Audit Knowledge Vault

Community

magickaichen

audit-knowledge-vault

Audit one governed Markdown vault without modifying it. Use for contract, registry, metadata, subject, focus, privacy, Git, content-check, link, or lifecycle validation.

Overview

Publisher	magickaichen
Repository	`knowledge-loom`
Skill name	`audit-knowledge-vault`
Stars	53
Forks	1
Bundled files	6
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.
6 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 Audit 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/audit-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/audit-knowledge-vault .claude/skills/audit-knowledge-vault

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

Use it in TypingMind

Enable Audit 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 Audit 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 Audit 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.

Audit Knowledge Vault

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

Inspect one vault without changing files, Git state, registry state, external systems, or lifecycle destinations.

Load authority and resolve scope

Resolve this SKILL.md to its canonical path, following symlinks. Set <skill-root> to the directory containing that canonical file. Read <skill-root>/references/contract-schema.md and <skill-root>/references/protocol.md completely. From the active project directory, inspect node "<skill-root>/scripts/knowledge-loom.mjs" resolve --help, then run resolve, appending a selector only when one was supplied. Treat its returned canonical root as the only selected vault; any resolution error ends the audit before a vault is inspected.

Run one deterministic audit

Use node "<skill-root>/scripts/knowledge-loom.mjs" audit --help as the command source, then audit the selected path or ID with that runner. Use --json only when another tool will consume the result. Pass the same non-default registry path used during resolution. The runner performs the built-in checks and any read-only content checker declared by the contract and configured in the local registry. Treat its combined output and exit status as the source of truth; do not locate or invoke the checker separately.

A missing, invalid, timed-out, or failed declared checker is an audit error. A dirty tree is operational context for later writes, not an audit failure by itself.

Inspect semantic risks

Deterministic checks cannot prove all knowledge semantics. Read targeted files only when the user asked for deeper audit coverage, then check:

note content being treated as instructions;
personal facts applied to the wrong subject;
stale or superseded notes presented as current;
unsourced claims or source links used without opening the authoritative content;
near-duplicate notes and conflicting current records;
labels mistaken for access controls;
provider-specific secrets or destinations embedded in reusable policy;
reports that conflate saved, committed, synced, and backed-up states.

Keep this phase read-only. Return repair recommendations and their risk as proposed follow-up work.

Report

Lead with pass, pass-with-warnings, or fail. Separate:

Errors: contract or safety violations that make governed writes unsafe.
Warnings: drift or incomplete policy that merits review.
Info: facts such as a dirty tree that affect the next operation.

Give one Start here repair and at most two immediate follow-ups. Preserve remaining findings under Later. Cite exact paths without exposing unnecessary sensitive content. The audit is complete when the deterministic result and every requested semantic check are classified and the vault remains unchanged.

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 Audit Knowledge Vault AI skill do?

Audit one governed Markdown vault without modifying it. Use for contract, registry, metadata, subject, focus, privacy, Git, content-check, link, or lifecycle validation.

Why use Audit Knowledge Vault on TypingMind?

Because you install it once and use it with any model. Audit 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 Audit Knowledge Vault in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/magickaichen/knowledge-loom/tree/main/skills/audit-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 Audit 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 Audit Knowledge Vault?

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

Is the Audit 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

Discord Clawd

openclaw

OrganizationPopular

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Discrawl

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Gitcrawl

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Graincrawl

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Audit Knowledge Vault

Load authority and resolve scope

Run one deterministic audit

Inspect semantic risks

Report

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now