Episode
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
- Podcast
- Daily Paper Cast
- Published
- Jun 2, 2026
- Duration seconds
- 1278
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/dc215157
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/colleague-skill-automated-ai-skill-generation-via-expert-knowledge-distillation/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/colleague-skill-automated-ai-skill-generation-via-expert-knowledge-distillation.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 73 | cs.AI, cs.CL, cs.LG Authors: Tianyi Zhou, Dongrui Liu, Leitao Yuan, Jing Shao, Xia Hu Title: COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation Arxiv: http://arxiv.org/abs/2605.31264v1 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 cumulativ…