From bette-think
Diagnoses root causes of AI feature failures like hallucinations, inconsistency, or slowness using 4D audit (Demand, Data, Discovery, Defense) from symptoms or Linear issues.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bette-think:ai-debugThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Figure out **why an existing AI feature is broken**.
Figure out why an existing AI feature is broken.
Works with:
When this skill is invoked, start with:
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
AI DEBUG
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
When AI fails, teams blame the model.
But 90% of failures are context failures.
What's going wrong?
1. Provide a Linear issue ID
2. Describe the symptoms
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
/ai-debug # Describe symptoms manually
/ai-debug LIN-123 # Start from Linear bug/issue
Works backwards from symptoms to root cause using the 4D audit:
| Symptom | Likely Root Cause | Focus Area |
|---|---|---|
| Hallucinations | Missing domain context, no grounding | D2, D4 |
| Inconsistency | Vague job definition, missing rules | D1, D4 |
| Generic outputs | Missing user/environment context | D2 |
| Wrong tone/format | Missing constraints, no examples | D1, D4 |
| Slow responses | Too much context, bad discovery | D2, D3 |
| High costs | Dumping everything in prompt | D2, D3 |
| Demo vs prod mismatch | Discovery strategy broken | D3, D4 |
Key insight: When AI fails, teams blame the model. But 90% of failures are context failures.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CONTEXT AUDIT COMPLETE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Feature: [Name]
Symptoms: [What was reported]
D1 Demand: [CLEAR / GAP / CRITICAL]
D2 Data: [CLEAR / GAP / CRITICAL]
D3 Discovery: [CLEAR / GAP / CRITICAL]
D4 Defense: [CLEAR / GAP / CRITICAL]
Primary Issue: [Root cause summary]
RECOMMENDED FIXES (prioritized):
1. [Highest impact fix]
2. [Second fix]
3. [Third fix]
Quick Win: [Smallest change that would help]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Questions to ask at each step:
Framework: 4D Context Canvas (Aakash Gupta & Miqdad Jaffer) Best for: Debugging hallucinations, inconsistency, performance issues in AI features
npx claudepluginhub breethomas/bette-think --plugin bette-thinkReferences 4D Context Canvas for engineering context in AI products. Archived; use /spec --ai for new features, /ai-debug for diagnosis, /context-check for quality.
Detects quality drops in AI-human collaboration and prompts re-anchoring. Useful when Claude repeats corrections, hallucinates, confuses context, or loops on the same step.
Use this skill when the user asks to "analyze AI errors", "error analysis for our AI feature", "open coding", "axial coding", "analyze model failures", "categorize AI mistakes", "find patterns in bad AI outputs", "what's wrong with our AI", or has a set of bad AI outputs and wants to understand what's failing and why. This is the first step in the AI eval methodology from Hamel Husain and Shreya Shankar.