SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

• URL: http://arxiv.org/abs/2602.12670v1
• Date: Fri, 13 Feb 2026 07:06:06 GMT
• Title: SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• Abstract summary: Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time.<n>We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers.<n>We show curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain.<n>Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming.
• Score: 61.89812116484928
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers. Each task is evaluated under three conditions: no Skills, curated Skills, and self-generated Skills. We test 7 agent-model configurations over 7,308 trajectories. Curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain (+4.5pp for Software Engineering to +51.9pp for Healthcare) and 16 of 84 tasks show negative deltas. Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming. Focused Skills with 2--3 modules outperform comprehensive documentation, and smaller models with Skills can match larger models without them.

Related papers

• SkillAlchemy: Open-World Agent Skill Creation [11.836010370630568]
  Agent skills are reusable procedural artifacts that extend language agents with specialized, tool conventions, and domain behaviors at inference time.<n>Create reliable skills still depends largely on human authorship, model priors, or execution traces.<n>We propose SkillAlchemy, an admission-centered framework for source-grounded skill creation.
  arXiv  Detail & Related papers  (2026-08-24T15:58:57Z)
• Signal or Noise? A Benchmark Study of Agent Skills in Web Development [6.7220476997481375]
  We use WebDev-Skills-Bench to study 31 public WebDev Skills on 50 Web-Bench projects and 1,000 ordered tasks.<n>Across four models, target Skill injection reduces mean Pass@2 by 1.3% to 4.2%, lowers task completion depth, and increases token cost by 72% to 394%.<n>Losses concentrate on easy early tasks, Skill rankings transfer weakly across models, and anti-pattern rules outperform example-heavy content within helpful Skills.
  arXiv  Detail & Related papers  (2026-08-24T10:13:07Z)
• Demystifying Agent Skills: Why They Work-Until They Don't [58.92875630998418]
  Existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: emphtextbfWhen do skills help, why do they work, and where do they fail?<n>We isolate the effects of representation, outcome annotation, retrieval difficulty, and cross-framework of skills.<n>We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes.
  arXiv  Detail & Related papers  (2026-08-14T07:26:38Z)
• Agent Skills Can Be Harmful: An Empirical Study of Skill-Induced Failures in LLM Agents [9.71657681051469]
  This paper presents a comprehensive analysis of skill-induced agent failures by attributing task failures and cost regressions to specific loaded skills.<n>We instantiate this framework on SkillsBench and SWE-Skills-Bench, yielding 307 skill-induced failures, including 125 functional failures and 182 efficiency regressions.<n>We propose research topics and tooling improvements for safer and more cost-aware skill reuse.
  arXiv  Detail & Related papers  (2026-08-12T10:15:19Z)
• Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning [72.09826781730662]
  Long-horizon reasoning demands that the model switch between distinct skills inside a reasoning chain.<n>We introduce Skill Entropy, a measure of the difficulty of switching from one skill to another.<n>We propose Skill-Entropy RL, an RL framework where the model predicts not only the answer at each step but also the skill used to produce it.
  arXiv  Detail & Related papers  (2026-08-05T17:57:16Z)
• SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing [81.51044612408793]
  SkillAudit is a framework for evolving agent skills without ground-truth feedback.<n>To turn behavioral differences into edit guidance, SkillAudit uses Process-Aligned Contrastive Evaluation.<n>It routes edits through two pipelines: Refine removes noisy or irrelevant guidance from broadly useful skills, while Repair replaces passages that conflict with the task.
  arXiv  Detail & Related papers  (2026-06-12T08:20:09Z)
• SkillJuror: Measuring How Agent Skill Organization Changes Runtime Behavior [23.11308948097101]
  Current benchmarks rarely distinguish what a Skill says from how it is organized.<n>We study this distinction through Progressive Disclosure, where a concise root file points agents to supporting resources on demand.<n>We present SkillJuror, a framework for evaluating Skill writing paradigms.
  arXiv  Detail & Related papers  (2026-06-10T01:11:50Z)
• SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization [99.18305770138677]
  Agent skills are reusable strategies that guide agent reasoning and action.<n>Current skill construction methods treat the problem as one-shot extraction.<n>We introduce SkillComposer, a framework that decomposes skill construction into three learnable operations.
  arXiv  Detail & Related papers  (2026-06-04T12:16:08Z)
• SkillsInjector: Dynamic Skill Context Construction for LLM Agents [16.631471381875816]
  Existing methods treat skill injection as a static step, selecting skills with fixed criteria, fixing the budget in advance, and leaving descriptions unchanged.<n>We propose SkillsInjector, a two-stage adaptive method that jointly addresses these decisions.<n>Across tau2-bench, SkillsBench, and ALFWorld, SkillsInjector achieves the highest score, improving over the strongest baseline by 3.9, 6.1, and 7.3 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-05-28T11:44:32Z)
• SkillGen: Verified Inference-Time Agent Skill Synthesis [60.927977774369516]
  SkillGen is a framework that synthesizes a single auditable skill from trajectories generated by a base agent.<n>It identifies reusable success patterns, recurring failure modes, and behaviors that appear in nearby successes but are missing from failures.<n>A key novelty in SkillGen is that we model agent skills as interventions to empirically verify the net effect of skills on the overall performance.
  arXiv  Detail & Related papers  (2026-05-09T19:24:11Z)
• EvoSkill: Automated Skill Discovery for Multi-Agent Systems [6.319876096746374]
  We introduce textbfEvoSkill, a self-evolving framework that automatically discovers and refines agent skills.<n>EvoSkill analyzes execution failures, proposes new skills or edits to existing ones, and materializes them into structured, reusable skill folders.<n>We evaluate EvoSkill on two benchmarks: OfficeQA, a grounded reasoning benchmark over U.S. Treasury data, and SealQA, a noisy retrieval benchmark.
  arXiv  Detail & Related papers  (2026-03-03T09:07:22Z)
• SkillCraft: Can LLM Agents Learn to Use Tools Skillfully? [67.69996753743129]
  We introduce SkillCraft, a benchmark explicitly stress-test agent ability to form and reuse higher-level tool compositions.<n> SkillCraft features realistic, highly compositional tool-use scenarios with difficulty scaled along both quantitative and structural dimensions.<n>We propose a lightweight evaluation protocol that enables agents to auto-compose atomic tools into executable Skills, cache and reuse them inside and across tasks.
  arXiv  Detail & Related papers  (2026-02-28T15:44:31Z)
• SkillNet: Create, Evaluate, and Connect AI Skills [159.47504178122156]
  SkillNet is an open infrastructure designed to create, evaluate, and organize AI skills at scale.<n>Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit.
  arXiv  Detail & Related papers  (2026-02-26T14:24:02Z)
• SoK: Agentic Skills -- Beyond Tool Use in LLM Agents [6.356997609995175]
  Agentic systems increasingly rely on reusable procedural capabilities, textita.k.a., agentic skills, to execute long-horizon reliably.<n>This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update)<n>We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution.
  arXiv  Detail & Related papers  (2026-02-24T13:11:38Z)
• PolySkill: Learning Generalizable Skills Through Polymorphic Abstraction [20.687269802717893]
  We introduce PolySkill, a new framework that enables agents to learn generalizable and compositional skills.<n> Experiments show that our method improves skill reuse by 1.7x on seen websites.<n>By enabling the agent to identify and refine its own goals, the PolySkill enhances the agent's ability to learn a better curriculum.
  arXiv  Detail & Related papers  (2025-10-17T17:56:00Z)
• SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills [48.05057798832005]
  We introduce SkillWeaver, a skill-centric framework enabling web agents to self-improve by autonomously synthesizing reusable skills as APIs.<n>Given a new website, the agent autonomously discovers skills, executes them for practice, and distills practice experiences into robust APIs.<n>Experiments on WebArena and real-world websites demonstrate the efficacy of SkillWeaver, achieving relative success rate improvements of 31.8% and 39.8%, respectively.
  arXiv  Detail & Related papers  (2025-04-09T17:51:50Z)
• Inducing Programmatic Skills for Agentic Tasks [69.29902147942673]
  We propose agent skill induction (ASI) to allow agents to adapt themselves by inducing, verifying, and utilizing program-based skills on the fly.<n>We show that ASI outperforms the static baseline agent and its text-skill counterpart by 23.5% and 11.3% in success rate.
  arXiv  Detail & Related papers  (2025-04-09T12:25:37Z)
• Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models [61.467781476005435]
  skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated rationales. Our skill-slices and framework open a new avenue in model evaluation, leveraging skill-specific analyses to unlock a more granular and actionable understanding of model capabilities.
  arXiv  Detail & Related papers  (2024-10-17T17:51:40Z)
• SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness [11.083396379885478]
  We release SkillMatch, a benchmark for the task of skill relatedness based on expert knowledge mining from millions of job ads. We also propose a scalable self-supervised learning technique to adapt a Sentence-BERT model based on skill co-occurrence in job ads.
  arXiv  Detail & Related papers  (2024-10-07T13:05:26Z)
• SkillMimic: Learning Basketball Interaction Skills from Demonstrations [85.23012579911378]
  We introduce SkillMimic, a unified data-driven framework that fundamentally changes how agents learn interaction skills.<n>Our key insight is that a unified HOI imitation reward can effectively capture the essence of diverse interaction patterns from HOI datasets.<n>For evaluation, we collect and introduce two basketball datasets containing approximately 35 minutes of diverse basketball skills.
  arXiv  Detail & Related papers  (2024-08-12T15:19:04Z)
• Agentic Skill Discovery [19.5703917813767]
  Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. We introduce a novel framework for skill discovery that is entirely driven by LLMs.
  arXiv  Detail & Related papers  (2024-05-23T19:44:03Z)
• Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics [18.546688182454236]
  Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. We propose accelerating exploration in the skill space using state-conditioned generative models. We validate our approach across four challenging manipulation tasks, demonstrating our ability to learn across task variations.
  arXiv  Detail & Related papers  (2022-11-04T02:42:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.