fable-judge

SKILLWorkflowcommunity
v0.0.0Sahir619MITUpdated 1mo agoSource →

Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
2kRepo stars
1Clients
1Formats
1mo agoLast update
Skill
AuthorSahir619
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptOpen (see Prompt tab)
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "

Keywords
skillclaude