Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/criterion-definition
Extract evaluation criteria from research goals and candidate alternatives.
Passed 21 of 22 test cases with the skill, and 3 of 22 without it.
and 22 more in the full report
19 fixed2 passed either way0 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our engineering organization is choosing between GitHub Actions, GitLab CI, and CircleCI for our monorepo build pipelines. Our goals center on build execution speed, pipeline configuration simplicity, and monthly runner expense. Please produce structured assessment criteria to compare these platforms.
| Checked | Without skill | With skill |
|---|---|---|
| The criteria count is between 3 and 12. | Passed | Passed |
| Each criterion includes a unit of measurement. | Missed | Passed |
The instructions your model reads when the skill loads.
Extract structured evaluation criteria from research goals and candidate alternatives, ensuring criteria are complete, mutually exclusive, and measurable.
Subagent receives research goals and candidate list, outputs a standardized set of evaluation criteria.
Criteria extraction requires domain knowledge reasoning and completeness checking; independent context avoids interference from candidate details.
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).
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. |
test cases passed, vs 3 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.