research-topic
Crawl and collect resources for a financial research topic using Exa with full HTML and chart extraction.
npx skills add majiayu000/claude-skill-registry --skill research-topic-epochdevs-claudecoderesearch --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Research Topic Crawler Collect raw resources (articles, charts, tables) for a financial research topic using the optimized Exa crawler. **Key Features:** - Full HTML content with tags preserved - Automatic chart/image URL extraction and download - Organized by source domain ## Usage ```bash /research-topic "seasonality in financial assets" /research-topic "FX macro correlations commodity currencies" /research-topic "momentum factor investing" ``` ## Workflow ### Phase 1: Initialize Topic Folder ```bash cd /home/adesola/EpochDev/ClaudeCodeResearch source .venv/bin/activate python report_notes/scripts/init_topic.py "$TOPIC" ``` This creates: ``` report_notes/<topic_slug>/ ├── manifest.json ├── sources/ │ ├── quantpedia/ │ ├── academic/ │ ├── broker_research/ │ ├── market_data/ │ └── misc/ └── images/ ``` ### Phase 2: Search and Crawl Sources Use the optimized Exa crawler script which: - Preserves HTML tags (`includeHtmlTags: true`) - Extracts image URLs (`extras.imageLinks: 30`) - Downloads charts automatically - Organizes by domain **General Search (broad coverage):** ```bash python report_notes/scripts/exa_crawler.py search "$TOPIC" --num 15 -o /tmp/search_results.json ``` **Doma
- Usage
- Workflow
- Phase 1: Initialize Topic Folder
- Phase 2: Search and Crawl Sources
- Phase 3: Save Sources to Topic
- Phase 4: Crawl Specific URLs
- Phase 5: Show Status
- Exa Crawler Script Reference
- Commands
- API Parameters Used
- What Gets Extracted
- Output Structure
- Manifest Format
- Source Markdown Format
cd /home/adesola/EpochDev/ClaudeCodeResearch source .venv/bin/activate python report_notes/scripts/init_topic.py "$TOPIC" python report_notes/scripts/exa_crawler.py search "$TOPIC" --num 15 -o /tmp/search_results.json python report_notes/scripts/exa_crawler.py search "$TOPIC academic research" --num 10 -o /tmp/academic_results.json python report_notes/scripts/exa_crawler.py search "USDCAD crude oil WTI correlation" --num 10 -o /tmp/usdcad_results.json Crawl single URL with full content python report_notes/scripts/exa_crawler.py crawl "<url>" --json -o /tmp/crawl_result.json Then save to topic using Python python -c "
What does the research-topic skill do?
Crawl and collect resources for a financial research topic using Exa with full HTML and chart extraction.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill research-topic-epochdevs-claudecoderesearch --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.