{"slug":"staruhub-xuefeng-method","source_name":"staruhub/xuefeng-method","name":"Staruhub/Xuefeng Method","description":"雪峰式AI-Native产品开发方法论。适用于：(1) 用户行为开放、不可穷举的AI-native产品（AI日历、AI助手、AI推荐、对话式产品等），(2) 强模型依赖型场景，AI驱动核心决策而非仅辅助，(3) 多专精Agent架构设计与分工，(4) 上线后快速校准、行为审计与漂移检测，(5) 模型选择和智能路由策略，(6) 概率性输出的质量评估。触发场景包括\"AI-native产品怎么做\"、\"用户行为不可预测怎么办\"、\"多agent怎么分工\"、\"模型漂移怎么处理\"、\"校准到95%太难了\"、\"唯快不破\"、\"怎么选模型\"、\"agent并行分工\"、\"AI产品上线后怎么迭代\"。注意：如果产品是场景明确、边界可定义的+AI类型，请改用 keqian-method skill。即使用户没有明确说\"AI-native\"，但在讨论AI驱动决策、用户行为不可预测、概率性输出等话题时也应触发。","version":1,"lift":{"pass_rate_delta_pts":31.82,"pass_rate_pct":86.4,"total_cases":22,"passed_cases":19,"tokens_delta_pct":80.5,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-18T09:30:41.262651+00:00"},"skill_score":null,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":31.82,"with_pass_pct":86.4,"without_pass_pct":54.5,"tokens_delta_pct":80.5,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":false,"completed_at":"2026-08-18T09:30:41.262651+00:00","run_id":"30d23b01-4d23-4132-a928-740647b4d6b1","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":"2acc8781220c956e78a69f6edb3496127ae63df7929445c77d4770c36b5c0594","raw_url":"https://app.decimal.ai/s/staruhub-xuefeng-method/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/staruhub-xuefeng-method"}