vault-groom
Skill179 starsChanged 8 months agoMITView on GitHub
Audit and clean up knowledge base state — archive completed work, fix inconsistencies
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- elixir-expertSkill
- find-skillsSkill
- modern-cssSkill
- vault-auditSkill
- vault-checkinSkill
- vault-dashboardSkill
- vault-ingestSkill
- vault-meetingSkill
- vault-okrSkill
- vault-prepSkill
- vault-streamSkill
- vault-updateSkill
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
- Distinctive: line 15
Run a health check on the knowledge base and fix issues.
- Very specific: line 66
Use ask_user to confirm each category of fix:
≈ “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.
Files
Run a health check on the knowledge base and fix issues.
Team Mode (Large Vaults)
For large vaults (500+ entries), spawn a team to parallelize grooming:
team_spawn(
team_name: "vault-grooming",
purpose: "Audit, archive, and fix issues across a large vault",
roles: [
%{name: "vault-auditor", role: "researcher"},
%{name: "vault-archiver", role: "coder"},
%{name: "vault-fixer", role: "coder"}
]
)Team roles:
- vault-auditor: Runs
vault_audit(scope: "full")and catalogs all issues. Shares the report with archiver and fixer. - vault-archiver: Processes completed task archival (
vault_kanban(action: "archive")), archives old checkins, and moves stale entries. - vault-fixer: Applies approved metadata fixes, corrects frontmatter, resolves structural issues.
For smaller vaults, skip team mode and process single-agent.
Audit
vault_audit(scope: "full") — get the full quality report.
Check Task Board
vault_kanban(action: "list", filter_column: "done") — find completed tasks ready for archive.
vault_kanban(action: "list", filter_column: "in_progress") — check for stale items (no activity in 7+ days).
Check Temporal Entries
vault_list(entry_type: "checkin") — find checkins older than 30 days for archiving.
Present Findings
Format as a structured report:
- Task issues (missing metadata, stale items)
- Completed tasks ready to archive
- Old checkins ready to archive
- Quality issues from vault_audit
- OKR/milestone status inconsistencies
Interactive Fix
Use ask_user to confirm each category of fix:
- "Archive these X completed tasks?"
- "Archive these Y old checkins?"
- "Fix these Z metadata issues?"
Apply Fixes
- Archive tasks:
vault_kanban(action: "archive") - Archive checkins:
vault_update_entry(status: "archived")for each - Fix metadata:
vault_update_entry(frontmatter_updates: "...")for each
Refresh
vault_dashboard(dashboard_type: "index") after all fixes.
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
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.

