skills.rest
haabe
haabeCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

canvas-health

Audits canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references.

42|3|Updated Apr 7, 2026
Search Tags:#risk assessment#knowledge base maintenance#AI decision-making#Mycelium framework#canvas health
One-click install
npx skills add https://github.com/haabe/mycelium --skill canvas-health
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: canvas-health
Source: https://github.com/haabe/mycelium/tree/main/plugins/mycelium/skills/canvas-health
Command: npx skills add https://github.com/haabe/mycelium --skill canvas-health

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the issue of maintaining the quality, consistency, and completeness of canvas files within the Mycelium framework, ensuring that the knowledge base is accurate and up-to-date for reliable AI decision-making.

Core Features & Use Cases

  • Quality Assurance: Lint canvas files for missing fields, inconsistent evidence types, and orphaned references.
  • Risk Management: Identifies assumptions and evidence that may need re-evaluation, reducing the risk of building on stale information.
  • Use Case: Before any major transition or when the agent's output quality degrades, this Skill can be run to check the health of the canvas files and ensure they meet the necessary standards.

Quick Start

Run the canvas-health skill to audit the canvas knowledge base for quality, consistency, and completeness. Example: /mycelium:canvas-health

Frequently Asked Questions about canvas-health

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit knowledge base files for staleness and orphaned references in AI decision-making?▼

To audit knowledge base files for staleness and orphaned references, you can run this Skill to lint canvas files, checking for missing fields and inconsistent evidence types to ensure reliable AI decision-making.

What is the best way to maintain canvas health and integrity within the Mycelium framework?▼

Maintaining canvas health within the Mycelium framework involves running audits to identify missing fields, stale assumptions, and orphaned references, ensuring the knowledge base remains accurate for AI agents.

When should I run a knowledge base quality assurance check for AI agents?▼

You should run a knowledge base quality assurance check before major transitions or when an AI agent's output quality degrades, ensuring the canvas files meet necessary standards and reducing the risk of using stale information.

Do I need Python to run canvas file audits for the Mycelium framework?▼

Yes, you need Python installed to run canvas file audits, as execution requires a Python environment and assumes you are operating within the Mycelium framework.

How does canvas health linting reduce risks in AI decision-making?▼

Canvas health linting reduces risks in AI decision-making by identifying assumptions and evidence that need re-evaluation, preventing the agent from building on inconsistent evidence types or stale information.

What specific errors does a canvas file audit detect in a knowledge base?▼

A canvas file audit detects staleness, missing fields, inconsistent evidence types, and orphaned references within the knowledge base, flagging areas that require immediate re-evaluation.

Related Skills

Explore More Product & Management Skills→
haabehaabe
42

feedback-review

Monitors Mycelium feedback loops and reports on their health.

Community
Advanced
kinnerkarmanishkinnerkarmanish

health

Diagnose workspace knowledge base health issues and generate ranked reports.

Community
Intermediate
haabehaabe
42

render

Route rendering intents to specialist render skills within the Mycelium framework.

Community
Advanced
DavidROliverBADavidROliverBA
49

Vault Maintenance

Automate quarterly knowledge base checks with parallel sub-agents.

Community
Advanced