agentleFS
AbilityaiAbilityai/cornelius/.claude/skills/synthesize-insights/SKILL.md

synthesize-insights

Skill109 starsChanged 40 days agoMITView on GitHub

Combine multiple insights into coherent narrative

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If specific notes listed: Retrieve those notes

    line 44
  2. Very specific:

    If topic/theme: Use /recall or Local Brain Search to find cluster - read role by mode (contract: scope-mount):

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Synthesize Insights

Combine multiple insights or permanent notes into a coherent narrative, framework, or argument. Discovers patterns and connections across disparate ideas.

Usage

/synthesize-insights <note names or topic cluster>

Parameters

  • note names: List of specific notes to synthesize
    • Comma-separated: "[[Note A]], [[Note B]], [[Note C]]"
    • Or topic cluster: "All notes about dopamine and AI"
    • Or theme: "Buddhism and neuroscience connections"

Examples

Synthesize Specific Notes

/synthesize-insights [[AI adoption bottleneck is psychological]], [[Professional identity creates AI resistance]], [[Belief is a way to deal with Uncertainty]]

Synthesize Topic Cluster

/synthesize-insights All notes connecting dopamine, social media, and AI

Synthesize Theme

/synthesize-insights Buddhism-neuroscience-AI triangle

Workflow

  1. Gather Notes
    • If specific notes listed: Retrieve those notes
    • If topic/theme: Use /recall or Local Brain Search to find cluster - read role by mode (contract: scope-mount):
      • pattern-finding / "what patterns emerge" → reasoning: BRAIN_READ_SCOPE=core,Books,document-insights resources/local-brain-search/run_search.sh "<topic>" --mode spreading --limit 10 --json
      • "summarize MY thoughts on X" → voice: BRAIN_READ_SCOPE=core resources/local-brain-search/run_search.sh "<topic>" --mode spreading --limit 10 --json
      • in either mode a Books/ or Document Insights/ note is encountered material and is labelled as such in the synthesis
    • Aim for 5-10 notes minimum
  2. Find Patterns
    • Identify common themes
    • Discover non-obvious connections
    • Note contradictions or tensions
    • Find consilience zones (multiple perspectives converging)
  3. Build Narrative
    • Structure: Pattern → Evidence → Implications
    • Show how insights relate and build on each other
    • Highlight emergent understanding
    • Suggest frameworks or models
  4. Output Synthesis
    • Coherent narrative (3-5 paragraphs)
    • Pattern description
    • Supporting evidence from notes
    • Implications and applications
    • Suggested next steps or questions

Output Format

🔗 Synthesis: [Topic/Theme]

**Pattern Identified:**
[Description of overarching pattern or framework emerging from notes]

**Key Connections:**

1. [Connection 1]: [[Note A]] + [[Note B]]
   [How these notes relate and what emerges]

2. [Connection 2]: [[Note C]] + [[Note D]] + [[Note E]]
   [Multi-way connection and emergent insight]

3. [Connection 3]: [[Note F]] ↔ [[Note G]]
   [Bidirectional or tension between notes]

**Emergent Understanding:**
[What new insight emerges from synthesizing these notes that wasn't obvious in any single note]

**Implications:**
- [Implication 1 for thinking/practice]
- [Implication 2 for content/frameworks]
- [Implication 3 for future exploration]

**Suggested Applications:**
- Article topic: "[Potential article title]"
- Framework: "[Potential framework name]"
- Research direction: "[Area to explore further]"

📝 Synthesized Notes:
- [[Note 1]] - Role in synthesis
- [[Note 2]] - Role in synthesis
- [[Note 3]] - Role in synthesis
[...]

Use Cases

1. Article Development

User: "I want to write about AI and psychology"

/synthesize-insights AI adoption psychological barriers cluster

# Output: Synthesized narrative showing how notes connect
# → Use as article foundation

2. Framework Creation

User: "Help me create a framework for AI resistance"

/synthesize-insights [[AI adoption bottleneck]], [[Professional identity]], [[Dopamine reinforcement]], [[Belief systems]]

# Output: Framework showing how psychological factors interact
# → Visualize in diagram or model

3. Connection Discovery

User: "How do my Buddhism notes relate to AI?"

/synthesize-insights Buddhism and AI connections

# Output: Non-obvious bridges between ancient wisdom and digital intelligence
# → Potential contrarian article angle

4. Content Planning

User: "What content can I create from my dopamine notes?"

/synthesize-insights All dopamine-related notes

# Output: Multiple synthesis narratives
# → Suggests 3-5 article topics or video series

Quality Indicators

High-quality synthesis: ✅ Identifies non-obvious patterns ✅ Shows connections between 5-10+ notes ✅ Produces emergent understanding ✅ Suggests practical applications ✅ Highlights tensions or contradictions ✅ Creates actionable frameworks

Low-quality (try different notes): ❌ Only surface-level connections ❌ No emergent insight ❌ Obvious or generic patterns ❌ Doesn't inspire new thinking

Advanced Techniques

Multi-Domain Synthesis

/synthesize-insights Notes connecting Buddhism, neuroscience, and AI agent design

Reveals consilience - where independent domains converge on same truth

Temporal Synthesis

/synthesize-insights Evolution of my thinking on AI from 2024 to 2025

Shows how perspectives change over time

Contrarian Synthesis

/synthesize-insights Notes that challenge conventional AI wisdom

Gathers all contrarian perspectives for provocative content

Problem-Solution Synthesis

/synthesize-insights Problem: AI adoption barriers + Solutions from psychology and Buddhism

Connects problem notes with solution notes from different domains

Integration with Other Commands

# Synthesis → Article workflow
/synthesize-insights Dopamine, social media, AI cluster
# → Get synthesis with connections
# → Use in /create-article skill

# Synthesis → Connections workflow
/synthesize-insights AI notes
/find-connections [synthesized theme]
# → Discover even more connections

# Synthesis → Video series workflow
/synthesize-insights Buddhism-AI connections
# → Extract 3-5 narratives
# → a content agent creates video series from each

Notes

  • Best with 5-10+ notes for rich synthesis
  • Looks for non-obvious connections semantic search might miss
  • Produces frameworks and models, not just summaries
  • Ideal for article planning and content strategy
  • Cost: ~$0.30-0.50 depending on number of notes
  • Can be called by a content agent for content ideation

Future Enhancements

  • Auto-suggest synthesis clusters
  • Visual network diagrams
  • Multi-layered synthesis (synthesis of syntheses)
  • Export as Mermaid diagram
  • Track synthesis quality over time

State Dependencies

SourceLocationReadWriteDescription
Brain notesBrain/**/*.mdXPermanent notes, AI insights, Document insights
Local Brain Searchresources/local-brain-search/XSemantic search for topic clusters
MOCsBrain/03-MOCs/XMap of Content for thematic organization

Completion Checklist

  • Notes gathered (5-10+ for rich synthesis)
  • Common themes identified
  • Non-obvious connections discovered
  • Contradictions or tensions noted
  • Emergent understanding articulated
  • Pattern → Evidence → Implications structured
  • Practical applications suggested
  • Cited notes listed with their role

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.