Trigger: judgment day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.
SkillScore68Maintained
Automatic
◆Coding pack
Last verified 9/29/2026
What it changes
Passed 14 of 20 test cases with the skill, and 8 of 20 without it.
Without skill40%
With skill68%
Checks it passed that the model alone missed
Escalate for an explicit human decision when judges contradict.
Escalate the verdict without extending the two-round fix budget.
Restrict ledger persistence strictly to the parent orchestrator.
and 9 more in the full report
12 fixed5 passed either way3 still failing5 broke
Pass-rate lift
+28 pp
Tokens
-5%
Agent turns
0%
Response time
-49%
Model gemini-3.6-flashMeasured 9/29/2026v117 of 25 cases passed with skill · 20 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 9
Prompt
When completing the review for `apps/mobile/login.swift`, if all findings are cleared, should we issue the verdict as `JUDGMENT: PASSED 🟢` or `JUDGMENT: CLEAN`?
What was checked, without and with the skill
Checked
Without skill
With skill
Format the successful terminal verdict strictly as JUDGMENT: APPROVED ✅.
Missed
Passed
case-21 · gemini-3.6-flash · 9/29/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md44 lines2 files
Activation Contract
Load only when the user explicitly requests Judgment Day or equivalent dual/adversarial review for a concrete target. Judgment Day is a standalone developer tool: judges run whenever asked, on any runtime, and need no review transaction, runtime identity, or delivery-receipt machinery to start. It replaces ordinary 4R as the adversarial method for that target; never run both.
Hard Rules
Resolve matching project skills before starting and pass the same paths to both judges (jd-judge-a, jd-judge-b) and the fix actor (jd-fix-agent).
Build one complete immutable target, then launch two blind read-only judges in parallel with identical scope and criteria.
Each judge returns one neutral findings result and terminates. Wait for both; never accept a partial judgment.
Never launch review-refuter; two-judge agreement is the corroboration mechanism.
Only the parent orchestrator merges/persists findings, launches the fix actor (jd-fix-agent), and launches scoped re-judgment.
Fix only severe findings confirmed by both judges. WARNING/SUGGESTION rows remain info.
Permit at most two fix rounds and two scoped re-judgments. Re-judgment sees only the frozen ledger plus fix delta and may record fix-caused defects.
The only terminal verdicts are APPROVED | ESCALATED; never reset or extend an exhausted round budget.
A judgment issues no receipt and carries no delivery authority: it satisfies no commit, push, PR, or release gate. When the caller explicitly wants ordinary negotiated review for the same target, run it as its own step; neither outcome authorizes delivery, which remains under ordinary repository policy.
Decision Gates
Condition
Action
Target unclear
Ask one scope question and stop.
Both judges confirm severe finding
Ask before round-one correction; then use the bounded fix actor.
One judge reports it
Record suspect; do not auto-fix.
Judges contradict
Escalate for explicit human decision.
Scoped re-judgment fails before round two
Parent may launch the final bounded fix round.
Any issue remains after round two
Escalate and stop.
Execution Steps
Build the complete immutable target and freeze the scope both judges will inspect.
Launch both read-only judges in parallel (jd-judge-a, jd-judge-b) against the same immutable target.
Merge findings into the frozen ledger and persist it through the selected artifact store.
Ask before round-one correction; run the fix actor (jd-fix-agent) only for confirmed severe IDs.
Run both judges again (jd-judge-a, jd-judge-b) only over the frozen ledger plus immutable fix delta.
Repeat once at most, then run independent final verification and return the terminal verdict.
Output Contract
Return target identity, round, confirmed/suspect/contradiction/INFO counts, correction work units, scoped re-judgment result, artifact references, skill resolution, and exactly one final JUDGMENT: APPROVED ✅ or JUDGMENT: ESCALATED ⚠️.