{"id":"https://openalex.org/W7204160725","doi":"https://doi.org/10.48550/arxiv.2608.23067","title":"Signal or Noise? A Benchmark Study of Agent Skills in Web Development","display_name":"Signal or Noise? A Benchmark Study of Agent Skills in Web Development","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204160725","doi":"https://doi.org/10.48550/arxiv.2608.23067"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23067","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23067","pdf_url":"https://arxiv.org/pdf/2608.23067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029661948","display_name":"Ziyue Yang","orcid":"https://orcid.org/0000-0002-1658-0260","observed_orcids":["https://orcid.org/0000-0002-1658-0260","https://orcid.org/0009-0004-6196-9293"]},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Ziyue","raw_affiliation_strings":["Baidu , NLP Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu , NLP Beijing , China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148074564","display_name":"Fan Ding","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9106000065803528,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9106000065803528,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10430","display_name":"Software Engineering Techniques and Practices","score":0.032600000500679016,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.010400000028312206,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/agent-skills","display_name":"agent skills","score":0.7590000033378601},{"id":"https://openalex.org/keywords/ai-coding-agents","display_name":"coding agents","score":0.7900000214576721},{"id":"https://openalex.org/keywords/web-development","display_name":"web development","score":0.7630000114440918},{"id":"https://openalex.org/keywords/prompt-injection","display_name":"prompt injection","score":0.6729999780654907},{"id":"https://openalex.org/keywords/prompt-length","display_name":"prompt length","score":0.46799999475479126},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.527999997138977},{"id":"https://openalex.org/keywords/anti-patterns","display_name":"anti-patterns","score":0.6269999742507935},{"id":"https://openalex.org/keywords/token-cost","display_name":"token cost","score":0.8050000071525574}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7949000000953674},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6033999919891357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5982000231742859},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.5740000009536743},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5562000274658203},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38839998841285706},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3779999911785126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37380000948905945},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23067","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23067","pdf_url":"https://arxiv.org/pdf/2608.23067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23067","doi":"https://doi.org/10.48550/arxiv.2608.23067","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23067","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23067","pdf_url":"https://arxiv.org/pdf/2608.23067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204160725.pdf","grobid_xml":"https://content.openalex.org/works/W7204160725.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W3027879771","https://openalex.org/W3030163527","https://openalex.org/W4385327683","https://openalex.org/W4392867139","https://openalex.org/W4401306867","https://openalex.org/W4409671919","https://openalex.org/W4411120254","https://openalex.org/W4415248976","https://openalex.org/W4415348594","https://openalex.org/W4415795469","https://openalex.org/W4417516960","https://openalex.org/W7129079999","https://openalex.org/W7133215859","https://openalex.org/W7138004636"],"related_works":["https://openalex.org/W7129079999","https://openalex.org/W7138004636","https://openalex.org/W7165018355","https://openalex.org/W7161067994","https://openalex.org/W7202353180","https://openalex.org/W7160518234","https://openalex.org/W7162330764","https://openalex.org/W7164331416","https://openalex.org/W7204093987","https://openalex.org/W7203627230"],"abstract_inverted_index":{"Agent":[0],"Skills":[1,72],"are":[2,7,161,176],"reusable":[3,19],"procedural":[4],"modules":[5],"that":[6,196],"increasingly":[8],"injected":[9,24,54],"into":[10,114],"coding-agent":[11],"sessions":[12],"to":[13,129,141,148,191],"encode":[14],"framework":[15],"conventions,":[16],"anti-patterns,":[17],"and":[18,60,77,92,135,209,244,248],"tools.":[20],"However,":[21],"because":[22],"each":[23],"Skill":[25,34,50,98,122,168,184,203,223],"expands":[26],"the":[27,49,108,115,172],"prompt":[28,109,179],"of":[29,68,150,171],"every":[30],"query,":[31],"an":[32,41,164],"effective":[33],"benchmark":[35,82],"must":[36],"determine":[37],"not":[38],"only":[39,105,146],"whether":[40,48],"agent":[42,116],"can":[43],"solve":[44],"a":[45,64,88,221,225,228,234,240,251],"task,":[46],"but":[47,183],"should":[51],"have":[52],"been":[53],"at":[55],"all.":[56],"We":[57],"introduce":[58],"WebDev-Skills-Bench":[59],"use":[61],"it":[62],"for":[63,254],"controlled":[65],"empirical":[66],"study":[67],"31":[69],"public":[70],"WebDev":[71],"on":[73,199],"50":[74],"Web-Bench":[75],"projects":[76],"1,000":[78],"ordered":[79],"tasks.":[80],"The":[81],"compares":[83],"four":[84,119],"matched":[85,222],"conditions,":[86],"including":[87],"length-matched":[89,246],"irrelevant":[90,167],"control":[91],"leave-one-out":[93],"component":[94],"ablations.":[95],"To":[96],"isolate":[97],"effects":[99],"from":[100],"prompt-length":[101],"artifacts,":[102],"we":[103],"place":[104],"SKILL.md":[106],"in":[107,145],"while":[110,174],"mounting":[111],"auxiliary":[112],"files":[113],"workspace.":[117],"Across":[118],"models,":[120,208],"target":[121],"injection":[123,238],"reduces":[124],"mean":[125],"Pass@2":[126,188],"by":[127,139,189],"1.3%":[128],"4.2%,":[130],"lowers":[131,187],"task":[132],"completion":[133],"depth,":[134],"increases":[136],"token":[137],"cost":[138],"72%":[140],"394%,":[142],"with":[143],"gains":[144],"17%":[147],"36%":[149],"Skill-project":[151],"pairs.":[152],"Length-matched":[153],"controls":[154,247],"reveal":[155],"two":[156],"failure":[157],"modes:":[158],"some":[159],"models":[160],"length-distracted,":[162],"where":[163,178],"equally":[165],"long":[166],"reproduces":[169],"most":[170],"loss,":[173],"others":[175],"content-misled,":[177],"length":[180],"is":[181],"neutral":[182],"content":[185,214],"still":[186],"1.1%":[190],"1.4%.":[192],"Further":[193],"analysis":[194],"shows":[195],"losses":[197],"concentrate":[198],"easy":[200],"early":[201],"tasks,":[202],"rankings":[204],"transfer":[205],"weakly":[206],"across":[207],"anti-pattern":[210],"rules":[211],"outperform":[212],"example-heavy":[213],"within":[215],"helpful":[216],"Skills.":[217],"These":[218],"findings":[219],"recast":[220],"as":[224,239],"hypothesis":[226],"about":[227],"particular":[229],"Skill-project-model":[230],"triple":[231],"rather":[232],"than":[233],"portable":[235],"asset,":[236],"reframing":[237],"per-deployment":[241],"routing":[242],"decision":[243],"making":[245],"per-model":[249],"audits":[250],"minimum":[252],"standard":[253],"Agent-Skill":[255],"evaluation.":[256]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}