Conduct exhaustive multi-source investigation with methodology tracking, source evaluation, and iterative depth.
数据来源:ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一:命令行安装(推荐)
推荐(无需提前安装 clawhub)
npx clawhub@latest --dir ~/.claude/skills install in-depth-research或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install in-depth-research⚠️ 需要 Node.js 18+,没有 Node?请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二:手动下载安装(无需 Node)
下载 ZIP,解压后将文件夹放到以下路径,重启 Agent 即可:
安装路径
~/.claude/skills/in-depth-research/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: "Deep Research" description: "Conduct exhaustive multi-source investigation with methodology tracking, source evaluation, and iterative depth." ---
Deep Research = investigate thoroughly until the question is answered. Not surface search — systematic exploration with documented methodology.
Not: quick lookups (→ just search), combining existing docs (→ Synthesize), ongoing monitoring (→ Digest)
Scope → Search → Evaluate → Deepen → Synthesize → Document → Deliver
Before searching, clarify:
Reframe vague questions into specific, answerable queries.
Multi-vector approach (see methodology.md):
Track every source. Nothing unattributed.
For each source (see sources.md):
Flag low-credibility sources. Weight findings accordingly.
Research is iterative:
Document decision to stop and why.
Merge findings (use Synthesize skill patterns):
Research trail matters:
Format per user needs (see output-formats.md):
🔬 DEEP RESEARCH: [Topic]
⚡ ANSWER
[Direct answer to the question — 2-3 sentences]
📊 CONFIDENCE: [High/Medium/Low] — [why]
🔍 KEY FINDINGS
• [Finding 1] — [source]
• [Finding 2] — [source]
• [Finding 3] — [source]
⚠️ CAVEATS
• [Important limitation or uncertainty]
🕳️ GAPS
• [What couldn't be determined]
📚 SOURCES ([count])
[Numbered list with credibility notes]
🔎 METHODOLOGY
[Brief: what was searched, how sources were evaluated]
| Level | Effort | Sources | When | |-------|--------|---------|------| | Quick | 5-10 min | 3-5 | Simple factual questions | | Standard | 30-60 min | 8-15 | Most research requests | | Thorough | 2-4 hours | 20-30 | Important decisions | | Exhaustive | Days | 50+ | Critical, high-stakes |
Confirm depth before starting. Adjust if findings warrant.
---
References: methodology.md, sources.md, output-formats.md
安装 Deep Research 后,可以对 AI 说这些话来触发它
Help me get started with Deep Research
Explains what Deep Research does, walks through the setup, and runs a quick demo based on your current project
Use Deep Research to conduct exhaustive multi-source investigation with methodology trac...
Invokes Deep Research with the right parameters and returns the result directly in the conversation
What can I do with Deep Research in my data & analytics workflow?
Lists the top use cases for Deep Research, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/in-depth-research/ 目录(个人级,所有项目可用),或 .claude/skills/in-depth-research/(项目级)。重启 AI 客户端后,用 /in-depth-research 主动调用,或让 AI 根据上下文自动发现并使用。
Deep Research 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Deep Research 可免费安装使用。请查阅仓库了解许可证信息。
Conduct exhaustive multi-source investigation with methodology tracking, source evaluation, and iterative depth.
Deep Research 属于「Data & Analytics」分类,该分类的技能帮助 AI 智能体在此领域执行专业任务。
Automate my data & analytics tasks using Deep Research
Identifies repetitive steps in your workflow and sets up Deep Research to handle them automatically