From 5663bab2b8f5d2ad682973dbb18507a338188fb3 Mon Sep 17 00:00:00 2001 From: zlei9 Date: Sun, 29 Mar 2026 13:14:52 +0800 Subject: [PATCH] Initial commit with translated description --- README.md | 108 +++++++++++++++++++++++++++++++++++ SKILL.md | 156 +++++++++++++++++++++++++++++++++++++++++++++++++++ _meta.json | 6 ++ package.json | 9 +++ 4 files changed, 279 insertions(+) create mode 100644 README.md create mode 100644 SKILL.md create mode 100644 _meta.json create mode 100644 package.json diff --git a/README.md b/README.md new file mode 100644 index 0000000..41edd63 --- /dev/null +++ b/README.md @@ -0,0 +1,108 @@ +# Deep Research Pro πŸ”¬ + +A powerful, self-contained deep research skill for [OpenClaw](https://github.com/openclaw/openclaw) / Clawdbot agents. Produces thorough, cited reports from multiple web sources. + +**No API keys required** β€” uses DuckDuckGo search. + +## Features + +- πŸ” Multi-query web + news search +- πŸ“„ Full-page content fetching for deep reads +- πŸ“Š Automatic deduplication across queries +- πŸ“ Structured reports with citations +- πŸ’Ύ Save to file (Markdown or JSON) +- πŸ†“ Completely free β€” no paid APIs + +## Installation + +### Via ClawdHub (coming soon) +```bash +clawdhub install deep-research-pro +``` + +### Manual +```bash +cd your-workspace/skills +git clone https://github.com/parags/deep-research-pro.git +``` + +## Usage + +### As an Agent Skill + +Just ask your agent to research something: +``` +"Research the current state of nuclear fusion energy" +"Deep dive into Rust vs Go for backend services" +"What's happening with the US housing market?" +``` + +The agent will follow the workflow in `SKILL.md` to produce a comprehensive report. + +### CLI Tool + +The `scripts/research` tool can also be used standalone: + +```bash +# Basic multi-query search +./scripts/research "query 1" "query 2" "query 3" + +# Full research mode (web + news + fetch top pages) +./scripts/research --full "AI agents 2026" "monetizing AI skills" + +# Save to file +./scripts/research --full "topic" --output results.md + +# JSON output +./scripts/research "topic" --json + +# Fetch specific URLs +./scripts/research --fetch "https://example.com/article" +``` + +### Options + +| Flag | Description | +|------|-------------| +| `--full` | Enable news search + fetch top 3 pages | +| `--news` | Include news search | +| `--max N` | Max results per query (default 8) | +| `--fetch-top N` | Fetch full text of top N results | +| `--output FILE` | Save results to file | +| `--json` | Output as JSON | + +## How It Works + +1. **Plan** β€” Break topic into 3-5 sub-questions +2. **Search** β€” Run multiple queries across web + news +3. **Deduplicate** β€” Remove duplicate sources +4. **Deep Read** β€” Fetch full content from key sources +5. **Synthesize** β€” Write structured report with citations + +## Report Structure + +```markdown +# Topic: Deep Research Report + +## Executive Summary +## 1. First Major Theme +## 2. Second Major Theme +## Key Takeaways +## Sources (with links) +## Methodology +``` + +## Requirements + +- Python 3.11+ +- [uv](https://github.com/astral-sh/uv) (auto-installs dependencies) + +The script is self-contained β€” dependencies install automatically on first run. + +## License + +MIT + +## Author + +Built by [AstralSage](https://moltbook.com/u/AstralSage) 🦞 diff --git a/SKILL.md b/SKILL.md new file mode 100644 index 0000000..5aa12dc --- /dev/null +++ b/SKILL.md @@ -0,0 +1,156 @@ +--- +name: deep-research-pro +version: 1.0.0 +description: "ε€šζΊζ·±εΊ¦η ”η©Άδ»£η†γ€‚" +homepage: https://github.com/paragshah/deep-research-pro +metadata: {"clawdbot":{"emoji":"πŸ”¬","category":"research"}} +--- + +# Deep Research Pro πŸ”¬ + +A powerful, self-contained deep research skill that produces thorough, cited reports from multiple web sources. No paid APIs required β€” uses DuckDuckGo search. + +## How It Works + +When the user asks for research on any topic, follow this workflow: + +### Step 1: Understand the Goal (30 seconds) + +Ask 1-2 quick clarifying questions: +- "What's your goal β€” learning, making a decision, or writing something?" +- "Any specific angle or depth you want?" + +If the user says "just research it" β€” skip ahead with reasonable defaults. + +### Step 2: Plan the Research (think before searching) + +Break the topic into 3-5 research sub-questions. For example: +- Topic: "Impact of AI on healthcare" + - What are the main AI applications in healthcare today? + - What clinical outcomes have been measured? + - What are the regulatory challenges? + - What companies are leading this space? + - What's the market size and growth trajectory? + +### Step 3: Execute Multi-Source Search + +For EACH sub-question, run the DDG search script: + +```bash +# Web search +/home/clawdbot/clawd/skills/ddg-search/scripts/ddg "" --max 8 + +# News search (for current events) +/home/clawdbot/clawd/skills/ddg-search/scripts/ddg news "" --max 5 +``` + +**Search strategy:** +- Use 2-3 different keyword variations per sub-question +- Mix web + news searches +- Aim for 15-30 unique sources total +- Prioritize: academic, official, reputable news > blogs > forums + +### Step 4: Deep-Read Key Sources + +For the most promising URLs, fetch full content: + +```bash +curl -sL "" | 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. + +### Step 5: Synthesize & Write Report + +Structure the report as: + +```markdown +# [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) β€” [one-line summary] +2. ... + +## Methodology +Searched [N] queries across web and news. Analyzed [M] sources. +Sub-questions investigated: [list] +``` + +### Step 6: Save & Deliver + +Save the full report: +```bash +mkdir -p ~/clawd/research/[slug] +# Write report to ~/clawd/research/[slug]/report.md +``` + +Then deliver: +- **Short topics**: Post the full report in chat +- **Long reports**: Post the executive summary + key takeaways, offer full report as file + +## Quality Rules + +1. **Every claim needs a source.** No unsourced assertions. +2. **Cross-reference.** If only one source says it, flag it as unverified. +3. **Recency matters.** Prefer sources from the last 12 months. +4. **Acknowledge gaps.** If you couldn't find good info on a sub-question, say so. +5. **No hallucination.** If you don't know, say "insufficient data found." + +## Examples + +``` +"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?" +``` + +## For Sub-Agent Usage + +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" +) +``` + +## Requirements + +- DDG search script: `/home/clawdbot/clawd/skills/ddg-search/scripts/ddg` +- curl (for fetching full pages) +- No API keys needed! diff --git a/_meta.json b/_meta.json new file mode 100644 index 0000000..e86a794 --- /dev/null +++ b/_meta.json @@ -0,0 +1,6 @@ +{ + "ownerId": "kn7aeqfsshm3b3ywbcttf6749h80e4pp", + "slug": "deep-research-pro", + "version": "1.0.2", + "publishedAt": 1770303332827 +} \ No newline at end of file diff --git a/package.json b/package.json new file mode 100644 index 0000000..2912287 --- /dev/null +++ b/package.json @@ -0,0 +1,9 @@ +{ + "name": "deep-research-pro", + "version": "1.0.0", + "description": "Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.", + "keywords": ["research", "search", "analysis", "citations", "reports", "duckduckgo"], + "license": "MIT", + "author": "AstralSage", + "files": ["SKILL.md", "scripts/research", "package.json"] +}