Diagnostic patterns and repair protocols for self-correcting AI components. Passive knowledge base for the /heal command.
/plugin marketplace add Git-Fg/thecattoolkit/plugin install git-fg-cat-toolkit-meta-plugins-meta@Git-Fg/thecattoolkitThis skill is limited to using the following tools:
assets/scripts/bootstrap.shreferences/bootstrap-protocol.mdreferences/diagnosis-patterns.mdreferences/shared-standards.mdDiagnostic logic for identifying why an AI component failed and repair strategies to fix it. Used by the /heal command in main context.
For common principles, integration patterns, and anti-patterns, see:
Symptom: AI tries to use a specific tool/workflow mentioned in the Skill but fails (e.g., "Tool not found" or "Invalid arguments").
Diagnosis: The SKILL.md examples or instructions are out of sync with the actual tools available.
Repair: Update SKILL.md examples to match the actual tool signature found in the environment.
Symptom: Subagent enters an infinite loop, asks user questions when prohibited, or fails to create output.
Diagnosis: Weak negative constraints in agents/*.md.
Repair: Add explicit <constraints> or NEVER clauses to the agent definition.
Symptom: Command invents arguments or fails to gather necessary context before delegation.
Diagnosis: argument-hint or description is vague.
Repair: Update frontmatter argument-hint and add explicit context gathering steps.
If the model failed to format an output correctly:
Action: Do not just change instructions. Add a concrete example block using Markdown to the component's definition showing the correct input/output pair based on the recent failure.
If the model violated a rule (e.g., edited a protected file):
Action: Move the rule from "Instructions" to a dedicated <constraints> XML block or use uppercase "MUST/NEVER" language.
If the model hallucinated a file path:
Action: Verify the actual path using ls/find and update the reference in the documentation.
When core tools (/build, /heal) are corrupted, use git restore to recover. See /heal command's "Emergency Bootstrap Recovery" section for protocols.
| Reference | Purpose |
|---|---|
| shared-standards.md | Common standards for all management skills |
| diagnosis-patterns.md | Decision tree for root cause analysis |
| bootstrap-protocol.md | Emergency git-based recovery procedures |
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.