titanwings/colleague-skill

★ 17,863PythonAudience · pm founderComplexity · 2/5LicenseSetup · easy

Mindmap

mindmap
  root((repo))
    What it captures
      Technical knowledge
      Workflows
      Communication style
      Decision patterns
    Source materials
      Slack and chat exports
      PDFs and Markdown
      Email and screenshots
    Skill structure
      Work Skill half
      Persona half
    Usage
      Claude Code skills
      Slash command invoke
      OpenClaw integration

mindmap root((repo)) What it captures Technical knowledge Workflows Communication style Decision patterns Source materials Slack and chat exports PDFs and Markdown Email and screenshots Skill structure Work Skill half Persona half Usage Claude Code skills Slash command invoke OpenClaw integration

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Capture an outgoing teammate's technical standards and communication style as a reusable AI Skill before their last day.

USE CASE 2

Create a mentor Skill from saved notes, documents, and chat logs so junior team members can ask for guidance at any time.

USE CASE 3

Build a Skill from a partner's domain knowledge to preserve their decision-making approach for future projects.

Tech stack

Python

Getting it running

Difficulty · easy Time to first run · 30min

Use freely for any purpose including commercial use as long as you keep the copyright notice.

In plain English

colleague.skill is a tool for capturing what a departing colleague, intern, mentor, or partner knew and how they worked, and turning that into an AI Skill you can keep using after they're gone. The pitch in the README is to turn cold goodbyes into warm Skills: instead of losing the context, voice, and habits of someone who has moved on, you distill them into something an AI assistant can act out on your behalf. You feed it source materials from places like Feishu, DingTalk, Slack, WeChat, email, PDFs, Markdown notes, screenshots, or directly pasted text, plus your own subjective description of the person, such as their level, personality tags, and corporate-culture style. From that input it generates a Skill with two halves: a Work Skill that captures their systems knowledge, technical standards, and workflows, and a Persona that captures how they speak and make decisions across five layers from hard rules to interpersonal style. When a task comes in, the Persona decides the attitude and the Work Skill carries out the actual job, so the response sounds and acts like that person. It is meant to plug into AI coding assistants. The README describes installing it under .claude/skills/ for Claude Code, or under an OpenClaw skills directory, then invoking commands like /create-colleague to build a new one, /list-colleagues to see what you have, and /{slug} to talk to a specific colleague. It is built in Python (3.9+ per the badge) and is open-source under the MIT license, with the project evolving into a broader effort called dot-skill described in its roadmap. The full README is longer than what was provided.

Copy-paste prompts

Prompt 1

I want to create a colleague Skill from our Slack export and a folder of meeting notes. Walk me through the /create-colleague command and what source materials to include.

Prompt 2

My senior engineer is leaving next week. What information should I gather from them to build the most useful colleague Skill, and how do I capture it with this tool?

Prompt 3

Show me how to install colleague-skill under .claude/skills/ and invoke a saved colleague Skill with /slug to ask it a code-review question in Claude Code.

Prompt 4

How do I tune the Work Skill and Persona halves separately so the Skill gives accurate technical answers while also sounding like the real person?

Open on GitHub → Explain another repo

← titanwings on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.