Stats
Actions
Tags
From claude-memory
This skill should be used when the user wants to run a vault health check, audit vault contents, check vault health, or perform vault maintenance. Trigger phrases: "audit vault", "check vault health", "vault maintenance", "/claude-memory:audit". <example> Context: User notices vault has grown and wants to check its health user: "audit vault" assistant: "I'll dispatch the vault-librarian to run a full health check." <commentary>Trigger phrase matches — dispatch vault-librarian agent and present findings.</commentary> </example>
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-memory:auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Dispatch the `vault-librarian` subagent via the Agent tool to run a deep vault health check.
Dispatch the vault-librarian subagent via the Agent tool to run a deep vault health check.
Dispatch the agent. Invoke the vault-librarian agent with no additional arguments. It will run all checks and write a full report to thinking/vault-audit-YYYY-MM-DD.md.
Review findings. Read the librarian's summary (top 5 findings returned to this conversation). Do not re-run any checks — trust the agent's output.
Present actionable summary grouped by severity:
related entries)Offer auto-fix for simple issues. After presenting the summary, ask the user:
"Want me to auto-fix simple issues (add missing
datefrom filename, add emptytags: [])? I'll show each change before writing."
Wait for explicit approval before modifying any file. Do not auto-fix broken wikilinks, orphan disposition, or stale note archiving without separate confirmation per item.
npx claudepluginhub arianjad/claude-memory --plugin claude-memoryCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.