evaluator

SKILLWorkflowcommunity
v0.0.0moses607Apache-2.0Updated 1mo agoSource →

An auto-evaluation and hallucination guard that scores an agent's output against a task-derived rubric, checks every claim for support, and returns an accept / revise / reject verdict with specific fixes. It derives the rubric from the task, tests factual grounding against provided context, probes e

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
1Clients
1Formats
1mo agoLast update
Skill
Authormoses607
Version0.0.0
LicenseApache-2.0
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

An auto-evaluation and hallucination guard that scores an agent's output against a task-derived rubric, checks every claim for support, and returns an accept / revise / reject verdict with specific fixes. It derives the rubric from the task, tests factual grounding against provided context, probes edge cases, and never rubber-stamps. Use when the user says "evaluate this", "verify", "grade this",

Keywords
skillclaude