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

memory/memory-consolidation

Skill10 starsChanged 2 months agoMITView on GitHub

Use when optimizing vault storage, archiving stale data, or deduplicating entries — consolidates related entries and ensures memory remains high-quality and retrievable. Inspired by AI-Ops working/episodic/semantic/procedural patterns. Default skill for 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

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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 Prime

    line 15
  2. Distinctive:

    Update skills based on accumulated learnings

    line 43
  3. Distinctive:

    Update all references to point to the kept entry

    line 52
  4. Distinctive:

    Vault: All vaults (operates on all vaults)

    line 70

≈ “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

Memory Consolidation

"The art of remembering is the art of forgetting what doesn't matter."

When This Skill Activates

  • Optimizing vault storage, archiving old entries, deduplicating
  • Keywords: "consolidate", "optimize memory", "clean up", "archive", "deduplicate"
  • Default for: Starlight Prime

What This Skill Does

Optimizes the Starlight Vaults by consolidating related entries, archiving stale data, deduplicating, and ensuring memory remains high-quality and retrievable. Inspired by AI-Ops research on memory consolidation patterns (Working -> Episodic -> Semantic -> Procedural).

Procedures

Procedure 1: Memory Hierarchy Consolidation

Following the AI-Ops memory hierarchy:

  1. Working Memory (current session context)
    • Review items in current context
    • Identify what should be promoted to persistent storage
  2. Episodic Memory (specific events/sessions)
    • Review Session Notes older than 30 days
    • Extract lasting insights, archive the rest
    • Promote patterns to Semantic Memory
  3. Semantic Memory (general knowledge/facts)
    • Review vault entries for accuracy
    • Merge related entries into comprehensive entries
    • Promote proven patterns to Procedural Memory
  4. Procedural Memory (how-to knowledge)
    • Review skill effectiveness
    • Update skills based on accumulated learnings
    • Archive deprecated procedures

Procedure 2: Deduplication

  1. Scan vaults for entries with high similarity
  2. Compare content, timestamps, and confidence scores
  3. For duplicates: keep the entry with highest confidence
  4. Merge unique details from discarded duplicates
  5. Update all references to point to the kept entry
  6. Log deduplication actions for audit

Procedure 3: Quality Assessment

  1. Calculate vault health metrics:
    • Entry count per vault
    • Average confidence score
    • Oldest entry age
    • Index accuracy
    • Retrieval success rate
  2. Identify low-quality entries (low confidence, never retrieved)
  3. Recommend actions: consolidate, archive, or remove
  4. Generate vault health report
  5. Store report in Operational Vault

Integration Points

  • Vault: All vaults (operates on all vaults)
  • Agents: Prime (authorizes consolidation), Sage (knowledge quality)
  • Notes: Archives old notes, creates consolidation reports

Quality Criteria

  • Did consolidation reduce total entries without losing knowledge?
  • Are remaining entries higher quality?
  • Were no high-confidence entries accidentally removed?
  • Is the vault healthier after consolidation?

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