- Home
- Skills
- Agents & Orchestration
- llm-wiki-maintainer 1.1
llm-wiki-maintainer 1.1
Turn your AI agent into a digital librarian that builds and audits a persistent markdown knowledge base.
$5
Works with the AI tools you already use
llm-wiki-maintainer 1.1
Example session with this skill installed
Record our decision to switch to FastAPI based on today's logs, reconcile the conflicting rate limit data from source_A and source_B, and run a health check on the wiki.
- Read your context and instructions
- Compiled the llm-wiki-maintainer 1 1
Updated index.md with 2 new entries.
Created decision-record: 'migration-to-fastapi.md'
Appended log.md: [2023-10-24] Resolved conflict between source_A and source_B regarding API rate limits.
Running wiki_lint.py... 0 orphans found. Wiki is healthy.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
Maintain a Persistent, Compound Knowledge Base
The LLM Wiki Maintainer solves the "memory leak" problem in AI workflows where knowledge is lost after a conversation ends. Instead of ephemeral chats, this skill enables your agent to build and maintain a living markdown wiki that grows more valuable over time.
What it does
This skill provides a structured framework for an AI agent to act as a librarian and synthesizer. It manages a directory of markdown files using a strict schema, ensuring that raw sources remain immutable while synthesized "knowledge pages" are continuously updated. It handles provenance tracking, contradiction management, and automated indexing.
Why use this skill
- Persistence: Every useful answer the AI generates is automatically filed back into the wiki for future use.
- Provenance: Tracks source hashes and claims so you always know where information came from.
- Structural Integrity: Includes Python scripts for linting, SQLite-backed indexing, and automated log generation to prevent the wiki from becoming a "junk drawer."
- Conflict Resolution: Instead of overwriting old data, it reconciles contradictions through dedicated reflection pages.
Technical Features
Supports markdown-based folders, SQLite for high-speed querying of page metadata, and custom linting rules for structural health. It works seamlessly with local file systems or cloud-based repositories.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
1 install
Downloaded by developers to date
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 5 months ago
- Passed all security checks, Safe to install