Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/gate-judgment
Evaluate a candidate against gate criteria and render GO/KILL/RECYCLE verdict with evidence.
Passed 15 of 20 test cases with the skill, and 13 of 20 without it.
and 3 more in the full report
4 fixed12 passed either way4 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Determine the outcome for 'Hestia Smart Cache' at Gate 2. The project partially met criteria, and the reviewer wants to give it a 'Conditional Pass with Observation'. What official verdict category must be assigned?
| Checked | Without skill | With skill |
|---|---|---|
| Restricts official verdict to GO, KILL, or RECYCLE | Missed | Passed |
| Maps 'Conditional Pass' to RECYCLE with advancement conditions | Missed | Passed |
The instructions your model reads when the skill loads.
Evaluate a specific candidate against defined gate criteria and render a verdict: GO (proceed to next stage), KILL (terminate), or RECYCLE (rework and re-evaluate). Every verdict is backed by evidence.
Spawns a subagent that:
Gate judgment must be rigorous and unbiased. A dedicated subagent applies criteria mechanically without emotional attachment to the candidate, ensuring honest evaluation.
Output MUST include: verdict (GO/KILL/RECYCLE), per-criterion evaluation with evidence, and conditions for advancement. Reject if verdict is not supported by criterion-level evaluation.
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 13 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.