# SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv: https://arxiv.org/abs/2605.13716 ยท HTML: https://mlsanity.com/paper/2605.13716/ ## Key facts - Cited by 18 papers in the map (data through 14 Oct 2026). - Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use. - Builds on 18 of its 26 references that are in the map. - First posted on arXiv 13 May 2026. ## Placed in - LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/) ## Builds on (most cited first, 18 of 18) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023) - [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023) - [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023) - [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020) - [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023) - [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019) - [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025) - [ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models](https://mlsanity.com/paper/2305.18323/) (2023) - [Reinforcement Learning for Self-Improving Agent with Skill Library](https://mlsanity.com/paper/2512.17102/) (2025) - [Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills](https://mlsanity.com/paper/2604.05333/) (2026) - [VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation](https://mlsanity.com/paper/2510.05156/) (2025) - [SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources](https://mlsanity.com/paper/2604.03964/) (2026) - [LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation](https://mlsanity.com/paper/2510.04851/) (2025) - [Test-Driven Development for Code Generation](https://mlsanity.com/paper/2402.13521/) (2024) - [Process Mining for Python (PM4Py): Bridging the Gap Between Process- and Data Science](https://mlsanity.com/paper/1905.06169/) (2019) - [CUA-Skill: Develop Skills for Computer Using Agent](https://mlsanity.com/paper/2601.21123/) (2026) - [GraSP: Graph-Structured Skill Compositions for LLM Agents](https://mlsanity.com/paper/2604.17870/) (2026) ## Built on by (most cited first, 18 of 18) - [SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment](https://mlsanity.com/paper/2605.27899/) (2026) - [Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember](https://mlsanity.com/paper/2607.29468/) (2026) - [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026) - [When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents](https://mlsanity.com/paper/2608.05810/) (2026) - [Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents](https://mlsanity.com/paper/2605.27955/) (2026) - [ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners](https://mlsanity.com/paper/2608.09732/) (2026) - [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026) - [Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence](https://mlsanity.com/paper/2608.21156/) (2026) - [From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained](https://mlsanity.com/paper/2607.00911/) (2026) - [From Cognitive Architectures to Language Agents: A Mechanism-Level Review of Lineage, Convergence, and Migration Gaps](https://mlsanity.com/paper/2607.23942/) (2026) - [SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries](https://mlsanity.com/paper/2608.05604/) (2026) - [Repo2Skill-Evo: Repository Skills Go Stale in Silence](https://mlsanity.com/paper/2608.21964/) (2026) - [Towards a Systems Foundation for Agentic Skills: Architecture, Lifecycle, and Security](https://mlsanity.com/paper/2608.29596/) (2026) - [FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA](https://mlsanity.com/paper/2609.19680/) (2026) - [EnSIMem: Entity-Structured Indexing for Long-Term Agent Memory](https://mlsanity.com/paper/2609.27279/) (2026) - [RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning](https://mlsanity.com/paper/2609.32326/) (2026) - [Skill-V: Verifiable Self-Evolving Skill Library for Interactive Agents](https://mlsanity.com/paper/2610.11781/) (2026) - [Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules](https://mlsanity.com/paper/2610.14216/) (2026) ## Abstract (arXiv) Large language model agents increasingly rely on skill libraries for multi-step tasks, yet these libraries can accumulate persistent defects as skills are added, reused, patched, and linked to changing dependencies. We call this failure mode skill technical debt: library-level defects that may not break a single skill locally but can harm future retrieval, composition, and execution. Existing skill-based agents mainly focus on task-time retrieval, planning, and repair, while library-time maintenance remains underexplored. We propose SkillOps, a method-agnostic plug-in framework for maintaining skill libraries. SkillOps represents each skill as a typed Skill Contract (P, O, A, V, F), organizes skills with a Hierarchical Skill Ecosystem Graph, and diagnoses library health across utility, compatibility, risk, and validation dimensions. Given a raw skill library, SkillOps produces a maintained library that can be used by existing retrieval or planning agents without changing their internal code. On ALFWorld, SkillOps achieves 79.5 percent task success as a standalone agent, outperforming the strongest baseline by 8.8 percentage points with no additional task-time large language model calls. As a plug-in layer, it improves retrieval-heavy baselines by 0.68 to 2.90 percentage points. The current rule-based maintenance implementation uses nearly zero library-time large language model calls or tokens, showing that skill-library maintenance can be added as a low-overhead architectural layer.