vault-audit

Full 7-phase vault audit: structural scan, duplicate detection, link integrity, frontmatter audit, MOC review, cross-agent integration check, and health report. Triggers: EN: "weekly review", "check the vault", "vault audit", "full audit", "vault health". IT: "revisione settimanale", "controlla il vault", "audit del vault", "salute del vault". FR: "audit du vault", "vérifier le vault". ES: "auditoría del vault", "revisar el vault". DE: "Vault-Audit", "Vault überprüfen". PT: "auditoria do vault", "verificar o vault".

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong, highly actionable workflow document with clear sequencing and robust validation for destructive/batch operations. Its main weakness is progressive disclosure: the skill is a single large file with no reference bundle, inlining templates and protocols that would be better split out.

Suggestions

Extract the ~60-line health report template into references/health-report-template.md and link to it from Phase 7, keeping only the field list inline.

Move the inter-agent coordination protocol ("Suggested next agent" / "Suggested new agent" output formats and decision rules) into references/agent-coordination.md, retaining just the core routing rules in SKILL.md.

Pull the per-phase report output blocks (Phases 1-7) into references/report-formats.md referenced once, to tighten the main body and reduce token load on every invocation.

Dimension	Reasoning	Score
Conciseness	Efficient and assumes Claude's competence (no explanations of Obsidian/wikilinks), but the large inlined report template and repeated confirmation themes could be trimmed; not every token earns its place, so it sits below anchor 5 rather than at it.	4 / 5
Actionability	Fully actionable instruction-only guidance: exact paths (Meta/user-profile.md, Meta/agent-log.md), required frontmatter fields (type, date, tags, status), concrete thresholds (>70% overlap, >30 days, 3+ notes), and copy-paste-ready output templates covering common cases.	5 / 5
Workflow Clarity	Seven phases are clearly sequenced with explicit validation/confirmation checkpoints ("Ask the user for confirmation before merging or deleting", "Apply all N fixes? [Yes / Let me review each / Skip]") and a post-it memory feedback loop, fully satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Well-sectioned but monolithic: no bundle files exist and everything — including a ~60-line health report template and the detailed inter-agent coordination protocol — is inlined in SKILL.md, matching the anchor 3 case of content that should be separate being inline.	3 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: it states concrete capabilities, gives explicit multi-language trigger guidance, and carves out a distinct niche with low conflict risk. No first/second-person voice issues are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "structural scan, duplicate detection, link integrity, frontmatter audit, MOC review, cross-agent integration check, and health report" — giving comprehensive coverage of the audit's scope, matching the anchor 5 example.	5 / 5
Completeness	Explicitly answers both what ("Full 7-phase vault audit: ...") and when ("Triggers:" followed by concrete trigger phrases), satisfying the anchor 5 and avoiding the missing-trigger cap.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases with synonyms ("weekly review", "check the vault", "vault audit", "full audit", "vault health") across six languages, well beyond the anchor 5 bar.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear vault-audit niche with distinct, vault-specific triggers; minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gnekt/My-Brain-Is-Full-Crew
Path: tests/regression/snapshot/.claude/skills/vault-audit/SKILL.md
Commit: 238ae8c

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.