Conduct deep research and generate structured reports.
Gather data from diverse sources:
# Web search (DuckDuckGo)
curl -s "https://api.duckduckgo.com/?q=QUERY&format=json" | jq '.RelatedTopics[:5]'
# GitHub (repos, stars, activity)
gh search repos "TOPIC" --limit 20 --json name,description,stargazersCount,url
# News/Tech (Hacker News, TechCrunch)
curl -s "https://hacker-news.firebaseio.com/v0/topstories.json" | jq '.[:10]'
# NPM packages
npm search PACKAGE --json 2>/dev/null | jq '.[0:5]'
Use the standard report structure from references/report-template.md.
Every research report follows this format:
# [Topic] Research Report
**Date:** YYYY-MM-DD
**Researcher:** Clawie (AI Research Agent)
**Sources:** X sources analyzed
---
## Executive Summary
[2-3 paragraph overview with key findings]
## Key Findings
### Finding 1: [Title]
[Evidence, data, sources]
### Finding 2: [Title]
[Evidence, data, sources]
## Market/Technology Landscape
[Competitors, alternatives, ecosystem]
## Trends & Predictions
[Where things are heading]
## Gaps & Opportunities
[What's missing, underserved areas]
## Recommendations
[Actionable next steps]
## Sources
[Numbered list of all sources with URLs]
## Methodology
[Brief note on research approach]
# Check trending GitHub repos for a topic
gh search repos "ai agent" --sort stars --limit 30 --json name,description,stargazersCount,url,updatedAt
# Get recent articles from a domain
curl -sL "https://DOMAIN.com/feed" | grep -oP '<title>.*</title>' | head -20
# Check npm package popularity
npm view PACKAGE version time.created time.modified
共 1 个版本