{"slug":"staruhub-keqian-method","source_name":"staruhub/keqian-method","name":"Staruhub/Keqian Method","description":"胥克谦式AI-Native产品开发方法论。适用于：(1) 使用AI Agent（Claude Code、Codex、Cursor等）进行产品级软件开发，(2) 设计和优化Harness/Skill体系，(3) 文档驱动开发(SDD)流程，(4) 构建自动化质量门禁和eval机制，(5) Token成本优化与缓存策略，(6) 产品人转型开发者的AI编程实践。触发场景包括\"帮我设计开发流程\"、\"怎么降低token成本\"、\"怎么提高AI编码质量\"、\"文档驱动\"、\"质量门禁\"、\"harness设计\"、\"单agent vs multi-agent\"、\"自动化迭代\"、\"AI产品开发\"、\"SDD\"、\"eval机制\"等。即使用户只是说\"帮我用AI写代码\"或\"怎么让agent干活更靠谱\"也应触发。注意：如果产品是行为开放、用户输入不可穷举的AI-native类型，请改用 xuefeng-method skill。不用于：单个bug修复或小改动（无需方法论）、PRD需求文档写作（用product-manager）。","version":1,"lift":{"pass_rate_delta_pts":50,"pass_rate_pct":95.5,"total_cases":22,"passed_cases":21,"tokens_delta_pct":61.9,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-18T08:56:34.048134+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":50,"with_pass_pct":95.5,"without_pass_pct":45.5,"tokens_delta_pct":61.9,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-18T08:56:34.048134+00:00","run_id":"c0ad82ec-a5b7-4f91-8f61-6981972157e9","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"d514449b2d985c476ae0b91653e866f195453f2164dea67eb0019685502b7e51","raw_url":"https://app.decimal.ai/s/staruhub-keqian-method/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/staruhub-keqian-method"}