Paper 2605.31264
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
- Published
- May 2026
- Research lab
- Independent
- Citations
- 3
- GitHub
- 21K stars
01 In brief
Summary
COLLEAGUE.SKILL is an open-source system that automatically distills heterogeneous traces of a person or role (e.g., work documents, chat logs, public interviews) into portable, inspectable, and correctable AI skill packages.
The system generates a versioned package with two tracks: a capability track for practices and decision heuristics, and a bounded behavior track for communication style and interaction rules.
The package includes SKILL.md, work.md, persona.md, sub-skills, and metadata, and supports installation across agent hosts (e.g., Claude Code, OpenClaw), natural-language corrections, rollback, and optional gallery distribution.
Three presets exist: colleague (primary), celebrity/public-figure, and relationship, each with different evidence, consent, and governance assumptions.
As of 2026-05-28, the repository has ~18.5k GitHub stars, and the gallery lists 215 skills from 165 contributors with >100k cumulative stars.
The system emphasizes artifact-level claims, not behavioral fidelity, and positions productization as key to governance and evaluation.
Future work includes human and task-based studies to measure judgment quality and interaction safety across deployment settings.
02 From the paper
Abstract
LLM agents are increasingly expected not only to complete isolated tasks, but also to carry bounded representations of human expertise, judgment, and interaction style. Building such person-grounded agents remains difficult because actionable knowledge associated with a person or role is usually embedded in heterogeneous traces rather than written as clean instructions. Existing memory and persona systems capture fragments of this evidence, while skill frameworks provide portable packaging formats; however, there is no end-to-end workflow for distilling these traces into inspectable, correctable, and agent-usable skills. We present an automated trace-to-skill distillation system for generating person-grounded AI skills via expert knowledge distillation. Given materials from a target person or role, COLLEAGUE.SKILL produces a versioned skill package with two coordinated tracks: a capability track for practices, mental models, and decision heuristics, and a bounded behavior track for communication style, interaction rules, and correction history. The package can be inspected, invoked, updated through natural-language feedback, rolled back, installed across agent hosts, and optionally prepared for controlled distribution. We describe the artifact contract, generation workflow, correction lifecycle, deployment surface, and domain presets implemented in the open-source system. At the time of writing, the public repository has approximately 18.5k GitHub stars; the gallery lists 215 skills from 165 contributors and more than 100k cumulative stars across listed skill cards. The system illustrates how person-grounded skills can be represented as portable, correctable packages rather than opaque prompts or hidden memories.