Activation Contract
Load this skill only when the user explicitly asks for Judgment Day, dual/adversarial review, or equivalent Spanish trigger (juzgar, que lo juzguen). Review a specific target: files, feature, PR, or architecture slice.
Hard Rules
- Resolve project skills before launching agents: read skill registry, match skill paths by target files/task, and inject the same
Skills to load before work block into both judge prompts and fix prompts.
- Launch two blind judges in parallel with identical target and criteria; never review the code yourself.
- Wait for both judges before synthesis; never accept a partial verdict.
- Classify warnings as
WARNING (real) only if normal intended use can trigger them; otherwise downgrade to INFO as WARNING (theoretical).
- Ask before fixing Round 1 confirmed issues.
- After any fix agent runs, immediately re-launch both judges in parallel before commit/push/done/session summary.
- Terminal states are only
JUDGMENT: APPROVED or JUDGMENT: ESCALATED.
- After 2 fix iterations with remaining issues, ask the user whether to continue.
Decision Gates
| Condition |
Action |
| Target unclear |
Ask for scope; do not launch judges. |
| No skill registry |
Warn, proceed with generic criteria, and record Skill Resolution: none. |
| Both judges find same CRITICAL/real WARNING |
Confirmed; ask/fix according to round rules. |
| One judge finds issue |
Suspect; report and triage, do not auto-fix. |
| Judges contradict |
Escalate for manual decision. |
| Round 2+ has only theoretical warnings/suggestions |
Report as INFO; do not re-judge. |
Execution Steps
- Confirm target and optional custom criteria.
- Resolve exact skill paths from registry or warn if missing.
- Start Judge A and Judge B concurrently via delegation.
- Synthesize findings into confirmed, suspect, contradiction, and INFO buckets.
- Ask before Round 1 fixes; delegate a separate fix agent for confirmed approved fixes only.
- Re-judge in parallel after fixes; repeat until approved, escalated, or user asks to stop.
- Before any terminal action, verify every active Judgment Day has a terminal state.
Output Contract
Return ## Judgment Day — {target} with round number, verdict table, confirmed/suspect/contradiction counts, fixes applied, re-judgment result, Skill Resolution, and final JUDGMENT: APPROVED ✅ or JUDGMENT: ESCALATED ⚠️.
References
- references/prompts-and-formats.md — judge/fix prompts, warning rubric, verdict tables, and language snippets.
1---2name: judgment-day3description: Trigger: judgment day, dual review, adversarial review, juzgar. Run blind dual review, fix confirmed issues, then re-judge.4license: Apache-2.05---67## Activation Contract89Load this skill only when the user explicitly asks for Judgment Day, dual/adversarial review, or equivalent Spanish trigger (`juzgar`, `que lo juzguen`). Review a specific target: files, feature, PR, or architecture slice.1011## Hard Rules1213- Resolve project skills before launching agents: read skill registry, match skill paths by target files/task, and inject the same `Skills to load before work` block into both judge prompts and fix prompts.14- Launch **two blind judges in parallel** with identical target and criteria; never review the code yourself.15- Wait for both judges before synthesis; never accept a partial verdict.16- Classify warnings as `WARNING (real)` only if normal intended use can trigger them; otherwise downgrade to INFO as `WARNING (theoretical)`.17- Ask before fixing Round 1 confirmed issues.18- After any fix agent runs, immediately re-launch both judges in parallel before commit/push/done/session summary.19- Terminal states are only `JUDGMENT: APPROVED` or `JUDGMENT: ESCALATED`.20- After 2 fix iterations with remaining issues, ask the user whether to continue.2122## Decision Gates2324| Condition | Action |25|---|---|26| Target unclear | Ask for scope; do not launch judges. |27| No skill registry | Warn, proceed with generic criteria, and record `Skill Resolution: none`. |28| Both judges find same CRITICAL/real WARNING | Confirmed; ask/fix according to round rules. |29| One judge finds issue | Suspect; report and triage, do not auto-fix. |30| Judges contradict | Escalate for manual decision. |31| Round 2+ has only theoretical warnings/suggestions | Report as INFO; do not re-judge. |3233## Execution Steps34351. Confirm target and optional custom criteria.362. Resolve exact skill paths from registry or warn if missing.373. Start Judge A and Judge B concurrently via delegation.384. Synthesize findings into confirmed, suspect, contradiction, and INFO buckets.395. Ask before Round 1 fixes; delegate a separate fix agent for confirmed approved fixes only.406. Re-judge in parallel after fixes; repeat until approved, escalated, or user asks to stop.417. Before any terminal action, verify every active Judgment Day has a terminal state.4243## Output Contract4445Return `## Judgment Day — {target}` with round number, verdict table, confirmed/suspect/contradiction counts, fixes applied, re-judgment result, `Skill Resolution`, and final `JUDGMENT: APPROVED ✅` or `JUDGMENT: ESCALATED ⚠️`.4647## References4849- [references/prompts-and-formats.md](references/prompts-and-formats.md) — judge/fix prompts, warning rubric, verdict tables, and language snippets.
JantonioFC