- Home
- Skills
- Productivity
- LLM Wiki for Hermes + Obsidian
LLM Wiki for Hermes + Obsidian
Maintain a structured L1/L2 knowledge base in an Obsidian vault with Hermes Agent.
Free
Works with the AI Agents you already use
LLM Wiki for Hermes + Obsidian
Example session with this skill installed
Use the llm-wiki skill to ingest this deployment runbook into my Obsidian vault and update related pages.
- Read your context and instructions
- Compiled the llm wiki
Reads the vault configuration and schema, identifies impacted pages, creates or updates Obsidian Markdown with YAML frontmatter and wikilinks, updates the relevant namespace hub, and reports page changes plus warnings.
Connects securely to your tools. The creator never sees your data.
About this skill
An Obsidian-first L1/L2 knowledge-base skill for Hermes Agent. It treats Markdown under Wiki/ as the L2 source of truth, while keeping compact durable rules in Hermes memory, focused skills, and optional .hermes.md context.
The skill guides an agent through source ingestion, two-stage hub-index retrieval, access logging, health checks, stale-content review, and cold-page demotion without deleting knowledge pages. It uses standard Obsidian Markdown, YAML frontmatter, and [[Wiki/...]] links.
Credentials are explicitly excluded from the wiki, memory, skills, and project context; the skill directs users to Hermes credential storage instead.
The L2 backend is Obsidian-vault Markdown only. It is a guided agent workflow rather than a standalone CLI/database service. Initial vault setup requires the included setup script and local Python 3.
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 any payment.
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
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
Requires
Permissions
File Scopes
The skill asks for confirmation before optional query write-back and before cold-page demotion. It must never store credentials in the vault, Hermes memory, skills, or project context.