# From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained arXiv: https://arxiv.org/abs/2607.00911 ยท HTML: https://mlsanity.com/paper/2607.00911/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. - Builds on 33 of its 57 references that are in the map. - First posted on arXiv 1 Jul 2026. ## Placed in - LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/) ## Builds on (most cited first, 30 of 33) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021) - [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023) - [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023) - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024) - [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023) - [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023) - [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026) - [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025) - [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024) - [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023) - [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024) - [EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction](https://mlsanity.com/paper/2401.06201/) (2024) - [An Empirical Study of the Non-determinism of ChatGPT in Code Generation](https://mlsanity.com/paper/2308.02828/) (2023) - [Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale](https://mlsanity.com/paper/2601.10338/) (2026) - [Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models](https://mlsanity.com/paper/2408.02442/) (2024) - [Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality](https://mlsanity.com/paper/2602.08004/) (2026) - [Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers](https://mlsanity.com/paper/2506.13538/) (2025) - [Backstabber's Knife Collection: A Review of Open Source Software Supply Chain Attacks](https://mlsanity.com/paper/2005.09535/) (2020) - [Taxonomy of Attacks on Open-Source Software Supply Chains](https://mlsanity.com/paper/2204.04008/) (2022) - [An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry](https://mlsanity.com/paper/2303.02552/) (2023) - [Can LLMs Replace Manual Annotation of Software Engineering Artifacts?](https://mlsanity.com/paper/2408.05534/) (2024) - [Small World with High Risks: A Study of Security Threats in the npm Ecosystem](https://mlsanity.com/paper/1902.09217/) (2019) - [Sampling in Software Engineering Research: A Critical Review and Guidelines](https://mlsanity.com/paper/2002.07764/) (2020) - [Agent READMEs: An Empirical Study of Context Files for Agentic Coding](https://mlsanity.com/paper/2511.12884/) (2025) - [An Empirical Comparison of Dependency Network Evolution in Seven Software Packaging Ecosystems](https://mlsanity.com/paper/1710.04936/) (2017) - [Categorizing the Content of GitHub README Files](https://mlsanity.com/paper/1802.06997/) (2018) - [SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems](https://mlsanity.com/paper/2605.13716/) (2026) - [On the Impact of AGENTS.md Files on the Efficiency of AI Coding Agents](https://mlsanity.com/paper/2601.20404/) (2026) - [On the Use of Agentic Coding Manifests: An Empirical Study of Claude Code](https://mlsanity.com/paper/2509.14744/) (2025) ## Built on by (most cited first, 2 of 2) - [Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts](https://mlsanity.com/paper/2607.18970/) (2026) - [Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills](https://mlsanity.com/paper/2610.19264/) (2026) ## Abstract (arXiv) AI coding agents increasingly rely on skills: structured context bundles, typically a SKILL.md file with a YAML header and Markdown body, loaded on demand for domain knowledge, workflows, and scripts. Public registries such as skills.sh now host tens of thousands of skills, making them an emerging unit of reuse in agent-based software engineering. Yet skills have largely been viewed as agent capabilities rather than software artefacts whose content and evolution shape agent behaviour. We present the first empirical study of AI agent skills as engineered artefacts that are authored, reused, customised and maintained, across public registries and personal-use repositories. We mined 18,463 skills from skills.sh and 23,199 personal-use skills from 5,876 GitHub repositories, identifying 3,709 reuse links. LLM-based classification into SWEBOK knowledge areas (KAs) shows Software Construction dominates alongside a long tail of specialised areas. A thematic analysis of 180 skills identifies six content categories. Qualitative coding of 444 modifications reveals six themes, of which reworking operational specifications and adapting knowledge and resources are the primary target of change. Our findings show that reuse is largely a one-time copy operation: most reused skills remain near-verbatim, 53% are never modified after adoption, and subsequent local maintenance is overwhelmingly additive. Customisation primarily adapts skills to local environments, whereas evolution accretes new inline domain knowledge. Across both, a stable behavioural contract - how a skill interacts with users, monitors runtime state, and recovers from failures - remains almost untouched. These results suggest maintenance effort should focus on project-specific bindings, and that registries and tool support should enable consolidating the domain knowledge skills re-author in isolation.