How Agent Skills Evolve: A Large-Scale Empirical Study of Skills on GitHub
cs.SE
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/ZJU-CTAG/SkillEMP
Terminology
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking
- A-MEM: Agentic Memory for LLM Agents
- Skill Retrieval Augmentation for Agentic AI
- AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
- Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
- Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality
- Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale
- A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
- SkillNet: Create, Evaluate, and Connect AI Skills
- Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- SkillRouter: Skill Routing for LLM Agents at Scale
- Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
- Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
- SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems
- CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
- SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
- "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters