{"paper":{"title":"SkillCT: A Multidimensional Benchmark and Execution-Free Baseline for Agent Skill Assessment","arxiv_id":"2610.38147","primary_cat":"cs.AI","submitted_at":"2026-10-28T01:30:12+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Agent skills package instructions, scripts, and resources for specialized tasks and are increasingly distributed through public Web repositories.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.01,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.96,"id":"s1","own":false,"role":"gap","text":"However, existing skill benchmarks primarily focus on downstream task execution, insufficiently assessing specification quality, behavioral robustness, semantic alignment, and responsibility boundaries.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.07,"main_claim_p":0.03,"quantitative":false,"quantitative_p":0.27,"role_probabilities":{"gap":0.96,"method":0.0,"result":0.0,"background":0.04,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.69,"id":"s2","own":false,"role":"gap","text":"Their reliance on task-specific tools, environments, and repeated executions limits scalability and pre-deployment assessment.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.05,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.1,"role_probabilities":{"gap":0.69,"method":0.0,"result":0.0,"background":0.28,"limitation":0.03,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":3,"p":1.0,"id":"s3","own":true,"role":"contribution","text":"To address these challenges, we introduce SkillCT, a benchmark that broadens skill assessment from downstream utility to a multidimensional characterization of skill quality.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.88,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.11,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":1.0,"interpretation":0.0}},{"i":4,"p":0.72,"id":"s4","own":true,"role":"method","text":"SkillCT evaluates skills across nine complementary dimensions spanning three aspects: Static Assessment, which captures intrinsic properties of the skill specification; Dynamic Assessment, which measures whether the induced behavior remains stable across backbone models and request variations; and Human-Assisted Assessment, which examines behavior-chain consistency and task granularity.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.9,"main_claim_p":0.08,"quantitative":true,"quantitative_p":0.96,"role_probabilities":{"gap":0.0,"method":0.72,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.28,"interpretation":0.0}},{"i":5,"p":0.74,"id":"s5","own":false,"role":"interpretation","text":"These dimensions provide a broader view of skill quality than execution success.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.43,"main_claim_p":0.1,"quantitative":true,"quantitative_p":0.72,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.02,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.22,"interpretation":0.74}},{"i":6,"p":0.67,"id":"s6","own":true,"role":"contribution","text":"Applying SkillCT to a public skill corpus establishes a reference benchmark for analyzing quality weaknesses and relationships across dimensions.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.92,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.17,"result":0.15,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.67,"interpretation":0.01}},{"i":7,"p":0.52,"id":"s7","own":true,"role":"contribution","text":"Building on this benchmark, we propose an execution-free quality evaluation baseline that predicts the multidimensional quality profiles of unseen skills by retrieving and leveraging similar reference skills, without executing the skills under evaluation.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.07,"role_probabilities":{"gap":0.0,"method":0.48,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.52,"interpretation":0.0}},{"i":8,"p":0.68,"id":"s8","own":true,"role":"result","text":"This reduces token consumption and evaluation time, while preserving consistency with the full assessment.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.79,"main_claim_p":0.07,"quantitative":false,"quantitative_p":0.42,"role_probabilities":{"gap":0.0,"method":0.05,"result":0.68,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.06,"interpretation":0.21}},{"i":9,"p":0.92,"id":"s9","own":true,"role":"result","text":"Furthermore, SkillCT-guided optimization improves downstream task success and execution efficiency, demonstrating its value for skill refinement.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.93,"main_claim_p":0.19,"quantitative":false,"quantitative_p":0.2,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.92,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.07}},{"i":10,"p":0.99,"id":"s10","own":true,"role":"interpretation","text":"These findings highlight the effectiveness of SkillCT in supporting scalable skill assessment, optimization, and repository maintenance.","hedge":{"p":0.97,"label":"asserted"},"own_p":0.86,"main_claim_p":0.7,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.99}}]},"compiled":{"main_claim":{"p":1.0,"text":"These findings highlight the effectiveness of SkillCT in supporting scalable skill assessment, optimization, and repository maintenance.","location":"abstract s10","hedge_strength":{"p":0.97,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":8143,"cost_usd_reported":0.0},"compiled_at":"2026-10-30","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.09,"states_limitation":0.14,"human_participants":0.24,"controlled_comparison":0.4,"randomized_assignment":0.01,"states_quantitative_result":0.18,"compares_with_prior_results":0.7,"mentions_code_or_data_availability":0.1},"evidential_basis":{"p":0.6,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.36,"observation_or_experiment":0.6,"simulation_or_computation":0.04}},"contribution_type":{"p":0.99,"value":"dataset or benchmark","probabilities":{"review":0.0,"method_or_tool":0.01,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.99,"position_or_commentary":0.0}},"contribution_statement":{"p":0.96,"text":"To address these challenges, we introduce SkillCT, a benchmark that broadens skill assessment from downstream utility to a multidimensional characterization of skill quality.","location":"abstract s3"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":11,"sentences_in_abstract":11},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}