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

memory/vault-management

Skill10 starsChanged 2 months agoMITView on GitHub

Use when storing, retrieving, or managing persistent memory across the Starlight Vaults — handles reading, writing, querying, and organizing entries across all vaults. Default skill for Starlight Prime and Starlight Sage.

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

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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, Starlight Sage

    line 15
  2. Distinctive:

    Search by: keywords, tags, date range, confidence threshold

    line 45
  3. Distinctive:

    Check for duplicate entries across vaults

    line 55
  4. Distinctive:

    Vault: All vaults (this skill operates ON vaults)

    line 62
  5. Distinctive:

    Agents: All agents use this skill for memory operations

    line 63

≈ “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

Vault Management

"Memory is the foundation of intelligence. Manage it well."

When This Skill Activates

  • Storing, retrieving, or managing persistent memory
  • Keywords: "vault", "store", "remember", "recall", "persist", "save", "memory"
  • Default for: Starlight Prime, Starlight Sage

What This Skill Does

Manages all operations on Starlight Vaults - the persistent memory system. Handles reading, writing, querying, and organizing vault entries across all five vaults.

Procedures

Procedure 1: Vault Write

  1. Determine which vault is appropriate:
    • Strategic decision? → Strategic Vault
    • Technical pattern? → Technical Vault
    • Creative insight? → Creative Vault
    • Operational state? → Operational Vault
    • Principle/lesson? → Wisdom Vault
  2. Structure the entry with:
    • Timestamp (ISO 8601)
    • Title (descriptive, searchable)
    • Category tags
    • Content (the knowledge to store)
    • Confidence score (0.0-1.0)
    • Related entries (links to other vault entries)
    • Source (where this knowledge came from)
  3. Append to the appropriate vault file
  4. Update vault index

Procedure 2: Vault Read/Query

  1. Determine which vault(s) to query
  2. Search by: keywords, tags, date range, confidence threshold
  3. Retrieve matching entries
  4. Sort by relevance (keyword match + recency + confidence)
  5. Return top N most relevant entries
  6. Include related entries if requested

Procedure 3: Vault Maintenance

  1. Review entries older than 90 days in Operational Vault
  2. Archive or remove stale operational entries
  3. Check for duplicate entries across vaults
  4. Merge duplicates, keeping the highest-confidence version
  5. Verify index accuracy
  6. Report vault health metrics

Integration Points

  • Vault: All vaults (this skill operates ON vaults)
  • Agents: All agents use this skill for memory operations
  • Notes: Creates notes as a side effect of significant vault operations
  • Memory: See memory/VAULT_ARCHITECTURE.md for full design

Quality Criteria

  • Is the entry in the correct vault?
  • Is the entry structured and searchable?
  • Is the confidence score calibrated?
  • Are related entries linked?

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