dogpile
Deep research aggregator that searches Brave (Web), Perplexity (AI), GitHub (Code/Issues), ArXiv (Papers), YouTube (Videos), and Wayback Machine simultaneously. Provides a consolidated Markdown report with an ambiguity check and Agentic Handoff.
npx skills add majiayu000/claude-skill-registry --skill dogpile --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.
# Dogpile: Deep Research Aggregator Orchestrate a multi-source deep search to "dogpile" on a problem from every angle. ## Analyzed Sources 1. **Codex (🤖)**: High-reasoning technical starting point and final synthesis (gpt-5.2). 2. **Perplexity (🧠)**: AI-synthesized deep answers and reasoning (Sonar Reasoning). 3. **Brave Search (🌐)**: **Three-Stage Search** (Search → Evaluate → Deep Extract via /fetcher). 4. **ArXiv (📄)**: **Three-Stage Search** (Abstracts → Details → Full Paper via /fetcher + /extractor). 5. **YouTube (📺)**: **Two-Stage Search** (Metadata → Detailed Transcripts via Whisper/Direct). 6. **GitHub (🐙)**: **Three-Stage Search**: - **Stage 1**: Search repositories and issues - **Stage 2**: Fetch README.md and metadata for top repos, agent evaluates relevance - **Stage 3**: Deep code search inside the selected repository 7. **Wayback Machine (🏛️)**: Historical snapshots for URLs. ## Features 1. **Query Tailoring**: Uses Codex to generate service-specific queries optimized for each source: - **ArXiv**: Academic/technical terms - **Perplexity**: Natural language questions - **Brave**: Documentation-style queries - **GitHub**: Code patterns, library names - **YouTube
- Analyzed Sources
- Features
- GitHub Three-Stage Search
- Presets (For Security Research)
- Commands
- Usage
- Agentic Handoff
- Error Reporting & Debugging
- Error Commands
- Error Logs
- Rate Limit Tracking
- Agent Debugging Workflow
- Error Types
- Task Monitor Integration
Use a preset (recommended for security research) Auto-detect preset from query List all presets python dogpile.py presets General research Security research with preset View error summary (human-readable) python dogpile.py errors View errors as JSON (for agent parsing) python dogpile.py errors --json
What does the dogpile skill do?
Deep research aggregator that searches Brave (Web), Perplexity (AI), GitHub (Code/Issues), ArXiv (Papers), YouTube (Videos), and Wayback Machine simultaneously. Provides a consolidated Markdown report with an ambiguity check and Agentic Handoff.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill dogpile --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.