# SkillFlow: Scalable and Efficient Agent Skill Retrieval System

arXiv: https://arxiv.org/abs/2504.06188 · HTML: https://mlsanity.com/paper/2504.06188/

## Key facts

- Cited by 22 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 30 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## 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)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [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)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [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)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Passage Re-ranking with BERT](https://mlsanity.com/paper/1901.04085/) (2019)
- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Multi-Stage Document Ranking with BERT](https://mlsanity.com/paper/1910.14424/) (2019)
- [Agent AI: Surveying the Horizons of Multimodal Interaction](https://mlsanity.com/paper/2401.03568/) (2024)
- [Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation](https://mlsanity.com/paper/2412.01130/) (2024)

## Built on by (most cited first, 22 of 22)

- [Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering](https://mlsanity.com/paper/2604.08224/) (2026)
- [SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents](https://mlsanity.com/paper/2605.05726/) (2026)
- [From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills](https://mlsanity.com/paper/2605.23899/) (2026)
- [OpenSkill: Open-World Self-Evolution for LLM Agents](https://mlsanity.com/paper/2606.06741/) (2026)
- [Agent Skill Evaluation and Evolution: Frameworks and Benchmarks](https://mlsanity.com/paper/2606.11435/) (2026)
- [Skill Is Not Document: Query-Conditioned Compatibility for LLM Agent Skill Routing](https://mlsanity.com/paper/2606.03565/) (2026)
- [Generative Skill Composition for LLM Agents](https://mlsanity.com/paper/2606.32025/) (2026)
- [Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries](https://mlsanity.com/paper/2607.10113/) (2026)
- [Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval](https://mlsanity.com/paper/2607.06283/) (2026)
- [Beyond Task-Only Matching: Personalized Skill Routing with Counterfactual Evaluation](https://mlsanity.com/paper/2608.28241/) (2026)
- [Imagine Before Retrieval: Prospective Skill Retrieval for LLM Agents](https://mlsanity.com/paper/2609.01642/) (2026)
- [SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents](https://mlsanity.com/paper/2607.15557/) (2026)
- [From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Based LLM Agents](https://mlsanity.com/paper/2608.09168/) (2026)
- [Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval](https://mlsanity.com/paper/2608.16071/) (2026)
- [Workflow Closure Is Not Scientific Closure in Auto-Research Systems](https://mlsanity.com/paper/2605.26200/) (2026)
- [Efficient Skill Grounding via Code Refactoring with Small Language Models](https://mlsanity.com/paper/2606.07999/) (2026)
- [Skill-Augmented AI Agents for Medical Research Analysis: An Exploratory Multi-Model Human Evaluation in an NSCLC Transcriptomic Biomarker Task](https://mlsanity.com/paper/2606.11830/) (2026)
- [Scientific Data Skills: Enabling Agent-Ready Scientific Data Services at Scale](https://mlsanity.com/paper/2608.19625/) (2026)
- [Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation](https://mlsanity.com/paper/2609.38024/) (2026)
- [SkillGATE: Gate-Aware Monte Carlo Tree Search for Skill Retrieval](https://mlsanity.com/paper/2610.05489/) (2026)
- [Mining Agent Skills from Production Traces](https://mlsanity.com/paper/2610.05777/) (2026)
- [Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution](https://mlsanity.com/paper/2610.12367/) (2026)

## Abstract (arXiv)

AI agents can extend their capabilities at inference time by loading reusable skills into context, yet equipping an agent with too many skills, particularly irrelevant ones, degrades performance. As community-driven skill repositories grow, agents need a way to selectively retrieve only the most relevant skills from a large library. We present SkillFlow, the first open, multi-stage retrieval system for agent skill discovery that frames skill acquisition as an information retrieval problem over a corpus of ~35K community-contributed SKILL.md definitions indexed from GitHub. The pipeline progressively narrows a large candidate set through four stages (dense retrieval, two rounds of cross-encoder reranking, and LLM-based selection), balancing recall and precision at each stage. We evaluate SkillFlow on two coding benchmarks: SkillsBench, a benchmark of 87 tasks and 229 matched skills; and Terminal-Bench, a benchmark that provides only 89 tasks, and no matched skills. On SkillsBench, SkillFlow-retrieved skills raise Pass@1 from 9.2% to 16.4% (+78.3%, padj = 3.64 × 10-2), reaching 84.1% of the oracle ceiling, while on Terminal-Bench, agents readily use the retrieved skills (70.1% use rate) yet show no performance gain, revealing that retrieval alone is insufficient when the corpus lacks high-quality, executable skills for the target domain. SkillFlow demonstrates that framing skill acquisition as an information retrieval task is an effective strategy, and that the practical impact of skill-augmented agents hinges on corpus coverage and skill quality, particularly the density of runnable code and bundled artifacts. (GitHub: https://github.com/IBPA/skill-flow)