Skip to content

staruhub/ClaudeSkills / skills/Geek-skills-keqian-method

keqian-method

Verified

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)。

FileKindSize
SKILL.mdskill md8.8 KB
evals/routing-evals.jsonconfig1.8 KB
references/eval-patterns.mdmarkdown4.0 KB
references/sdd-framework.mdmarkdown2.7 KB

evals/routing-evals.json

View on GitHub
[
  {
    "id": "kq-01",
    "prompt": "我要做一个记账 App,功能明确,帮我按规范流程从需求推到实现。",
    "should_trigger": true,
    "reason": "closed-behavior product with enumerable flows, SDD fits"
  },
  {
    "id": "kq-02",
    "prompt": "这个项目要过质量门禁,单 agent 一步步来,别并行。",
    "should_trigger": true,
    "reason": "quality-gate + single-agent trigger keywords"
  },
  {
    "id": "kq-03",
    "prompt": "带我用 AI 把这个 CRUD 后台从需求文档一路写到测试全部通过。",
    "should_trigger": true,
    "reason": "场景触发:确定性交付流程,未出现 description 中的任何关键词"
  },
  {
    "id": "kq-04",
    "prompt": "我想做一个行为开放的 AI 陪聊产品,模型说了算,怎么设计?",
    "should_trigger": false,
    "route_to": "xuefeng-method",
    "reason": "open-behavior model-driven product; 已知失败风险:keqian description 缺少反向负触发声明"
  },
  {
    "id": "kq-05",
    "prompt": "帮我评审这份 PRD 的需求优先级排得对不对。",
    "should_trigger": false,
    "route_to": "product-manager",
    "reason": "PRD review is product management, not dev methodology"
  },
  {
    "id": "kq-06",
    "prompt": "修一下这个函数里的空指针 bug。",
    "should_trigger": false,
    "route_to": "none",
    "reason": "single fix, no methodology overhead needed"
  },
  {
    "id": "kq-07",
    "prompt": "做一个客服机器人,大部分流程固定,但兜底要靠模型自由发挥。",
    "should_trigger": true,
    "boundary": true,
    "reason": "混合型产品。xuefeng 第零步规则:混合型=两者结合、按模块选用,所以本例双侧都可触发(镜像 xf-07),由确定性主流程侧主导"
  }
]
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall