Cross-document consistency check: detects GDD entities with conflicting stats, values, or formulas.
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Detects cross-document inconsistencies by comparing GDDs against entity registry (design/registry/entities.yaml). Grep-first: read registry once, then grep only matching names — no full document reads.
Run: after each new GDD, and before /architecture-decision. Output: conflict report + optional registry corrections.
| Mode | Behavior |
|---|---|
full / no arg | All registered entries vs all GDDs |
since-last-review | Only GDDs modified since last review report |
entity:<name> | One entity across all GDDs |
item:<name> | One item across all GDDs |
Read design/registry/entities.yaml. Empty/missing → stop ("Run /design-system to populate"). Build lookup tables: entity_map, item_map, formula_map, constant_map.
Glob design/gdd/*.md (exclude game-concept, systems-index, game-pillars). For since-last-review: git log to find GDDs modified since last gdd-cross-review-*.md.
For each registered entry, grep all in-scope GDDs for the name (-C 3 context). Extract values near the name and compare against registry.
| Scan | Extract | Compare |
|---|---|---|
| Entity | Numeric/categorical attributes, derived values | Registry attribute values |
| Item | Sell price, weight, stack rules, category | Registry item values |
| Formula | Variable names, output range/caps | Registry formula vars + range |
| Constant | Numeric values near name | Registry value |
Classification: CONFLICT (different values), NOTE (mentioned but unverifiable).
Full-section read of conflicting GDD. Determine: which GDD is correct (source field = authoritative owner), is registry stale (source GDD updated after registry), is this intentional design change?
Categories: 🔴 CONFLICT (different values, must resolve), ⚠️ STALE REGISTRY (source changed but registry not updated), ℹ️ UNVERIFIABLE (no comparable attribute stated).
Registry entries checked + GDDs scanned + conflicts (entry/attribute/values/resolution needed) + stale entries (registry vs source GDD) + unverifiable references + clean entries count.
Verdict: PASS (no conflicts) or CONFLICTS FOUND (list resolution steps).
Stale entries → ask to update registry (update value, set revised date, comment old value). New entries in GDDs not in registry → ask to add (only if appears in 2+ GDDs). Never delete — set status: deprecated.
If 🔴 conflicts found → append to docs/consistency-failures.md (if exists): date, domain, docs involved, what happened, resolution, pattern/lesson.
/architecture-decisionsource: field) is authoritative ownerNo reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan, design, and implement A/B tests and experiments with statistical rigor. Covers hypothesis frameworks, sample sizing, metrics, and result analysis.
The English summary is being prepared. Showing the original description.
Web/mobile accessibility decision guide: WCAG 2.2 AA, ARIA, keyboard nav, focus management, contrast, testing. Use for: a11y, accessibility, wcag, aria, screen reader, keyboard, contrast.
The English summary is being prepared. Showing the original description.
Generate, iterate, and scale ad creative for paid advertising across Google, Meta, LinkedIn, and X. Covers platform specs, creative frameworks, and quality validation.
The English summary is being prepared. Showing the original description.
Musica interactiva para juegos: layering vertical, re-secuenciacion horizontal, stingers, reglas de transicion con sync points, y mapeo de estados de gameplay a musica. Usar para: musica adaptativa, sistema de musica dinamica, transiciones musicales, combat music.
The English summary is being prepared. Showing the original description.
Design multi-agent systems, create agent architectures, define communication patterns, and build autonomous agent workflows with structured evaluation frameworks.
The English summary is being prepared. Showing the original description.
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, response formats, and quality loops.
The English summary is being prepared. Showing the original description.