AI deep research powered by CellCog. Market research, competitive analysis, investment research, academic research, due diligence, literature reviews with ci...
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 research-cog或使用 clawhub CLI(需提前安装)
clawhub --dir ~/.claude/skills install research-cog⚠️ 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/research-cog/💡解压后将文件夹放到上方路径,重启 Agent 即可生效
--- name: research-cog description: "Deep multi-source research with citations. Market research, competitive analysis, investment research, academic reviews, due diligence, industry reports, financial analysis, crypto research, data analysis, news monitoring. Use when a task requires thorough investigation or source verification. Outputs: text, PDF, HTML, XLSX. Powered by CellCog." metadata: openclaw: emoji: "🔬" os: [darwin, linux, windows] author: CellCog homepage: https://cellcog.ai dependencies: [cellcog] ---
Deep research with multi-source synthesis and cited evidence — market, competitive, investment, academic, and more.
---
This skill requires the cellcog skill for SDK setup and API calls.
clawhub install cellcog
Read the cellcog skill first for SDK setup. This skill shows you what's possible.
OpenClaw agents (fire-and-forget — recommended for long tasks):
result = client.create_chat(
prompt="[your task prompt]",
notify_session_key="agent:main:main", # OpenClaw only
task_label="my-task",
chat_mode="agent", # See cellcog skill for all modes
)
All other agents (blocks until done):
result = client.create_chat(
prompt="[your task prompt]",
task_label="my-task",
chat_mode="agent",
)
See the cellcog mothership skill for complete SDK API reference — delivery modes, timeouts, file handling, and more.
---
---
---
Citations are NOT automatic — explicitly request them in your prompt if you need source URLs.
---
| Scenario | Recommended Mode | |----------|------------------| | Quick lookups, focused research questions | "agent" | | Deep multi-source synthesis, comprehensive reports | "agent team" |
---
安装 Research Cog 后,可以对 AI 说这些话来触发它
Help me get started with Research Cog
Explains what Research Cog does, walks through the setup, and runs a quick demo based on your current project
Use Research Cog to aI deep research powered by CellCog
Invokes Research Cog with the right parameters and returns the result directly in the conversation
What can I do with Research Cog in my data & analytics workflow?
Lists the top use cases for Research Cog, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/research-cog/ 目录(个人级,所有项目可用),或 .claude/skills/research-cog/(项目级)。重启 AI 客户端后,用 /research-cog 主动调用,或让 AI 根据上下文自动发现并使用。
Research Cog 支持 Claude、Cursor、OpenClaw,可与这些 AI 平台无缝集成,扩展其能力。
Research Cog 可免费安装使用。请查阅仓库了解许可证信息。
AI deep research powered by CellCog. Market research, competitive analysis, investment research, academic research, due diligence, literature reviews with ci...
Research Cog 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 Research Cog
Identifies repetitive steps in your workflow and sets up Research Cog to handle them automatically