重要前提
安装AI Skills的关键前提是:必须科学上网,且开启TUN模式,这一点至关重要,直接决定安装能否顺利完成,在此郑重提醒三遍:科学上网,科学上网,科学上网。查看完整安装教程 →
deep-research-pro by parags/deep-research-pro
npx skills add https://github.com/parags/deep-research-pro --skill deep-research-pro一个功能强大、自包含的深度研究技能,可从多个网络来源生成详尽且附有引用的报告。无需付费 API —— 使用 DuckDuckGo 搜索。
当用户要求研究任何主题时,请遵循以下工作流程:
提出 1-2 个快速的澄清性问题:
如果用户说“直接研究就行”——则使用合理的默认值跳过此步骤。
将主题分解为 3-5 个研究子问题。例如:
针对每个子问题,运行 DDG 搜索脚本:
# Web search
/home/clawdbot/clawd/skills/ddg-search/scripts/ddg "<sub-question keywords>" --max 8
# News search (for current events)
/home/clawdbot/clawd/skills/ddg-search/scripts/ddg news "<topic>" --max 5
搜索策略:
对于最有希望的 URL,获取完整内容:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
curl -sL "<url>" | python3 -c "
import sys, re
html = sys.stdin.read()
# Strip tags, get text
text = re.sub('<[^>]+>', ' ', html)
text = re.sub(r'\s+', ' ', text).strip()
print(text[:5000])
"
完整阅读 3-5 个关键来源以获取深度信息。不要仅仅依赖搜索摘要。
按以下结构组织报告:
# [Topic]: Deep Research Report
*Generated: [date] | Sources: [N] | Confidence: [High/Medium/Low]*
## Executive Summary
[3-5 sentence overview of key findings]
## 1. [First Major Theme]
[Findings with inline citations]
- Key point ([Source Name](url))
- Supporting data ([Source Name](url))
## 2. [Second Major Theme]
...
## 3. [Third Major Theme]
...
## Key Takeaways
- [Actionable insight 1]
- [Actionable insight 2]
- [Actionable insight 3]
## Sources
1. [Title](url) — [one-line summary]
2. ...
## Methodology
Searched [N] queries across web and news. Analyzed [M] sources.
Sub-questions investigated: [list]
保存完整报告:
mkdir -p ~/clawd/research/[slug]
# Write report to ~/clawd/research/[slug]/report.md
然后交付:
"Research the current state of nuclear fusion energy"
"Deep dive into Rust vs Go for backend services in 2026"
"Research the best strategies for bootstrapping a SaaS business"
"What's happening with the US housing market right now?"
当作为子代理启动时,请包含完整的研究请求和上下文:
sessions_spawn(
task: "Run deep research on [TOPIC]. Follow the deep-research-pro SKILL.md workflow.
Read /home/clawdbot/clawd/skills/deep-research-pro/SKILL.md first.
Goal: [user's goal]
Specific angles: [any specifics]
Save report to ~/clawd/research/[slug]/report.md
When done, wake the main session with key findings.",
label: "research-[slug]",
model: "opus"
)
/home/clawdbot/clawd/skills/ddg-search/scripts/ddg每周安装次数
180
仓库
首次出现
2026 年 2 月 25 日
安全审计
安装于
cursor176
codex176
opencode176
gemini-cli175
amp175
github-copilot175
A powerful, self-contained deep research skill that produces thorough, cited reports from multiple web sources. No paid APIs required — uses DuckDuckGo search.
When the user asks for research on any topic, follow this workflow:
Ask 1-2 quick clarifying questions:
If the user says "just research it" — skip ahead with reasonable defaults.
Break the topic into 3-5 research sub-questions. For example:
For EACH sub-question, run the DDG search script:
# Web search
/home/clawdbot/clawd/skills/ddg-search/scripts/ddg "<sub-question keywords>" --max 8
# News search (for current events)
/home/clawdbot/clawd/skills/ddg-search/scripts/ddg news "<topic>" --max 5
Search strategy:
For the most promising URLs, fetch full content:
curl -sL "<url>" | python3 -c "
import sys, re
html = sys.stdin.read()
# Strip tags, get text
text = re.sub('<[^>]+>', ' ', html)
text = re.sub(r'\s+', ' ', text).strip()
print(text[:5000])
"
Read 3-5 key sources in full for depth. Don't just rely on search snippets.
Structure the report as:
# [Topic]: Deep Research Report
*Generated: [date] | Sources: [N] | Confidence: [High/Medium/Low]*
## Executive Summary
[3-5 sentence overview of key findings]
## 1. [First Major Theme]
[Findings with inline citations]
- Key point ([Source Name](url))
- Supporting data ([Source Name](url))
## 2. [Second Major Theme]
...
## 3. [Third Major Theme]
...
## Key Takeaways
- [Actionable insight 1]
- [Actionable insight 2]
- [Actionable insight 3]
## Sources
1. [Title](url) — [one-line summary]
2. ...
## Methodology
Searched [N] queries across web and news. Analyzed [M] sources.
Sub-questions investigated: [list]
Save the full report:
mkdir -p ~/clawd/research/[slug]
# Write report to ~/clawd/research/[slug]/report.md
Then deliver:
"Research the current state of nuclear fusion energy"
"Deep dive into Rust vs Go for backend services in 2026"
"Research the best strategies for bootstrapping a SaaS business"
"What's happening with the US housing market right now?"
When spawning as a sub-agent, include the full research request and context:
sessions_spawn(
task: "Run deep research on [TOPIC]. Follow the deep-research-pro SKILL.md workflow.
Read /home/clawdbot/clawd/skills/deep-research-pro/SKILL.md first.
Goal: [user's goal]
Specific angles: [any specifics]
Save report to ~/clawd/research/[slug]/report.md
When done, wake the main session with key findings.",
label: "research-[slug]",
model: "opus"
)
/home/clawdbot/clawd/skills/ddg-search/scripts/ddgWeekly Installs
180
Repository
First Seen
Feb 25, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
cursor176
codex176
opencode176
gemini-cli175
amp175
github-copilot175
超能力技能使用指南:AI助手技能调用优先级与工作流程详解
55,300 周安装
MCP向量搜索工作流:使用mcp-vector-search索引代码库,实现语义搜索与AI集成
98 周安装
沟通叙事技巧:如何将复杂数据转化为清晰故事,提升说服力与影响力
99 周安装
Gemini 3 Pro Image API 图像生成教程 - Nano Banana Pro 快速上手指南
102 周安装
YouTube数据分析技能 - 使用YouTube API v3进行频道分析、视频表现评估与SEO优化
102 周安装
AI代码重构助手 | 自动审查TypeScript/JavaScript代码质量,优化设计模式与规范
102 周安装
tuzi-infographic 信息图生成器:21种布局×20种风格,AI驱动一键生成专业图表
107 周安装