judgment-day
Skill12 starsChanged 14 days agoMITView on GitHub
Trigger: judgment day, dual review, adversarial review, juzgar. Run explicit blind dual review with at most two scoped fix/re-judgment rounds.
3 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- upex-galaxy/agentic-qa-boilerplatetheir own version, first seen Nov 7, 2026
- svg153/skillstheir own version, first seen Nov 1, 2026
- AndyTechnologies/my-own-skillsedited, first seen Oct 8, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- AndyTechnologies/my-own-skills★ 060% same
Wrote their own version · 2
- upex-galaxy/agentic-qa-boilerplate★ 26same name
- svg153/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/skills/react-doctor/AGENTS.mdAGENTS.md
- .claude/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-agent-developmentSkill
- angular-developerSkill
- api-design-principlesSkill
- aws-serverlessSkill
- brainstormingSkill
- cavemanSkill
- cognitive-doc-designSkill
- diagram-designSkill
- error-handling-patternsSkill
- frontend-designSkill
- golang-proSkill
- gsap-animationSkill
- impeccable-bridgeSkill
- impeccableSkill
- kaizenSkill
- nestjs-expertSkill
- product-manager-toolkitSkill
- pr-reviewSkill
- react-doctorSkill
- security-auditSkill
- seo-auditSkill
- shadcn-uiSkill
- social-marketingSkill
- software-architectSkill
- stitch-designSkill
- systematic-debuggingSkill
- tailwind-design-systemSkill
- tddSkill
- ui-ux-pro-maxSkill
- vercel-react-best-practicesSkill
- video-productionSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Never launch review-refuter.
- Distinctive: line 23
Only the parent orchestrator merges/persists findings, launches the fix actor, launches scoped re-judgment, and updates native counters.
- Very specific: line 57
Start review/start(target, mode=judgment_day) and persist the transaction.
- Distinctive: line 60
Ask before round-one correction.
- Distinctive: line 61
Run both judges again only over the frozen ledger plus immutable fix delta.
- Distinctive: line 88
Prefer running the two judges on a model different from the one that authored the design (author ≠ auditor, per AKILI model routing).
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Activation Contract
Load only when the user explicitly requests Judgment Day or equivalent dual/adversarial review for a concrete target. Judgment Day replaces ordinary 4R for that target; never run both.
Hard Rules
- Resolve matching project skills before starting and pass the same paths to both judges and any fix actor.
- 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, launches scoped re-judgment, and updates native counters.
- Fix only severe findings confirmed by both judges. WARNING/SUGGESTION rows remain
info. - Judges must contrast every count, total, and quantity the target asserts against the prose of the other in-scope documents. Documents agreeing with each other is not corroboration — it is often one wrong idea copied forward; a figure contradicted by any in-scope document's own prose is a finding.
Before any other reading, judges attack the design's Premise Ledger at its source: re-run or re-read every citation, try to refute every
UNVERIFIEDrow with their own search, and look for premises the design depends on that carry no row. A premise is never accepted because the requirements and the design agree on it — only the source settles it. Row shape, classes, and triggers are defined in/akili-specifyStep 2.2 — Premise Ledger block and are not restated here; this rule sets only what a bad row costs.A row the citations cannot settle is attacked, not merely scored. Action 1 needs a citation and action 2 is written for the marker, so two row states fall between them: a citation cell holding neither a citation as run nor the
UNVERIFIEDmarker, and a citation naming a secondary source rather than the primary one. Which sources count as secondary is set by citation rule (d) of the/akili-specifyStep 2.2 — Premise Ledger block, and is not restated here. Both states are attacked under action 2, as though the row carried the marker: the judge searches for the primary source itself and reports what that search returns, includingnot re-runwhere its host cannot reach that source. Re-reading a document settles that document, never the system it describes, so a document that agrees with the design is not confirmation. Recording a severity from the table below without attempting that refutation does not discharge this rule.Judge finds Severity The source contradicts a premise severe A citation does not reproduce at its verified-at commit severe The design names existing code and has no Premise Ledger, or a false stated-empty line severe A triggered class with no row severe A depended-on premise with no row finding, severity by Impact A premise confirmed not a finding Read-only is not no-search. A read-only judge writes nothing. Within that contract it may read and search the repository, and read its history where the host allows (the packaged judge tool set searches but has no shell). A judge that cannot run a cited command re-derives from the cited files where feasible and reports that row
not re-run— never as confirmed. The protocol is unchanged: two-judge confirmation still gates auto-fix, and a premise contradiction reported by one judge is recorded as suspect with its command as run, so the architect settles it with a single re-run.- 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.
- Terminal transaction states are only
approved | escalated; never reset or extend an exhausted lineage.
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
- Start
review/start(target, mode=judgment_day)and persist the transaction. - Launch both read-only judges 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 only for confirmed severe IDs.
- Run both judges again only over the frozen ledger plus immutable fix delta.
- Repeat once at most, then run independent final verification and emit the terminal receipt.
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 ⚠️.
References
- ../_shared/review-ledger-contract.md — canonical transaction, ledger, persistence, and lifecycle contract.
- references/prompts-and-formats.md — compact judge/fix prompts and verdict shape.
These reference files are not packaged with AKILI-SPECS. When they are unavailable, proceed with the contract described in this document alone: persist the findings ledger inside the spec folder (see below) and derive judge prompts from the Hard Rules and Output Contract.
AKILI-SPECS Integration
| AKILI moment | How to use this skill |
/akili-specify Step 2.5 — Present & Approve, Review Design option | The user-selected blind dual review of design.md before tasks are written; the target is the approved requirements + draft design, and judges attack the Premise Ledger first |
/akili-review Step 3 — Merge and Verify, full tier (via the pr-review skill) | Two blind judges per critical finding (blind protocol only, no fix rounds); a critical only one judge confirms becomes a warning with suspect: true. lite uses one verifier pass and trivial none, so they do not run this protocol |
/akili-archive Kaizen Measure | Severe confirmed findings from Judgment Day runs are a signal row in the kaizen retrospective |
Adaptation rules:
- Persist the findings ledger as
docs/specs/<spec-path>/judgment.mdso/akili-archivecan read it as evidence. - The two-judge blind protocol, the two-round fix ceiling, and the
APPROVED/ESCALATEDterminal states apply unchanged. - Under AKILI
pre-approvedthe review still runs. A target corrected without re-judgment (/akili-specifyStep 2.5 Fix only) closesjudgment.mdwith the AKILI annotationfixed, not re-judgedplus the fixed finding IDs, neverJUDGMENT: APPROVED. The annotation is an AKILI-layer record; this skill's terminal states stay unchanged (see Hard Rules). - Prefer running the two judges on a model different from the one that authored the design (author ≠ auditor, per AKILI model routing).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

