Works with the AI Agents you already use
Lina obsidian vault curator
Privacy-first Obsidian vault curation with actionable audits, taxonomy-aware tag and YAML suggestions, and safe change previews.
$10
Lina obsidian vault curator
Example session with this skill installed
Audit my /Research/AI-Ethics folder for inconsistent tags and missing 'status' YAML properties. Provide a preview of the changes.
- Read your context and instructions
- Compiled the lina obsidian vault
I have completed the audit of the /Research/AI-Ethics directory. I scanned 12 Markdown files and skipped 2 files due to the default exclusion policy. No files have been modified.
Vault Audit Report: /Research/AI-Ethics
Findings Summary
- Tag Inconsistency: Found variations of
#machine-learning(e.g.,#MachineLearning,#ml). - Missing Metadata: 4 notes are missing the
statusproperty required by your folder convention. - Orphaned Notes:
ethics-framework-v2.mdhas no incoming or outgoing wikilinks.
Proposed Changes (Dry Run)
| Path | Operation | Reason | Proposed Change |
|---|---|---|---|
bias-in-llms.md | Update YAML | Missing status | Add status: seedling |
policy-draft.md | Update Tag | Normalize casing | Change #AI-Policy to #ai-policy |
data-privacy.md | Add Link | Related content | Add [[privacy-regulations]] |
neural-nets.md | Update YAML | Missing status | Add status: permanent |
Next steps
- Review the proposed table for accuracy.
- Reply with "Apply all" to execute these changes, or specify the paths you wish to update.
- Let me know if you want to scan for related notes in the
/Archivefolder to find more link candidates.
Connects securely to your tools. The creator never sees your data.
About this skill
Fragmented notes and inconsistent metadata make your Obsidian vault harder to navigate as it grows. This skill audits your Markdown files to align them with your existing taxonomy without the risk of automated bulk-edits or privacy leaks.
What it does
- Vault auditing scans authorized directories to identify orphaned notes, broken wikilinks, and inconsistent tag casing.
- Taxonomy normalization suggests tag and YAML property updates based on your established vault conventions.
- Relationship discovery identifies potential links between notes using lexical and structural evidence from your content.
- Privacy-first processing enforces strict exclusion rules for sensitive paths like
.git/,.obsidian/, or private folders. - Controlled modification generates exact before-and-after diffs for review before applying any changes to your filesystem.
How it works
- Inventory the vault root to collect metadata, tags, and wikilink structures while respecting your exclusion policy.
- Analyze note relationships and frontmatter consistency to build a list of evidence-based recommendations.
- Present a dry-run report detailing every proposed change for your explicit approval.
- Apply the approved patches precisely, ensuring YAML syntax and file integrity are preserved.
Frameworks & tools
This skill is designed for Obsidian Markdown vaults. It works with standard YAML frontmatter, wikilinks, and tag structures.
Why this beats prompting it yourself
Generic prompts often hallucinate tags or rewrite entire files, destroying your carefully maintained formatting. This skill follows a multi-phase safety protocol that separates evidence from inference and guarantees no silent writes occur.
Use cases
- Audit a research folder for redundant tags and missing metadata properties.
- Find conceptual overlaps between two sets of notes to suggest new wikilinks.
- Standardize YAML frontmatter across a vault after changing your organizational system.
- Identify and fix broken internal links after a major file reorganization.
Known limitations
Does not support semantic search or embeddings unless specific external tools are provided. Cannot access files outside the authorized vault root.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
No semantic/vector search support without external tools. Limited to Markdown files. Cannot process encrypted notes or non-textual attachments. Requires explicit file access permissions.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 13 days ago