Skip to content

staruhub/ClaudeSkills / skills/Geek-skills-xuefeng-method

xuefeng-method

Verified

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。

evals/routing-evals.json

View on GitHub
[
  {
    "id": "xf-01",
    "prompt": "我在做一个 AI 日历助手,用户想怎么说就怎么说,行为根本没法穷举,怎么开发?",
    "should_trigger": true,
    "reason": "open-behavior AI-native product, canonical case"
  },
  {
    "id": "xf-02",
    "prompt": "多个 agent 怎么分工?不同环节想用不同的模型来路由。",
    "should_trigger": true,
    "reason": "multi-agent split + model routing keywords"
  },
  {
    "id": "xf-03",
    "prompt": "我们的 AI 助手上线之后回答越来越怪,怎么系统性地发现和纠正这种变化?",
    "should_trigger": true,
    "reason": "场景触发:模型漂移与校准,未出现 description 中的任何关键词"
  },
  {
    "id": "xf-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": true,
    "reason": "镜像 kq-04:开放行为产品归本 skill"
  },
  {
    "id": "xf-05",
    "prompt": "我要做一个发票 OCR 归档工具,流程完全固定,AI 只负责识别这一步。",
    "should_trigger": false,
    "route_to": "keqian-method",
    "reason": "+AI 场景依赖型:行为可枚举,第零步规则应转 keqian"
  },
  {
    "id": "xf-06",
    "prompt": "帮我选个便宜的大模型 API,我写个爬虫玩玩。",
    "should_trigger": false,
    "route_to": "none",
    "reason": "关键词陷阱:出现'选模型'但只是一次性工具咨询,无产品方法论需求"
  },
  {
    "id": "xf-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,镜像 kq-07。第零步规则:两者结合、按模块选用,开放兜底模块由本 skill 负责"
  }
]
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