Matrix Deep Research
Scannednpx machina-cli add skill ojowwalker77/Claude-Matrix/deep-research --openclawMatrix Deep Research
Perform comprehensive research on a topic using multiple sources: web search, Context7 documentation, Matrix memory, GitHub repositories, and more.
Usage
Parse user arguments from the skill invocation (text after the trigger phrase).
Format: <query> [depth]
- query: The research topic or question
- depth (optional):
quick|standard|exhaustive(default:standard)
Depth Levels
- quick: Fast research using 2-3 sources, ~500 words output
- standard: Balanced research using 4-5 sources, ~1500 words output
- exhaustive: Deep research using 6+ sources, ~3000+ words output
Research Pipeline
Follow the 5-phase research pipeline detailed in references/research-pipeline.md:
- Phase 1: Query Expansion - Analyze query, generate sub-queries, identify domains
- Phase 2: Multi-Source Gathering - Collect from Web, Context7, Matrix, GitHub
- Phase 3: Content Fetching - Retrieve full content from promising URLs
- Phase 4: Synthesis - Deduplicate, organize, identify patterns
- Phase 5: Output - Generate polished markdown report
Output
Save to session directory: $CLAUDE_SESSION_DIR/matrix-research-[slug]-[timestamp].md
If $CLAUDE_SESSION_DIR is not available, fall back to current working directory.
After completing research:
- Display a summary of findings in the chat
- Report the full markdown file location
- Offer to elaborate on any section
Examples
/matrix:deep-research React Server Components best practices standard
/matrix:deep-research "how to implement OAuth 2.0 with PKCE" exhaustive
/matrix:deep-research TypeScript generics quick
Additional Resources
Reference Files
For detailed pipeline procedures, consult:
references/research-pipeline.md- Complete 5-phase research process with output format
Source
git clone https://github.com/ojowwalker77/Claude-Matrix/blob/main/skills/deep-research/SKILL.mdView on GitHub Overview
Matrix Deep Research performs thorough investigations across web search, Context7 documentation, Matrix memory, and GitHub repositories to deliver a comprehensive topic report. It follows a structured 5-phase pipeline to unify data from multiple sources into a polished markdown document.
How This Skill Works
Provide a query and optional depth (quick, standard, exhaustive). The skill collects sources from Web, Context7 docs, Matrix memory, and GitHub, deduplicates content, and synthesizes insights. It saves a markdown report in the session directory and presents a chat summary along with the file location.
When to Use It
- Research a topic across web, documentation, and memory sources.
- Perform deep or exhaustive analysis for thorough understanding.
- Gather information from Web, Context7 docs, Matrix memory, and GitHub.
- Produce a polished markdown report saved in the session directory.
- Receive a chat summary and a link to the full report for review.
Quick Start
- Step 1: Trigger the skill with your topic and optional depth, e.g., /matrix:deep-research <topic> <depth>.
- Step 2: The tool collects sources, synthesizes insights, and saves a Markdown report to the session directory.
- Step 3: In chat, read the summary and open the full report location to review or elaborate.
Best Practices
- Define a precise query and optional depth up front (quick/standard/exhaustive).
- Frame sub-queries to expand the topic and improve coverage.
- Leverage all supported sources: Web, Context7 docs, Matrix memory, GitHub.
- During synthesis, deduplicate results and identify patterns or contradictions.
- Review the final markdown output and confirm the file path; request elaboration if needed.
Example Use Cases
- /matrix:deep-research React Server Components best practices standard
- /matrix:deep-research how to implement OAuth 2.0 with PKCE exhaustive
- /matrix:deep-research TypeScript generics quick
- /matrix:deep-research Kubernetes scalability standard
- /matrix:deep-research machine learning model evaluation metrics exhaustive
