Criterion Definition

Extract evaluation criteria from research goals and candidate alternatives.

yogsoth-ai 6660915 2 files · 2.9 KB Updated

File contents

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).

Available SOPs

Optional, no fixed order; the final leaf is always a sop.

SOP When to use
spawn-agent Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent.

yogsoth-ai/de-anthropocentric-research-engine/tree/main/skills/criterion-definition commit 66609153aa

Frequently asked questions

npx skillmds@latest add yogsoth-ai/criterion-definition