review-vault-health
Skill1 starsChanged 22 days agoMITView on GitHub
Assess vault usefulness, current state and retrieval in the selected deployed vault; recommend maintenance priorities, read-only by default.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ingest-sourceSkill
- lint-vaultSkill
- process-inboxSkill
- process-ready-ingestion-inboxSkill
- start-a-focusSkill
- update-project-next-actionsSkill
- update-project-summarySkill
- skill.mdSkill
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
- Distinctive: line 18
Read the vault rules and Procedure completely before acting.
- Distinctive: line 22
Default to read-only and inventory canonical notes only.
- Distinctive: line 26
Use compactness metrics as evidence, not a reason to shorten cold Sources or Events.
- Distinctive: line 27
Prefer a few high-value recommendations and propose broad changes before applying them.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Review Vault Health
Assess whether the vault remains useful, current and easy to navigate. Recommend a few high-value improvements, read-only by default.
For mechanical defects, use lint-vault. Health review interprets some of the same audit evidence; a structurally valid vault can still contain stale summaries or buried decisions.
Source of truth
- Vault rules:
AGENTS.md - Complete workflow:
procedures/review-vault-health.md - Helper:
.agents/skills/lint-vault/scripts/compactness_audit.py
Read the vault rules and Procedure completely before acting.
Guardrails
- Default to read-only and inventory canonical notes only.
- Inspect entry points, Types, active Projects and Responsibilities, views, Questions, synthesis, Procedures, ADRs, and skills.
- Judge low counts rather than enforcing quotas.
- Distinguish lint findings from strategic issues such as overloaded entry notes, append-only writeback, weak resumption, or hidden knowledge.
- Use compactness metrics as evidence, not a reason to shorten cold Sources or Events.
- Prefer a few high-value recommendations and propose broad changes before applying them.
Select this package by the requested vault role, not its name alone. Reuse rules and the complete Procedure already read in this session while they remain current; reread after a relevant change.
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.

