agentleFS
Sign inStart free
Arcanea-LabsArcanea-Labs/Starlight-Intelligence-System/skills/memory/knowledge-synthesis/SKILL.md

memory/knowledge-synthesis

Skill10 starsChanged 2 months agoMITView on GitHub

Use when combining knowledge from vaults, notes, transmissions, and external sources into coherent unified understanding — creates new knowledge from the intersection of existing knowledge. Default skill for Starlight Sage and Starlight Prime.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Default for: Starlight Sage, Starlight Prime

    line 15
  2. Distinctive:

    Vault: All vaults (reads from all, writes synthesis to appropriate vault)

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Knowledge Synthesis

"The whole is greater than the sum of its parts."

When This Skill Activates

  • Combining knowledge from multiple sources into unified understanding
  • Keywords: "synthesize", "combine", "merge", "integrate", "unify"
  • Default for: Starlight Sage, Starlight Prime

What This Skill Does

Combines knowledge from vaults, notes, transmissions, and external sources into coherent, unified understanding. Creates new knowledge from the intersection of existing knowledge.

Procedures

Procedure 1: Multi-Source Synthesis

  1. Identify all relevant knowledge sources
  2. Retrieve from each source:
    • Vault entries (by relevance)
    • Active notes (by recency)
    • Transmission history (by channel)
    • External references (if available)
  3. Organize by theme/topic
  4. Identify overlaps (reinforcing knowledge)
  5. Identify contradictions (conflicting knowledge)
  6. Resolve contradictions using confidence scores and recency
  7. Produce unified knowledge summary
  8. Store synthesis result in appropriate vault

Procedure 2: Cross-Domain Synthesis

  1. Identify knowledge from different domains (technical + strategic + creative)
  2. Find unexpected connections between domains
  3. Apply analogical reasoning (patterns from one domain applied to another)
  4. Generate novel insights from cross-pollination
  5. Validate insights against domain-specific knowledge
  6. Store valuable cross-domain insights in Wisdom Vault

Procedure 3: Temporal Synthesis

  1. Retrieve knowledge entries across time periods
  2. Identify how understanding has evolved
  3. Track which early assumptions proved correct/incorrect
  4. Extract lessons about the evolution process itself
  5. Project forward based on observed trajectory
  6. Store temporal insights in Wisdom Vault

Integration Points

  • Vault: All vaults (reads from all, writes synthesis to appropriate vault)
  • Agents: Sage (primary), Prime (council synthesis), Weaver (creative synthesis)
  • Notes: Creates Insight Notes from synthesis discoveries

Quality Criteria

  • Were all relevant sources consulted?
  • Were contradictions resolved, not ignored?
  • Did the synthesis produce new understanding (not just aggregation)?
  • Is the synthesis stored for future use?

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.

Check your setup, free