skill** β€” not just colleagues, **anyone** can be distilled into a Skill Colleagues Β· partners Β· family Β· old friends Β· idols Β· public figures Β· fictional characters β€” even yourself **Source material + your description β†’ an AI Skill that genuinely thinks like them** Thinks in their frame, speaks in their voice
[πŸ†• What's new](#-whats-new-in-this-major-release) Β· [πŸ“¦ Data Sources](#-supported-data-sources) Β· [⚑ Install](#-install) Β· [πŸš€ Usage](#-usage) Β· [✨ Demo](#-demo) Β· [πŸ’¬ Discord](https://discord.gg/aRjmJBdK) [**δΈ­ζ–‡**](docs/lang/README_ZH.md) Β· [**EspaΓ±ol**](docs/lang/README_ES.md) Β· [**Deutsch**](docs/lang/README_DE.md) Β· [**ζ—₯本θͺž**](docs/lang/README_JA.md) Β· [**Русский**](docs/lang/README_RU.md) Β· [**PortuguΓͺs**](docs/lang/README_PT.md) Β· [**ν•œκ΅­μ–΄**](docs/lang/README_KO.md)
---
### πŸŽ‰ 2026.04.19 Milestone β€” **dot-skill just hit 15k ⭐!** Massive thanks to everyone who starred β€” we'll keep shipping, keep distilling.
> πŸ“’ **2026.04.22 Update** β€” **WeChat group 8 is live!** Come hang out with the dot-skill community β€” share skills, discuss features, trade tips. > > dot-skill WeChat group QR > > QR refreshes every 7 days (expires 2026-04-29) β€” if expired, ping me on Discord. > πŸ—ΊοΈ **2026.04.13** β€” **dot-skill Roadmap is live!** colleague.skill is evolving into **dot-skill** β€” distill anyone, not just colleagues. πŸ‘‰ **[Full Roadmap](ROADMAP.md)** Β· **[πŸ’¬ Discord](https://discord.gg/aRjmJBdK)** > 🌐 **2026.04.07** β€” Community gallery is live! Any skill / meta-skill can drive traffic directly to your own GitHub repo. No middleman. πŸ‘‰ **[titanwings.github.io/colleague-skill-site](https://titanwings.github.io/colleague-skill-site/)**
Created by [@titanwings](https://github.com/titanwings) Β· Powered by **Shanghai AI Lab Β· AI Safety Center**
--- ## πŸ†• 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 β€” one engine distills anyone, instead of being a colleague-specific script. ### 2️⃣ Three character families
πŸ§‘β€πŸ’Ό colleague πŸ’ž relationship 🌟 celebrity
Coworkers Β· mentors Β· teammates Β· up/downstream partners Exes Β· partners Β· parents Β· friends Β· close family Public figures Β· creators Β· public voices Β· fictional characters
Work Skill + Persona two-layer architecture β€” learns both their technical standards and workflows, and their manner of speaking and workplace posture. Supports Feishu / DingTalk / Slack auto-collection. πŸ†• Photo-sharing feature coming soon β€” 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 β†’ transcript cleanup β†’ research merge β†’ quality check). Not mimicking tone β€” reproducing their mental models and decision frameworks.
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: | Host | Description | |------|-------------| | 🟣 **Claude Code** | Native slash-command support | | 🟠 **Hermes Agent** | One-command install, `/dot-skill` works directly | | πŸ”΅ **OpenClaw** | Fully compatible | | ⚫ **Codex** | Invoke by skill name | Generated character Skills can also be one-command installed into any host. --- ## πŸ“¦ Supported Data Sources | Source | Messages | Docs / Wiki | Spreadsheets | Notes | |--------|:--------:|:-----------:|:------------:|-------| | 🟒 Feishu (auto) | βœ… API | βœ… | βœ… | Just enter a name, fully automatic | | 🟑 DingTalk (auto) | ⚠️ Browser | βœ… | βœ… | DingTalk API doesn't support message history | | 🟣 Slack (auto) | βœ… API | β€” | β€” | Requires admin to install Bot; free plan limited to 90 days | | πŸ’¬ WeChat chat history | βœ… SQLite | β€” | β€” | Export first with WeChatMsg / PyWxDump / η•™η—• | | πŸ“„ PDF / Images / Screenshots | β€” | βœ… | β€” | Manual upload | | πŸ“¦ Feishu JSON export | βœ… | βœ… | β€” | Manual upload | | βœ‰οΈ Email `.eml` / `.mbox` | βœ… | β€” | β€” | Manual upload | | πŸ“ Markdown / direct paste | βœ… | βœ… | β€” | Manual input | --- ## ⚑ Install It's 2026 β€” 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.
πŸ› οΈ Want to install it yourself? Click for paths
```bash git clone https://github.com/titanwings/colleague-skill ``` | Host | `` 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)](INSTALL.md)** --- ## πŸš€ Usage In the host where dot-skill is installed, launch it β€” type `/dot-skill`, or just tell your Agent "start dot-skill". It first asks which family you want to distill: `colleague` Β· `relationship` Β· `celebrity`. Then enter alias, basic profile, personality tags, and pick a data source. All fields can be skipped β€” even a description alone can generate a Skill. Once created, invoke the generated Skill with `/{character}-{slug}`. ### πŸŽ›οΈ Commands | 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 | ### πŸ”¬ Celebrity Research Toolchain The `celebrity` family ships with an end-to-end research toolchain, from subtitles to a finished draft: ```bash # Download video subtitles bash tools/research/download_subtitles.sh "" "./tmp/subtitles" # Subtitles β†’ transcript python3 tools/research/srt_to_transcript.py "./tmp/subtitles/example.srt" # Merge research notes python3 tools/research/merge_research.py "./skills/celebrity/" # Quality check python3 tools/research/quality_check.py "./skills/celebrity//SKILL.md" ``` --- ## ✨ Demo One from each family.
### 🌟 celebrity β€” distilling Andrej Karpathy > Six-dimension research: works Β· interviews Β· decisions Β· expression DNA Β· external evaluations Β· timeline
> Case adapted from community work [alchaincyf/karpathy-skill](https://github.com/alchaincyf/karpathy-skill) ``` User ❯ Everyone's talking about Agents now β€” 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 β€” 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 β€” I'm betting on the best scaffolding and the strictest eval. ```
### πŸ§‘β€πŸ’Ό colleague β€” 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 β€” 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. ```
### πŸ’ž relationship β€” 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? ```
πŸ“š More real-world cases in the **[community gallery](https://titanwings.github.io/colleague-skill-site/)** β€” 100+ skills and counting
--- ## πŸ”§ Features ### 🧱 Generated Skill Structure dot-skill uses **Persona** as the universal base, with family-specific modules layered on top: | Family | Persona Content | Additional Modules | |--------|-----------------|-------------------| | πŸ§‘β€πŸ’Ό **colleague** | 6-layer personality: hard rules β†’ identity β†’ expression β†’ decisions β†’ interpersonal β†’ Correction | βž• **Work Skill**: scope, workflow, output preferences, experience knowledge base | | πŸ’ž **relationship** | Expression DNA Β· emotional triggers Β· conflict pattern Β· repair pattern | β€” | | 🌟 **celebrity** | Mental models Β· decision heuristics Β· expression DNA Β· external-evaluation contrast | βž• Six-dimension research dossier (works / interviews / decisions / timeline...) | > **Execution**: Receive task β†’ Persona decides attitude & tone β†’ Additional modules fill in execution detail β†’ Output in their voice ### 🧬 Evolution - πŸ“₯ **Append files** β†’ auto-analyze delta β†’ merge into relevant sections, never overwrite existing conclusions - πŸ’¬ **Conversation correction** β†’ say "they wouldn't do that, they'd be xxx" β†’ writes to the Correction layer, takes effect immediately - πŸ•°οΈ **Version control** β†’ auto-archive on every update, rollback to any previous version - πŸ”¬ **Celebrity research pipeline** β†’ subtitles β†’ transcript cleanup β†’ six-dimension research β†’ quality check --- ## πŸ“‚ Project Structure This project follows the [AgentSkills](https://agentskills.io) open standard. The entire repo is a skill directory: ``` dot-skill/ β”œβ”€β”€ SKILL.md # skill entry point (official frontmatter) β”œβ”€β”€ prompts/ # prompt system across three families β”‚ β”œβ”€β”€ intake.md # [colleague] info intake β”‚ β”œβ”€β”€ work_analyzer.md # [colleague] work capability extraction β”‚ β”œβ”€β”€ persona_analyzer.md # [colleague] personality extraction β”‚ β”œβ”€β”€ work_builder.md # [colleague] work.md generation β”‚ β”œβ”€β”€ persona_builder.md # [colleague] persona.md 6-layer structure β”‚ β”œβ”€β”€ merger.md # [shared] incremental merge logic β”‚ β”œβ”€β”€ correction_handler.md # [shared] conversation correction β”‚ β”œβ”€β”€ relationship/ # [relationship] emotion/conflict/repair prompts β”‚ └── celebrity/ # [celebrity] six-dimension research + mental-model prompts β”œβ”€β”€ tools/ # Python tools β”‚ β”œβ”€β”€ feishu_auto_collector.py # [colleague] Feishu auto-collector β”‚ β”œβ”€β”€ dingtalk_auto_collector.py # [colleague] DingTalk auto-collector β”‚ β”œβ”€β”€ slack_auto_collector.py # [colleague] Slack auto-collector β”‚ β”œβ”€β”€ email_parser.py # [shared] email parser β”‚ β”œβ”€β”€ research/ # [celebrity] celebrity research toolchain β”‚ β”‚ β”œβ”€β”€ download_subtitles.sh # subtitle download β”‚ β”‚ β”œβ”€β”€ transcribe_audio.py # audio β†’ text β”‚ β”‚ β”œβ”€β”€ srt_to_transcript.py # subtitles β†’ transcript β”‚ β”‚ β”œβ”€β”€ merge_research.py # six-dimension research merge β”‚ β”‚ └── quality_check.py # quality check β”‚ β”œβ”€β”€ install_*_skill.py # [shared] multi-host one-shot installers β”‚ β”œβ”€β”€ skill_writer.py # [shared] skill file management β”‚ └── version_manager.py # [shared] version archive & rollback β”œβ”€β”€ skills/ # generated Skills (gitignored) β”‚ β”œβ”€β”€ colleague/ # colleagues β”‚ β”œβ”€β”€ relationship/ # close relationships β”‚ └── celebrity/ # public figures β”œβ”€β”€ docs/PRD.md β”œβ”€β”€ requirements.txt └── LICENSE ``` --- ## ⚠️ Notes **Source material quality = Skill quality** β€” and quality sources differ across families: | Family | Source priority (high β†’ low) | |--------|------------------------------| | πŸ§‘β€πŸ’Ό **colleague** | Their **own long-form writing** (design docs / review comments) **β€Ί** **decision-making replies** **β€Ί** casual group chat | | πŸ’ž **relationship** | Complete chat history **β€Ί** letters / social posts / diaries **β€Ί** third-party descriptions | | 🌟 **celebrity** | First-person books / blogs / long interviews **β€Ί** decision records (launches, commits, Q&A) **β€Ί** 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 β€” please file issues if you find bugs! --- ## πŸ“„ Technical Report > **[Colleague.Skill: Automated AI Skill Generation via Expert Knowledge Distillation](colleague_skill.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 β€” the theoretical foundation for today's `colleague` family. Separate papers on the relationship / celebrity family extensions are planned. --- ## ⭐ Star History Star History Chart ---
**MIT License** © [titanwings](https://github.com/titanwings) Made with 🧬 for everyone who wants to distill a person into a skill.