$npx skillfedfor your agent

1,858 reusable skills mined from 22,511 real chats — zero weight updates

Notes on AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution (arXiv:2603.01145) — Yutao Yang, Junsong Li, Qianjun Pan, Bihao Zhan, Yuxuan Cai, Linge Du, Jie Zhou, Kai Chen, Qin Chen, Xin Li, Bo Zhang, Liang He · March 2026

Note published · written by SkillFed’s research pipeline from the paper above · how these notes are made

AI-assisted notes · reviewed by SkillFed Skill evolution

AutoSkill is a training-free plug-in layer that turns repeated user requests into versioned skill artifacts instead of treating them as disposable chat history. Two loops run in tandem. A serving loop rewrites the incoming query, ranks stored skills with a hybrid BM25+dense retrieval score, and injects only the ones that clear a similarity threshold. A background evolution loop extracts a candidate skill from the user's own queries — never the model's replies — and hands it to an LLM judge that compares it against its single nearest neighbor and decides add, merge, or discard. A merge doesn't concatenate text: it bumps the existing skill's version number and folds in only the new, non-conflicting constraints, so a skill like a writing-style preference accumulates as one evolving artifact rather than a pile of near-duplicate prompts.

Running the extraction pipeline across four WildChat-1M subsets — English and Chinese, GPT-3.5 and GPT-4, each filtered to conversations with more than 8 turns — turns up 1,858 extracted skills from 22,511 conversations. The resulting SkillBank skews toward programming and technical writing: Programming & Software Dev. is the largest category at 482 skills, roughly a quarter of the corpus, and "python" is the single most common tag. It also catches softer behavioral preferences — roleplay personas, translation conventions. Case studies confirm the versioning mechanism works as designed: one English text-rewriting skill reached version 0.1.34 after 34 rounds of incremental refinement from recurring feedback, while a rarely-revisited Chinese counseling-persona skill sat untouched at 0.1.0.

Key numbers

Skills extracted (4 WildChat subsets)1,858
Conversations analyzed (>8 turns each)22,511
Largest category share482 skills, Programming & Software Dev. (~26%)
Deepest single-skill refinement depthv0.1.34 (34 rounds)
Most common skill tagpython — 98 skills

Skills related to this research

wiki-retrieve wiki-retrieve upgrades vault search from page-level to chunk-level granularity, combining contextual prefixes, BM25 sparse retrieval, and dense reranking to reduce retrieval failures. Setup is opt-in with built-in privacy gates: run fully on-machine with synthetic prefixes, or opt into Anthropic API or claude CLI tiers for better context generation.★ 10,007 search This skill guides you through building complete search applications on OpenSearch, covering index setup, document processing, and multiple search strategies including BM25, semantic, hybrid, and agentic approaches. Deploy ML models, ingest PDFs and other documents, and evaluate search quality end-to-end.★ 37 Microsoft Teams This skill connects your agent to Microsoft Teams chats (1:1 and group conversations) through Microsoft Graph v1.0, letting you list chats, retrieve recent messages, and send replies. Uses delegated OAuth scopes that don't require tenant admin approval. Note: channel messages are not supported—they need elevated admin-gated permissions.★ 13 Deep Research Deep Research automates end-to-end investigation workflows by intelligently selecting and combining data sources—academic papers, domain-specific databases via ToolUniverse, and web results—to extract, analyze, and synthesize findings into structured reports. It decomposes research questions into multiple dimensions, orchestrates parallel data collection across sources, and produces publication-ready documents tailored to your inquiry.★ 564

Related notes

References

  1. Yang, Li, Pan et al., "AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution," arXiv:2603.01145 (2026)
  2. Zhao et al., "WildChat: 1M ChatGPT Interaction Logs in the Wild" (2024)
  3. Packer et al., "MemGPT: Towards LLMs as Operating Systems" (2023)
  4. Zhong et al., "MemoryBank: Enhancing Large Language Models with Long-Term Memory," AAAI (2024)
  5. Wang et al., "Voyager: An Open-Ended Embodied Agent with Large Language Models" (2023)