SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Tingxu Han; Yi Zhang; Wei Song; Chunrong Fang; Zhenyu Chen; Youcheng Sun; Lijie Hu

cs.SEMar 16, 2026

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

Authors: Tingxu Han, Yi Zhang, Wei Song, Chunrong Fang, Zhenyu Chen, Youcheng Sun, Lijie Hu

Organizations: Nanjing University · Mohamed bin Zayed University of Artificial Intelligence · South China University of Technology · The University of New South Wales

Abstract

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.

Figures & tables

Figure 1: Illustration of how agent skills are used in a software engineering workflow. Given a natural-language requirement, the LLM-based agent selects the most relevant skill from its skill library, including skills such as writing code, running tests, debugging, creating pull requests, and deploying, and injects it into the context window. The agent then executes a series of SWE actions to produce the final software artifacts (such as code) that fulfill the requirement.

Benchmark	Size	Skill Cond.	Real Projects	Det. Verifier	SWE-Focused
SWE-Bench Verified Jimenez et al. (2024)	500	None	Yes	Yes	Yes
TerminalBench Merrill and others (2026)	200	None	Yes	Yes	Yes
HumanEval Chen and others (2021)	164	None	No	Partial	No
SkillsBench Li et al. (2026)	84	Yes	Yes	Yes	Partial
SWE-Skills-Bench	565	Yes	Yes	Yes	Yes

Table 1: Comparison of SWE-Skills-Bench with existing benchmarks. “Skill Cond.” indicates whether the benchmark includes agent skills. “Det. Verifier” indicates whether deterministic (non-LLM) verification is included. “SWE-Focused” indicates whether the benchmark is specifically designed for software engineering tasks.

Figure 2: The distribution of the curated skills and generated tasks.

Figure 3: Overview of the SWE-Skills-Bench construction pipeline. We begin with 84,192 public skills and narrow them down through three filtering stages: category selection, semantic filtering, and feasibility screening. This process yields 49 SWE skills (Stage 1). Next, for each skill, we identify a matching GitHub project and generate 565 task instances of the form $(R,E,P,S)$ (Stage 2). For each criterion in the requirements document $P$ , we build deterministic verifiers using pytest unit tests (Stage 3). Finally, we run a paired evaluation that compares agent performance with and without the SKILL.md file, allowing us to measure the effectiveness of the skill (Stage 4).

Figure 4: The pipeline of task instance generation.

Skills	$\#$ Tasks	$\textbf{Pass}^{+}$	$\textbf{Pass}^{-}$	$\boldsymbol{\Delta P}$	$\boldsymbol{C^{+}}$	$\boldsymbol{C^{-}}$	$\boldsymbol{\rho}$	CE
add-uint-support	12	100.0%	100.0%	0.0%	880K	414K	+112.6%	—
analytics-events	10	100.0%	100.0%	0.0%	321K	157K	+104.6%	—
analyze-ci	11	100.0%	100.0%	0.0%	66K	74K	-10.6%	—
dbt-transformation-patterns	10	100.0%	100.0%	0.0%	422K	208K	+103.2%	—
gitops-workflow	13	100.0%	100.0%	0.0%	130K	57K	+127.1%	—
grafana-dashboards	12	100.0%	100.0%	0.0%	150K	116K	+29.3%	—

Table 2: Evaluation results across all 49 skills.

\text{Pass}^{+}

and

\text{Pass}^{-}

denote pass rates with and without skill injection, respectively.

\Delta P

is the skill utility delta,

C^{+}

and

C^{-}

are average token costs,

\rho

is the token overhead ratio, and

\mathrm{CE}

is cost efficiency. Best viewed in color.

Figure 5: Context interference in the linkerd-patterns skill (

\Delta P=-9.1\%

). The task requires a Server CRD and a ServerAuthorization CRD enforcing mTLS identity verification for a gRPC service. Left: Template 5 from the injected skill, which near-matches the task but encodes different concrete values: API version v1beta1 with proxyProtocol: HTTP/1 , and multiple authorization modes (meshTLS, unauthenticated, and CIDR-based). Center: Without the skill, the agent reasons from first principles and produces a correct solution using v1beta3 , gRPC , and standard meshTLS.serviceAccounts . Right: With the skill, the agent’s output degrades through three stages, each traceable to a specific region of the template (matched by circled numbers): 1 Surface anchoring, the agent copies v1beta1 and HTTP/1 verbatim; 2 Hallucination, while reconciling the template’s mixed authorization modes, the agent fabricates a nonexistent rules/metricsServers field; 3 Concept bleed, the template’s NetworkPolicy example causes the agent to append an unrequested resource, conflating Linkerd-level and Kubernetes-level authorization.

Figure 6: The prompt used for requirement-driven verification generation.

Figure 7: The prompt used for task instance requirement generation.

Figure 8: An example of the generated requirement in SWE-Skills-Bench.

Software Engineering Agents

Software Engineering Agents are AI systems that use code, tools, and feedback to perform software development tasks.

See all 323 papers

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering
Apr 10, 2026Jingzhi Gong, Ruizhen Gu, Zhiwei Fei +7Software Engineering Agents Multi-Objective Evolutionary Optimization
King’s College London, London, United Kingdom · Queen’s University Belfast, Belfast, United Kingdom · Nanjing University, Nanjing, China +3
Signal or Noise? A Benchmark Study of Agent Skills in Web Development
Aug 24, 2026Ziyue Yang, Fan DingLLM Agent Skill Evaluation Software Engineering Agents
Baidu, NLP Beijing, China
SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
Sep 8, 2026Pujun Zheng, Zixin Shang, Shufan Jiang +5Reward Hacking Software Engineering Agents
East China Normal University · Shanghai Artificial Intelligence Laboratory · Fudan University

Apr 10, 2026J/K move · Enter open · S save

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering

Jingzhi Gong, Ruizhen Gu, Zhiwei Fei, Yazhuo Cao+6

King’s College London, London, United Kingdom · Queen’s University Belfast, Belfast, United Kingdom · Nanjing University, Nanjing, China+3

Software Engineering Agents Multi-Objective Evolutionary Optimization

Open paper AskPDF arXiv

Agent skills are increasingly used to configure coding agents for software engineering (SE) tasks, yet current practice treats them as static, hand-crafted assets, or evolved on pass rate alone. This is insufficient: a skill can improve task success while substantially raising token cost, or introducing misleading guidance. We argue that SE agent skill bundles can be treated as multi-objective search objects and present SkillMOO, a framework that evolves skill bundles through LLM-proposed edits and NSGA-II Pareto selection on pass rate and inference cost. Evaluated across all 16 SkillsBench SE tasks, SkillMOO achieves the top pass rate rank on 11 of 12 non-zero-pass tasks while achieving cost reductions of up to 31.7% over static bundles, with pass rate gains up to 21 percentage points. Analysis of 38 skill edits shows that pruning and substitution dominate successful operations, offering actionable principles for skill bundle design. Thereby, the current practice of deploying skills without cost-aware validation leaves better skill configurations unexplored, motivating a new class of cost-aware, search-based skill engineering.

Abstract

Software Engineering Agents

Explore similar work

SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering

Signal or Noise? A Benchmark Study of Agent Skills in Web Development

SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents