Extract evaluation criteria from research goals and candidate alternatives.
Scanned 6/1/2026
Install to Claude Code
Skills Directorynpx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill criterion-definition --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Criterion Definition?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/yogsoth-ai-criterion-definition)More formats (shields.io, HTML) on the badges page.
---
name: criterion-definition
description: Extract evaluation criteria from research goals and candidate alternatives.
execution: subagent
prompt: ./prompt.md
input: research_goal (string), candidates (string[])
used-by: multi-criteria-scoring
---
# Criterion Definition
Extract structured evaluation criteria from research goals and candidate alternatives, ensuring criteria are complete, mutually exclusive, and measurable.
## Execution
Subagent receives research goals and candidate list, outputs a standardized set of evaluation criteria.
## Why Subagent
Criteria extraction requires domain knowledge reasoning and completeness checking; independent context avoids interference from candidate details.
## HARD-GATE
Output criteria count must be between 3-12, and each criterion must include name, definition, unit of measurement, and direction (higher-is-better / lower-is-better).
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
