← 返回 Skills 市场
Deep Research
作者
Deonte Cooper
· GitHub ↗
· v1.0.0
· MIT-0
144
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install deep-research-ecc
功能描述
Conduct multi-source research with synthesized reports and citations. Searches the web, reads full content from key sources, and produces structured reports....
使用说明 (SKILL.md)
Deep Research
Produce thorough, cited research reports from multiple web sources using search and fetch tools.
When to Activate
- User asks to research any topic in depth
- Competitive analysis, technology evaluation, or market sizing
- Due diligence on companies, investors, or technologies
- User says "research", "deep dive", "investigate", or "what's the current state of"
Quick Start
- Clarify goal — "learning, decision, or writing?"
- Plan 3-5 research sub-questions
- Execute multi-source search using
web_search(15-30 sources total) - Deep-read 3-5 key sources with
web_fetch - Synthesize findings into structured report with citations
Key Concepts
- Multi-source synthesis — Combine data from academic, official, reputable news sources
- Citation discipline — Every claim must have a source; cross-reference critical facts
- Recency focus — Prefer sources from the last 12 months
- Separate fact from inference — Label estimates, projections, and opinions clearly
- Acknowledge gaps — Say "insufficient data found" rather than hallucinate
Common Usage
Most frequent patterns:
- Competitive landscapes and market sizing
- Technology evaluations ("Rust vs Go")
- Business strategy research ("bootstrapping SaaS")
- Current events and trends
- Due diligence on companies or products
References
references/workflow.md— Detailed 6-step workflow with report templatereferences/examples.md— Example research queries and output formats
安全使用建议
This skill appears coherent and low-risk: it only describes web search/fetch and synthesis and asks for no secrets or installs. Before enabling, confirm the agent tools it calls (web_search, web_fetch) are trustworthy and configured to respect privacy (they will make network requests). If you plan to save long reports, verify where files will be written and whether those files may contain sensitive personal data. Finally, be mindful when requesting investigations that involve personal or sensitive information — the skill will gather public web sources, which may include PII or legally sensitive material.
功能分析
Type: OpenClaw Skill
Name: deep-research-ecc
Version: 1.0.0
The skill bundle defines a 'deep-research-agent' designed to conduct multi-source web research and generate cited reports. The instructions in SKILL.md and workflow.md outline a legitimate process for information gathering using standard web_search and web_fetch tools. There is no evidence of malicious intent, data exfiltration, or unauthorized execution; the behavior is entirely consistent with the stated purpose of deep research.
能力评估
Purpose & Capability
Name and description match the runtime instructions: plan sub-questions, run web_search across many sources, deep-read key URLs with web_fetch, and synthesize reports. There are no unrelated binaries, credentials, or config paths requested.
Instruction Scope
Instructions stay within research scope (search, fetch, read, synthesize). They explicitly call web_search and web_fetch (network calls) and recommend saving long reports to a file; the SKILL.md does not instruct reading local system files or accessing secrets. Caveat: actual behavior depends on the agent's implementation of web_search/web_fetch (which perform network access and may have their own permissions/endpoints).
Install Mechanism
No install spec and no code files — instruction-only skill. This minimizes disk-write/installation risk.
Credentials
No environment variables, credentials, or config paths are required. The skill's needs are minimal and proportional to a web-research task.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent or elevated presence. It does not modify other skills or system-wide settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install deep-research-ecc - 安装完成后，直接呼叫该 Skill 的名称或使用
/deep-research-ecc触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release. Multi-source research with synthesized reports and citations. Adapted from everything-claude-code by @affaan-m (MIT)
元数据
常见问题
Deep Research 是什么？
Conduct multi-source research with synthesized reports and citations. Searches the web, reads full content from key sources, and produces structured reports.... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 144 次。
如何安装 Deep Research？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install deep-research-ecc」即可一键安装，无需额外配置。
Deep Research 是免费的吗？
是的，Deep Research 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Deep Research 支持哪些平台？
Deep Research 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（darwin, linux, win32）。
谁开发了 Deep Research？
由 Deonte Cooper（@djc00p）开发并维护，当前版本 v1.0.0。
推荐 Skills