From evaluator
Structured bug autopsy after fixing a bug. Analyzes root cause, classifies the bug, and recommends prevention. Run after any non-trivial bug fix.
npx claudepluginhub artmin96/forge-studio --plugin evaluatorThis skill is limited to using the following tools:
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Reviews prose for communication issues impeding comprehension, outputs minimal fixes in a three-column table per Microsoft Writing Style Guide. Useful for 'review prose' or 'improve prose' requests.
Run this after fixing a bug. Don't just fix and move on — every bug is a potential guardrail.
Describe the bug behavior in one sentence. What did the user see? What was expected?
Explain WHY it happened — not just what you changed to fix it. Trace the chain:
Classify the bug. Pick one:
One concrete recommendation. Not vague ("be more careful") — specific:
POSTMORTEM
==========
Bug: [One-sentence description]
Root Cause: [Why it happened]
Category: [From list above]
Missed By: [What should have caught it]
Prevention: [Specific action]
Keep it short. This is a quick post-fix analysis, not a 500-word essay.