{"adoption": {"forks": 612, "observed_at": "2026-08-28T04:09:29.066892+00:00", "stars": 5754}, "canonical_url": "https://ross.abutalabs.com/products/darwin-skill", "card": {"archived": false, "artifact_type": "plugin", "description": "达尔文.skill —— 一个让你的Skill无限进化的系统：评估→改进→测试→保留或回滚 | Autoresearch-inspired autonomous skill optimization for Claude Code. Evaluate, improve, test, keep or revert.", "domain": ["developer-tools", "artificial-intelligence"], "enriched": true, "function": ["agent-framework", "prompt-engineering", "testing", "benchmarking", "workflow-automation"], "health_score": 80, "homepage": null, "language": "HTML", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["alchaincyf/darwin-skill"], "name": "alchaincyf/darwin-skill", "platform": ["cli", "cross-platform"], "pushed_at": "2026-08-25T03:01:10+00:00", "repo": "alchaincyf/darwin-skill", "stars": 5754, "tags": ["claude-code", "agent-skills", "skill-optimization", "autoresearch", "skillopt", "evaluation-loop", "llm-tools", "ai-agents", "automation", "nodejs"], "topics": [], "urls": [], "use_cases": ["automatically improve my claude code skills", "evaluate and score agent skill quality", "optimize skil.md files like training a model", "run regression tests on agent skills before keeping changes", "bulk maintain a large collection of agent skills", "set up an autonomous skill optimization loop", "audit agent skills for failure modes and risky actions"], "what_it_is": "Darwin.skill is an agent skill for Claude Code that autonomously optimizes other SKILL.md agent skills through an evaluate-improve-test-keep-or-revert loop, inspired by Karpathy's autoresearch and aligned with Microsoft Research's SkillOpt validation-gated framework. It scores skills across nine rubric dimensions, uses independent multi-judge review, and enforces human-in-the-loop checkpoints and regression gates so only genuinely improved changes are kept.", "when_to_avoid": ["you don't use Claude Code or any SKILL.md-compatible agent tool", "you need fully autonomous optimization with no human-in-the-loop pauses", "you only have one or two simple skills where manual editing is cheaper"], "when_to_choose": ["you maintain many Claude Code / SKILL.md-format agent skills and need systematic quality improvement", "you want evaluation-gated optimization with human checkpoints rather than fully automatic rewrites", "you want rubric-based scoring of both structure and real-world effectiveness of skills"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/darwin-skill", "repo": "alchaincyf/darwin-skill", "role": "main", "score": 59}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:29.066892+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:53:16.965665+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339e75c4a285b5084ea626f9c95514c8dd218e4133d2c36d07b9517216772bc2", "fetched_at": "2026-08-28T04:09:29.066892+00:00", "kind": "readme", "missing": false, "url": "https://github.com/alchaincyf/darwin-skill"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 10, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 142, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 59, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}