awesome-llm-agent-skills-papers GitHub Details, Stars and Alternatives | OpenRepoFinder
wmmthu / repository
awesome-llm-agent-skills-papers
A curated list of papers, blog posts, and systems on skills for LLM agents — reusable, named capability units that an agent can store, retrieve, compose, and improve over time — together with closely adjacent research on tool use, function calling, procedural memory, and skill induction.
A transparent discovery signal based on current public GitHub metadata.
Recent activity35% weight
90
Community adoption25% weight
7
Maintenance state20% weight
100
License clarity10% weight
100
Project information10% weight
75
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
README preview
Awesome LLM Agent Skills Papers
A curated list of papers, blog posts, and systems on skills for LLM agents — reusable, named capability units that an agent can store, retrieve, compose, and improve over time — together with closely adjacent research on tool use, function calling, procedural memory, and skill induction.
Scope. Entries here treat skills as first-class artifacts (Anthropic-style skill folders, Voyager-style code skill libraries, learned options, induced procedures, retrievable prompts, callable tools). General LLM-agent work that does not put a skill abstraction at the center is mostly out of scope and lives in other awesome-lists.
Format. One line per entry, chronological within each section (oldest → newest):
- **Title** — First Author et al. *Venue Year*. [paper](url) [code](url)
Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward — Xu and Yan. arXiv 2026. paper
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering — Zhou et al. arXiv 2026. paper
Skill Definition & Formats
Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections — Schmotz et al. arXiv 2025. paper
Agent Skills Open Standard — Anthropic. 2025. site
Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale — Liu et al. arXiv 2026. paper
Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study — Liu et al. arXiv 2026. paper
Skill Acquisition & Induction
Code as Policies: Language Model Programs for Embodied Control — Liang et al. arXiv 2022. paper
Voyager: An Open-Ended Embodied Agent with Large Language Models — Wang et al. arXiv 2023. papercode
Eureka: Human-Level Reward Design via Coding Large Language Models — Ma et al. ICLR 2024. papercode
SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience — Sun et al. arXiv 2025. papercode
CUA-Skill: Develop Skills for Computer Using Agent — Chen et al. arXiv 2026. paper
Improving Interactive In-Context Learning from Natural Language Feedback — Klissarov et al. arXiv 2026. paper
From Context to Skills: Can Language Models Learn from Context Skillfully? — Si et al. arXiv 2026. papercode
Skill Curation & Learning
Reinforcement Learning for Self-Improving Agent with Skill Library — Wang et al. arXiv 2025. paper
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization — Lu et al. arXiv 2026. papercode
SkillX: Automatically Constructing Skill Knowledge Bases for Agents — Wang et al. arXiv 2026. paper
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning — Shi et al. arXiv 2026. paper
SkillOS: Learning Skill Curation for Self-Evolving Agents — Ouyang et al. arXiv 2026. paper
Skill Retrieval & Selection
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills — Liu et al. arXiv 2026. papercode
Skill Composition & Reuse
ReAct: Synergizing Reasoning and Acting in Language Models — Yao et al. ICLR 2023. papercode
Reflexion: Language Agents with Verbal Reinforcement Learning — Shinn et al. arXiv 2023. paper
When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail — Li. arXiv 2026. paper
Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis — Jiao et al. arXiv 2026. paper
Tool Use & Function Calling
Toolformer: Language Models Can Teach Themselves to Use Tools — Schick et al. arXiv 2023. paper
CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models — Qian et al. Findings of EMNLP 2024. paper
Gorilla: Large Language Model Connected with Massive APIs — Patil et al. arXiv 2023. papercode
Large Language Models as Tool Makers — Cai et al. arXiv 2023. papercode
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs — Qin et al. arXiv 2023. papercode
Tool Learning with Large Language Models: A Survey — Qu et al. arXiv 2024. paper
Benchmarks & Evaluation
CL-bench: A Benchmark for Context Learning — Dou et al. arXiv 2026. papercode
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks — Li et al. arXiv 2026. papersite
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? — Han et al. arXiv 2026. papercode
SkillTester: Benchmarking Utility and Security of Agent Skills — Wang et al. arXiv 2026. papercodesite
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings — Liu et al. arXiv 2026. papercode
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks — Zhong et al. arXiv 2026. papercode
Systems & Frameworks
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation — Wu et al. arXiv 2023. papercode
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework — Hong et al. arXiv 2023. papercode
Blogs & Engineering Notes
Introducing Agent Skills — Anthropic. Oct 2025. blog
Contributing
PRs adding papers, fixing venue/year metadata, or filling empty sections are very welcome. Please read CONTRIBUTING.md first — it covers the entry format, the chronological ordering rule, and the PR checklist.
License
To the extent possible under law, the contributors to this list have waived all copyright and related rights to the list itself under CC0 1.0. Cited papers, blog posts, and code repositories retain their own licenses.
A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - that works with Claude Code, Codex, Gemini CLI and your custom AI Agents
A curated collection of top-tier penetration testing tools and productivity utilities across multiple domains. Join us to explore, contribute, and enhance your hacking toolkit!
