Skip to content

staruhub/ClaudeSkills / skills/Geek-skills-deep-research

deep-research

Verified

Use this skill when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a clear conclusion. Best for tasks that need synthesis across multiple external sources, iterative follow-up research, or a reusable written artifact. Do not use for quick factual lookups, single-source summaries, simple Q&A, summarizing one document the user already provided, plan-only requests where the user explicitly defers the actual research, or when the user wants a short answer with no need for cited evidence (a short but evidence-backed conclusion is still a brief memo, which this skill covers). Chinese trigger examples: "帮我调研", "深度研究", "综述报告", "技术选型分析", "竞品研究", "政策分析".

evals/routing-evals.json

View on GitHub
[
  {
    "id": "rt-01",
    "prompt": "帮我调研一下 MCP 在企业里落地的主要安全风险,给我一个带引用的决策 brief。",
    "should_trigger": true,
    "reason": "multi-source decision brief"
  },
  {
    "id": "rt-02",
    "prompt": "做一份关于 RAG 评估方法的综述报告,要有来源、有局限性。",
    "should_trigger": true,
    "reason": "literature-style research artifact"
  },
  {
    "id": "rt-03",
    "prompt": "继续上一轮,把支付风控方案再深挖一轮,重点看失败模式。",
    "should_trigger": true,
    "reason": "delta / progressive research"
  },
  {
    "id": "rt-04",
    "prompt": "比较 OpenAI 和 Anthropic 在 agent skills 上的思路,输出 1500 字带引用分析。",
    "should_trigger": true,
    "reason": "comparative multi-source memo"
  },
  {
    "id": "rt-05",
    "prompt": "帮我做个竞品研究:对比 5 家客服 AI 厂商的定位、能力、局限。",
    "should_trigger": true,
    "reason": "competitive research"
  },
  {
    "id": "rt-06",
    "prompt": "MCP 是什么?一句话说清楚。",
    "should_trigger": false,
    "reason": "quick definition"
  },
  {
    "id": "rt-07",
    "prompt": "把这篇文章总结成 5 句话。",
    "should_trigger": false,
    "reason": "single-source summary"
  },
  {
    "id": "rt-08",
    "prompt": "给我一个关于 WebRTC 的简短解释,不用查资料。",
    "should_trigger": false,
    "reason": "user explicitly wants short non-research answer"
  },
  {
    "id": "rt-09",
    "prompt": "列一下 Stripe 的主要产品。",
    "should_trigger": false,
    "reason": "simple lookup"
  },
  {
    "id": "rt-10",
    "prompt": "帮我写一个研究计划,先别开始调研。",
    "should_trigger": false,
    "reason": "planning-only, no research execution yet"
  },
  {
    "id": "rt-11",
    "prompt": "深度研究一下 AI browser use 的真实落地边界,别只讲 demo。",
    "should_trigger": true,
    "reason": "contested evidence-based research"
  },
  {
    "id": "rt-12",
    "prompt": "帮我快速比较一下 Supabase 和 Firebase,用 6 句话以内。",
    "should_trigger": false,
    "reason": "brief direct comparison better handled without deep research"
  },
  {
    "id": "rt-13",
    "prompt": "对比一下主流向量数据库的选型,给个有依据的简短结论就行,不用写长报告。",
    "should_trigger": true,
    "expected_mode": "brief",
    "reason": "needs multi-source evidence but explicitly short -> brief memo"
  },
  {
    "id": "rt-14",
    "prompt": "写一份 AI 编程工具市场的完整综述报告,要有文献级引用、局限性和决策建议。",
    "should_trigger": true,
    "expected_mode": "full",
    "reason": "comprehensive literature-style request -> full report"
  },
  {
    "id": "rt-15",
    "prompt": "接着上次的 MCP 安全调研再补一轮,只看最近三个月的新漏洞和防护实践。",
    "should_trigger": true,
    "expected_mode": "delta",
    "reason": "continuation of a prior round -> delta update"
  },
  {
    "id": "rt-16",
    "prompt": "帮我写一篇介绍 RAG 技术的公众号文章。",
    "should_trigger": false,
    "route_to": "wechat-article-writer",
    "reason": "content creation task; belongs to wechat-article-writer"
  },
  {
    "id": "rt-17",
    "prompt": "把上次的调研结论做成一组信息图。",
    "should_trigger": false,
    "route_to": "deck-studio",
    "reason": "visualization of existing findings; belongs to deck-studio"
  },
  {
    "id": "rt-18",
    "prompt": "分析一下低空经济这个赛道值不值得进,要有依据,也要有反面证据。",
    "should_trigger": true,
    "expected_mode": "brief",
    "reason": "says 分析 but requires multi-source evidence and counter-evidence"
  }
]
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