{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.23067", "kind": "paper", "url": "https://arxiv.org/abs/2608.23067v1"}], "authors": ["Ziyue Yang", "Fan Ding"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.23067", "source_url": "https://arxiv.org/abs/2608.23067"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "A benchmark for evaluating agent skills in web development, comparing matched conditions with length-matched controls and ablation studies on 31 skills across 50 projects."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.23067v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.23067v1", "title": "WebDev-Skills-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.23067", "modality": null, "name": "WebDev-Skills-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_webdev-skills-bench_00be1a53", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "646eb177596f2a3465b2aad5c053325940b28b07c5908b4a00d053c1bba819ae", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:18:56.318436Z", "source_url": "https://arxiv.org/abs/2608.23067v1"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.23067", "source_url": "https://arxiv.org/abs/2608.23067v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-23067", "source": "claire_radar", "source_benchmark_id": "2608.23067", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-25T23:36:26.005677Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.23067", "observedAt": "2026-08-24T11:31:30.653116Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-25T23:36:26.005677Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Relevant to coding agents and AI-assisted development, but lack of public benchmarks and data limits early attention.", "score": 35}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:22:25.189955Z", "inputHash": "e17a7a7b0240e4059a6c34ad5c337543bf21da2dd072dd495f2fb2382f994798", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "We introduce WebDev-Skills-Bench and use it for a controlled empirical study", "canonicalNameSource": "abstract", "decisionReason": "Formally named benchmark with a repeatable protocol and public tasks, used to compare models and skill conditions.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark for evaluating agent skills in web development, comparing matched conditions with length-matched controls and ablation studies on 31 skills across 50 projects.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce WebDev-Skills-Bench and use it for a controlled empirical study of 31 public WebDev Skills on 50 Web-Bench projects and 1,000 ordered tasks."}, "familyId": "bmf_4a4dced0ed77", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_webdev-skills-bench_00be1a53", "indexedAt": "2026-08-25T16:21:05.134052Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "http://arxiv.org/abs/2608.23067v1", "pdf": "https://arxiv.org/pdf/2608.23067v1", "project": null, "report": "http://arxiv.org/abs/2608.23067v1"}, "metrics": [], "motivation": "Agent Skills are reusable procedural modules that are increasingly injected into coding-agent sessions to encode framework conventions, anti-patterns, and reusable tools.", "name": "WebDev-Skills-Bench", "oneLine": "A benchmark for evaluating agent skills in web development, comparing matched conditions with length-matched controls and ablation studies on 31 skills across 50 projects.", "paperTitle": "Signal or Noise? A Benchmark Study of Agent Skills in Web Development", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.23067v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-25T16:21:05.134052Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v11", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v11", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Ziyue Yang", "Fan Ding"], "categories": ["cs.CL"], "id": "2608.23067", "title": "Signal or Noise? A Benchmark Study of Agent Skills in Web Development", "type": "arxiv", "url": "http://arxiv.org/abs/2608.23067v1"}, "sourceUpdatedAt": "2026-08-24T10:13:07Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Raises the standard for agent-skill evaluation by incorporating length-matched controls and per-model audits, revealing that skill efficacy varies by model and deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
