Automated summary
This skill calls the Flywheel MCP server to produce a diagnostic report for an Obsidian vault: note and link counts, orphans, broken links and top hubs, plus a health score and recommended next actions.
Strengths
- Structured, easy-to-scan report enforced by a fixed output template (score, issues, top hubs, recommendations)
- Explicit and reproducible health score calculation with documented thresholds (excellent, good, fair, needs attention)
- Cheap to run: a single MCP call to get_vault_stats, roughly 2-3 seconds, with no caching needed
- Points to the right remediation skills (/vault-fix-links, /orphans, /suggest) based on the issues it detects
Limitations
- Fully dependent on the Flywheel MCP server and two specific tools; without them it produces nothing
- Diagnostics are structural only (links, orphans, connectivity) and do not assess note content quality or staleness
- Health score weights are fixed heuristics that cannot adapt to vault size or purpose
- find_broken_links is allowed but the report only surfaces a count and percentage, not per-link detail
Use it when you want a quick structural health check of your vault before a maintenance or link-cleanup session.
Avoid it if you need semantic content analysis, note deduplication, or if the Flywheel MCP server is not configured.
Security analysis
SafeThe skill only uses two declared Flywheel MCP read/statistics tools and contains no shell execution, network calls, destructive actions, credential access, or obfuscated instructions. Execution risk is minimal.
No concerns found
How this analysis is madeExamples
Run a vault health check on my knowledge base and tell me the health score plus what I should fix first.How's my vault? Give me a health report with broken links, orphans and my top hubs.Diagnose my vault and tell me how many broken links and orphan notes I have, with recommendations.name: vault-health description: Comprehensive vault diagnostics and health report. Triggers when user mentions "vault health", "health report", "vault diagnostics". auto_trigger: true trigger_keywords:
- "vault health"
- "health report"
- "vault diagnostics"
- "vault status"
- "vault report"
- "how is my vault"
- "vault overview"
- "vault checkup"
- "how's my vault"
- "vault condition"
- "knowledge base health"
- "vault stats"
- "check vault"
- "diagnose vault"
- "vault summary" allowed-tools: mcp__flywheel__get_vault_stats, mcp__flywheel__find_broken_links
Vault Health
Quick vault diagnostics and health assessment.
When to Use
Invoke when you want to:
- Check overall vault health
- See broken link count
- Identify top hubs (most connected notes)
- Get recommendations for maintenance
Process
1. Get Vault Statistics
Call mcp__flywheel__get_vault_stats to retrieve:
- Total notes
- Total links
- Average links per note
- Orphan count
- Broken link count
- Top connected notes (hubs)
- Tag distribution
- Folder breakdown
2. Assess Health
Calculate vault health score based on:
- Broken links percentage (lower is better)
- Orphan percentage (lower is better)
- Average connectivity (higher is better)
- Link growth trend
3. Generate Report
Format comprehensive health report:
Vault Health Report
═══════════════════════════════════════════════
📊 Overview:
• Total Notes: 1,000
• Total Links: 15,000
• Average Links/Note: 15.0
⚠️ Issues Found:
• Broken Links: 200 (1.3% of all links)
• Orphan Notes: 100 (10% of all notes)
🌟 Top Hubs:
1. [[Project A]] - 150 backlinks
2. [[Technology X]] - 120 backlinks
3. [[Daily Workflow]] - 100 backlinks
📈 Vault Health Score: 85% (Good)
💡 Recommendations:
• Run /vault-fix-links to repair broken links
• Review /orphans to connect isolated notes
═══════════════════════════════════════════════
4. Provide Action Items
Link to relevant skills based on issues found:
- Many broken links → Suggest
/vault-fix-links - Many orphans → Suggest
/orphans - Low connectivity → Suggest
/suggestfor link suggestions
Health Score Calculation
Base Score: 100%
Deductions:
- Broken links: -0.5% per 1% of total links broken
- Orphans: -0.3% per 1% of notes orphaned
- Low connectivity: -10% if avg < 5 links/note
Bonuses:
- High connectivity: +5% if avg > 15 links/note
- Few orphans: +5% if orphan% < 10%
- Few broken: +5% if broken% < 5%
Final Score: 0-100%
90-100%: Excellent ✅
75-89%: Good 👍
60-74%: Fair ⚠️
<60%: Needs Attention 🚨
Output Format
Always use the branded format:
Vault Health Report
═══════════════════════════════════════════════
[Report content here]
═══════════════════════════════════════════════
Performance
- Speed: 2-3 seconds (single MCP call)
- Accuracy: 100% (direct from Flywheel MCP)
- Caching: None needed (live data)
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/vault-health-mrx3xxjy/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/vault-health-mrx3xxjy' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/vault-health-mrx3xxjy/download' --output '.skill-downloads/vault-health-mrx3xxjy/SKILL.md.part' && mv '.skill-downloads/vault-health-mrx3xxjy/SKILL.md.part' '.skill-downloads/vault-health-mrx3xxjy/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): mcp__flywheel__get_vault_stats, mcp__flywheel__find_broken_links
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/vault-health-mrx3xxjy/SKILL.md' && test -s '.skill-downloads/vault-health-mrx3xxjy/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/vault-health' && cp -R '.skill-downloads/vault-health-mrx3xxjy' '.claude/skills/vault-health'Cursor
test -f '.skill-downloads/vault-health-mrx3xxjy/SKILL.md' && test -s '.skill-downloads/vault-health-mrx3xxjy/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/vault-health' && cp -R '.skill-downloads/vault-health-mrx3xxjy' '.cursor/skills/vault-health'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/vault-health-mrx3xxjy'openskills read 'vault-health-mrx3xxjy'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/vault-health-mrx3xxjy/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
PDF Reader
Productivity
Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.
Discord Messaging Workflows
Productivity
Use the message tool to send, edit, and moderate Discord messages with interactive components.
Interactive Verdict Preview
Productivity
Generate an interactive HTML preview of keep/drop verdicts for maintainer review, then process the pasted feedback JSON.