{"adoption": {"forks": 364, "observed_at": "2026-08-28T04:05:28.095091+00:00", "stars": 1725}, "canonical_url": "https://ross.abutalabs.com/products/skillsbench", "card": {"archived": false, "artifact_type": "dataset", "description": "SkillsBench evaluates how well skills work and how effective agents are at using them.", "domain": ["artificial-intelligence", "large-language-models", "developer-tools", "tutorials"], "enriched": true, "function": ["benchmarking", "agent-framework", "testing"], "health_score": 95, "homepage": "https://www.skillsbench.ai", "language": "PDDL", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["benchflow-ai/skillsbench"], "name": "benchflow-ai/skillsbench", "platform": ["python", "cli", "cloud"], "pushed_at": "2026-07-23T19:09:35+00:00", "repo": "benchflow-ai/skillsbench", "stars": 1725, "tags": ["agent-skills", "benchmark", "llm-evaluation", "skill-composition", "sandboxed-tasks", "leaderboard", "benchflow", "evaluation", "ai-agents", "docker"], "topics": ["benchmark", "skillsbench"], "urls": [], "use_cases": ["benchmark how well AI agents use skills", "compare LLM performance with and without skills", "evaluate agent skill composition across tasks", "measure agent resolution rate and wall-clock efficiency", "create and contribute agent evaluation tasks", "run reproducible agent evaluations in cloud sandboxes"], "what_it_is": "SkillsBench is the first benchmark for evaluating how effectively AI agents use skills—modular folders of instructions, scripts, and resources—across expert-curated professional tasks. It provides sandboxed task packages with oracle solutions and outcome-based verifiers, runnable via the BenchFlow CLI on Modal or Docker.", "when_to_avoid": ["you need a general-purpose agent framework for building products rather than evaluation", "you want a simple unit-testing tool for code", "you cannot use Modal or Docker sandbox execution", "you need benchmarking of non-agent software performance"], "when_to_choose": ["you need to measure how effectively agents leverage skills on specialized workflows", "you want to compare frontier models on skill-using agent tasks", "you need a gym-style evaluation harness with oracle sanity checks and verifiers", "you want to contribute or curate benchmark tasks for agent skills"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/skillsbench", "repo": "benchflow-ai/skillsbench", "role": "main", "score": 76}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:28.095091+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:32:34.895333+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e4444821f0a73857d84d35b0e6b081465755aa3f45b03d37c3bea9ac868db22", "fetched_at": "2026-08-28T04:05:28.095091+00:00", "kind": "readme", "missing": false, "url": "https://github.com/benchflow-ai/skillsbench"}, {"content_hash": "efc21c281b6b1656970e0d63627fc3a9e04ea39b92f1ac159ec8fa026ecd64cd", "fetched_at": "2026-08-29T11:09:09.799238+00:00", "kind": "homepage", "missing": false, "url": "https://www.skillsbench.ai"}, {"content_hash": "e477c5e677d9cb3413b7c17e5fcddd081b8166f724ec5dc6913def67a6a27c56", "fetched_at": "2026-08-29T11:09:09.808806+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs/getting-started"}, {"content_hash": "2ac6d9bc8be677d65de981b3abdc412d4278b951e892da2933a0db14ec18959a", "fetched_at": "2026-08-29T11:09:09.810860+00:00", "kind": "site_page", "missing": false, "url": "https://www.skillsbench.ai/docs"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 94, "longevity": 17, "rhythm": 88}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 247, "days_push": 41, "days_rel": 80, "gap_med": 2, "n_releases_24m": 2}, "score": 76, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}