Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →staruhub/keqian-method
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）。
Passed 21 of 22 test cases with the skill, and 10 of 22 without it.
and 13 more in the full report
11 fixed10 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
During long coding sessions, our LLM agents start failing subtly or ignoring constraints after extended turns. The developer wants to let the context grow to 95% capacity before taking action. At what context threshold should we trigger maintenance, and what operation should be performed?
| Checked | Without skill | With skill |
|---|---|---|
| Triggers context maintenance when session length reaches 0.4 to 0.5 of the maximum context window. | Missed | Passed |
| Prescribes running a compact operation to maintain agent intelligence. | Passed | Passed |
The instructions your model reads when the skill loads.
核心理念：产品人思维 × 极致单Agent × 文档驱动 × 质量门禁闭环
来源：胥克谦——从音乐教师到产品经理到AI-Native连续创业者，皮影客创始人， 十几万行自建skill和脚本的harness工程实践者。
概率乘是第一性原理。
每个环节的成功率相乘决定最终质量。即使每次0.99，n=51后也不及格。 因此：不追求一次完美，追求每个环节可验证、可修复、可迭代。
推论：
不盲目使用multi-agent。单agent做到极致，再考虑编排。
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.