agentleFS
DojoGenesisDojoGenesis/openclaw-plugin/skills/research-synthesis/SKILL.md

research-synthesis

Skill0 starsChanged 9 months agoMITView on GitHub

Synthesize multiple research files into actionable insights through cross-referencing and pattern identification. Use when you have 3+ sources on a topic, need a literature review, consolidating notes from multiple sources, or understanding topics from multiple angles. Trigger phrases: 'synthesize these research files', 'find patterns across sources', 'consolidate these notes', 'create a literature review', 'understand by synthesizing'.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use competitive-analysis, literature-review and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    competitive-analysis

    Framework for building competitive landscape decks — market positioning, competitor deep-dives, comparative analysis, strategic synthesis. Use when the user asks for a competitive landscape, competitor analysis, peer comparison, market positioning assessment, strategic review, or investment memo deck. Also triggers on "who are the competitors to X", "benchmark X against peers", "build a market map", or any request to systematically evaluate competitive dynamics across an industry.

    Also in 3 projects that use this

  • JDerekLomasSkill

    literature-review

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

    Also in 3 projects that use this

  • OpenAISkill

    brainstorming

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

    Also in 3 projects that use this

  • BlockSkill

    frontend-design

    Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

    Also in 4 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. 0 are common, 11 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 11

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Goal: Read all uploaded research files and create a structured catalog.

    line 41
  2. Very specific:

    Read Files: Use the file tool to read each uploaded file (use view for PDFs).

    line 43
  3. Distinctive:

    Create Catalog: Create an internal catalog document listing all files and their metadata.

    line 45
  4. Distinctive:

    Identify Themes: Read through the catalog to identify recurring themes.

    line 51
  5. Distinctive:

    Create Cross-Reference Matrix: Create an internal matrix to map themes to sources.

    line 55
  6. Distinctive:

    Goal: Create a unified synthesis document that integrates findings from all files.

    line 59
  7. Distinctive:

    Goal: Ensure the synthesis is accurate, complete, and actionable.

    line 69
  8. Distinctive:

    Review for Accuracy: Check that all claims are supported by the source files.

    line 71
  9. Distinctive:

    Check for Completeness: Ensure all major themes and contradictions are covered.

    line 72
  10. Distinctive:

    Verify Actionability: Ensure that recommendations are concrete and can be implemented.

    line 73
  11. Very specific:

    Send Synthesis: Use the message tool to send the synthesis document as an attachment.

    line 79
  12. Distinctive:

    Cite Your Sources: Every claim in the synthesis should be traceable to a specific source file.

    line 90
  13. Distinctive:

    When running inside the Dojo Genesis plugin:

    line 104

“Common” is measured: kept by at least 6 in 10 of the 24 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

OpenClaw Integration: This skill is invoked by the Dojo Genesis plugin via /dojo run research-synthesis. The agent receives project context automatically via the before_agent_start hook. Use dojo_get_context for full state, dojo_save_artifact to persist outputs, and dojo_update_state to record phase transitions and decisions.

Research Synthesis Engine

Version: 1.0
Created: 2026-02-08
Author: Manus AI
Purpose: To turn raw research into a coherent understanding of a topic, identifying patterns, contradictions, and key recommendations.


I. The Philosophy: From Information to Insight

This skill transforms the act of research from a process of information gathering to a process of insight generation. By systematically cataloging, cross-referencing, and synthesizing multiple sources, it uncovers patterns and contradictions that are not visible from any single source, leading to a deeper, more actionable understanding.


II. When to Use This Skill

  • When you have 3 or more research files on a single topic.
  • When you need to create a literature review or a competitive analysis.
  • When you want to consolidate notes from multiple meetings or interviews.
  • When the planning-with-files meta-skill routes to this mode.

III. The Workflow

This is a 5-step workflow for synthesizing multiple research files.

Step 1: File Ingestion and Cataloging

Goal: Read all uploaded research files and create a structured catalog.

  1. Read Files: Use the file tool to read each uploaded file (use view for PDFs).
  2. Extract Metadata: Identify author, date, and key topics for each file.
  3. Create Catalog: Create an internal catalog document listing all files and their metadata.

Step 2: Cross-Referencing and Pattern Identification

Goal: Identify patterns, contradictions, and connections across all files.

  1. Identify Themes: Read through the catalog to identify recurring themes.
  2. Note Convergence: Where do the sources agree?
  3. Note Divergence: Where do the sources disagree or contradict each other?
  4. Identify Gaps: What topics are mentioned in one source but not others?
  5. Create Cross-Reference Matrix: Create an internal matrix to map themes to sources.

Step 3: Synthesis Document Creation

Goal: Create a unified synthesis document that integrates findings from all files.

  1. Organize by Themes: Structure the document by the themes identified in Step 2 (not by individual files).
  2. Summarize Evidence: For each theme, summarize the convergent evidence and highlight contradictions.
  3. Provide Key Insights: For each theme, provide a key insight that is not obvious from any single source.
  4. Include Actionable Recommendations: Provide a list of concrete next steps based on the synthesis.
  5. Cite Sources: Include citations to the specific files that support each claim.

Step 4: Validation and Refinement

Goal: Ensure the synthesis is accurate, complete, and actionable.

  1. Review for Accuracy: Check that all claims are supported by the source files.
  2. Check for Completeness: Ensure all major themes and contradictions are covered.
  3. Verify Actionability: Ensure that recommendations are concrete and can be implemented.

Step 5: Delivery

Goal: Deliver the synthesis to the user with clear next steps.

  1. Send Synthesis: Use the message tool to send the synthesis document as an attachment.
  2. Summarize: Briefly summarize the key insights and recommendations.
  3. Offer Deeper Dive: Offer to answer questions or explore specific themes in more detail.

IV. Best Practices

  • Organize by Themes, Not by Files: Synthesis requires integration, not just summarization.
  • Contradictions Are Valuable: Highlight disagreements between sources—they often reveal the most interesting insights.
  • Actionable Recommendations Are the Goal: A synthesis should lead to action.
  • Cite Your Sources: Every claim in the synthesis should be traceable to a specific source file.

V. Quality Checklist

  • Is the synthesis organized by themes, not by individual files?
  • Does the synthesis highlight both convergent evidence and contradictions?
  • Does the synthesis provide actionable recommendations?
  • Does the synthesis cite the source files for its claims?

OpenClaw Tool Integration

When running inside the Dojo Genesis plugin:

  1. Start by calling dojo_get_context to retrieve full project state, history, and artifacts
  2. During the skill, follow the workflow steps documented above
  3. Save outputs using dojo_save_artifact with the artifacts output directory
  4. Update project state by calling dojo_update_state to record skill completion and any phase transitions

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.