pmstack-vibe-test

SKILLWorkflowcommunity
v0.0.0RyanAlbertsMITUpdated 1mo agoSource →

Walks a PM through the layer-1 ritual of reading raw transcripts of an AI feature in action — what Anthropic calls "manual testing, dogfooding, and intuition" — before formalizing a structured eval. Surfaces failure patterns, drafts task candidates (including balanced negative cases per Anthropic St

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
8Repo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorRyanAlberts
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Walks a PM through the layer-1 ritual of reading raw transcripts of an AI feature in action — what Anthropic calls "manual testing, dogfooding, and intuition" — before formalizing a structured eval. Surfaces failure patterns, drafts task candidates (including balanced negative cases per Anthropic Step 3), and produces a verdict on whether the feature is ready for /eval. Use when the user says "I w

Keywords
skillclaude