Use Knowledge Vault

Community

magickaichen

use-knowledge-vault

Invoke before substantive work in a vault-linked directory, where an ancestor contract or project association may apply; this skill call starts vault activation for one governed Markdown vault. Also invoke for explicit requests to consult, remember, update, or sync vault knowledge.

Overview

Publisher	magickaichen
Repository	`knowledge-loom`
Skill name	`use-knowledge-vault`
Stars	53
Forks	1
Bundled files	5
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by magickaichen on GitHub. Read the source before you install it.

Installation

Install the Use Knowledge Vault AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/magickaichen/knowledge-loom/tree/main/skills/use-knowledge-vault
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/magickaichen/knowledge-loom.git /tmp/knowledge-loom
mkdir -p .claude/skills
cp -r /tmp/knowledge-loom/skills/use-knowledge-vault .claude/skills/use-knowledge-vault

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Use Knowledge Vault in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Use Knowledge Vault on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Use Knowledge Vault is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Use Knowledge Vault

Requires Node.js 20+ and local file/command access.

Execute the Knowledge Vault Protocol for one selected vault while keeping the primary task first. Limit actions to the primary task and contract-authorized vault operations.

Load the protocol

Resolve this SKILL.md to its canonical path, following symlinks. Set <skill-root> to the directory containing that canonical file. Read <skill-root>/references/protocol.md completely before vault access; it is the installed source of truth for authority, selection, retrieval, write policy, lifecycle, and failure behavior.

Run the loop

From the active project directory, inspect both node "<skill-root>/scripts/knowledge-loom.mjs" probe --help and resolve --help.
Choose the entry mode:
- For ordinary substantive work, run probe. Treat implementation, planning, prioritization, review, research synthesis, decisions, and durable communication as substantive. When it returns NO_APPLICABLE_VAULT, continue the primary task without vault work or a selection question.
- When the user explicitly requests a vault operation, run resolve. Append a selector only when the user or invoking wrapper supplied one, and apply the protocol's selection failure behavior.
Treat the returned canonical root as the only selected vault. Read its contract and instruction roots, then follow Prepare inbound access with node "<skill-root>/scripts/knowledge-loom.mjs" access <vault-path> --json before ordinary retrieval. Preserve an explicit read-only request. After integration, reload governing files and complete Retrieve using the updated knowledge. Carry degraded access state into claims that depend on remote freshness; use only context that materially affects the primary task.
Evaluate Write authorization after the primary task. Enter Distill only when the selected policy and current request authorize a vault change. When that branch will create or restructure an agent-consumed note or navigation pointer, apply the protocol's Agent-readable writing gate. If the active skill catalog exposes writing-for-agents, invoke that unmodified companion at this point for structure, context pointers, information hierarchy, co-location, and pruning, then complete the protocol gate. Its absence selects the built-in gate and does not block the authorized write.
After any write, run the deterministic audit:
```
bash
node "<skill-root>/scripts/knowledge-loom.mjs" audit <vault-path>
```
This single audit includes any read-only content checker declared by the contract and configured in the local registry; do not invoke that checker separately. Pass the same non-default registry path used during resolution. The write branch is complete only after the combined audit result and every required Git, sync, and backup state are known. Preserve a valid partial result when a later lifecycle step fails. For pending synchronization or divergent history, follow the protocol's Pending synchronization reference; finish agent evidence review before escalating an unresolved factual question.

Report

Lead with the primary outcome. Name vault context only when it changed that outcome. For a write, list every affected note and its exact saved, validated, committed, synced, and backed-up state. For a blocked write, apply the protocol's failure behavior and return one capture candidate when useful.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Use Knowledge Vault AI skill do?

Why use Use Knowledge Vault on TypingMind?

Because you install it once and use it with any model. Use Knowledge Vault is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Use Knowledge Vault in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/magickaichen/knowledge-loom/tree/main/skills/use-knowledge-vault. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Use Knowledge Vault?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Use Knowledge Vault?

As many as you like. As long as a model supports skills, you can use Use Knowledge Vault with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Use Knowledge Vault AI skill free?

Yes. It is published on GitHub by magickaichen under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Testing

openclaw

OrganizationPopular

Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.

Release Openclaw Ci

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

Release Openclaw Mac

Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.

Release Openclaw Maintainer

openclaw

OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Use Knowledge Vault

Load the protocol

Run the loop

Report

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now