skillfed

200k+ skills wired into one graph, +40% reward across three backbones

Notes on SkillNet: Create, Evaluate, and Connect AI Skills (arXiv:2603.04448) — Yuanying Liang, R. Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jiasheng Gu, Shumin Deng, Yu-Zhe Yao, Mengru Wang, Shuofei Qiao, Xin Xu, and 37 more · February 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 retrieval Bridge: retrieval × benchmarks

A nineteen-institution team spanning Zhejiang University, Alibaba, Tencent, Ant Group, and UCLA built SkillNet, infrastructure that creates, grades, and connects agent skills at scale instead of just hosting them. Skills get pulled from execution trajectories, GitHub repositories, PDFs and slide decks, and raw natural-language prompts through an LLM-driven pipeline, then run through deduplication (directory-structure and MD5 comparison) plus rule-based and model-based filtering before landing in one of ten functional categories. The distinguishing piece is a three-layer skill ontology: a taxonomy of categories and tags, a relation graph linking individual skills via similar_to, compose_with, belong_to, and depend_on edges, and a package library for modular deployment. Skills here aren't vetted one at a time and left to sit — they're wired into a queryable network.

Every admitted skill is graded on five axes — Safety, Completeness, Executability, Maintainability, Cost-awareness — by an LLM evaluator (GPT-5o-mini) on a Good/Average/Poor scale, with Executability getting a second check: code-bearing skills actually run in sandboxes. Against a 200-skill sample independently rated by three PhD-level annotators, the automated scores stayed under a mean absolute error of 0.03 on every dimension, with quadratic weighted kappa essentially at 1.000. Then came the real test: across ALFWorld, WebShop, and ScienceWorld, three backbone models — DeepSeek V3.2, Gemini 2.5 Pro, o4 Mini — equipped with SkillNet-derived skill collections beat both a ReAct baseline and an ExpeL-style experience-retrieval baseline, on seen and unseen task splits alike, with zero overlap between the skill-source trajectories and the test tasks.

Key numbers

Average reward gain over ReAct+40%
Reduction in interaction steps-30%
Total candidate skills aggregated200,000+
Curated high-quality skills retained150,000+
Evaluator MAE vs. human raters (200-skill sample)<0.03

Skills related to this research

wiki-export Wiki Export transforms your Obsidian vault's wikilink graph into multiple structured formats—JSON, GraphML, Cypher scripts, and interactive HTML—ready for use in Gephi, Neo4j, and custom tools. Optionally filter by project or visibility tags, and assign community IDs for graph analysis and visualization.★ 3,032 tooluniverse-gene-regulatory-networks This skill maps transcription factor regulation by combining binding motif analysis, chromatin immunoprecipitation data, and expression quantitative trait loci to answer which TFs control a gene and which genes a TF targets. It separates direct regulatory evidence (ChIP-seq binding) from indirect signals (co-expression), integrates protein interaction networks, and grounds claims in perturbation experiments rather than computational prediction alone.★ 1,595 datamodellm DataModelLM is a visual editor for building database schemas in Prisma format, rendering them as entity-relationship diagrams on an interactive canvas. Define models, relationships, and constraints through a structured schema file, then view the resulting data structure graphically. Supports one-to-many, one-to-one, and many-to-many relationships with full Prisma type and attribute support.★ 1,333

Related notes

References

  1. SkillNet: Create, Evaluate, and Connect AI Skills (arXiv:2603.04448)
  2. Reflexion: language agents with verbal reinforcement learning (Shinn et al., NeurIPS 2023)
  3. ExpeL: LLM Agents Are Experiential Learners (Zhao et al., AAAI 2024)
  4. ALFWorld / WebShop / ScienceWorld benchmarks