reference/output-formats.md | you need the exact report template or section structure |
reference/design-methodology.md | you need the full per-mode process, phase order, or pre-check rules |
reference/design-trends.md | you need current trend buckets, AI-tool guardrails, or trend-evaluation rules |
reference/agent-orchestration.md | you need delegation flow or Accord validation |
reference/design-system-anti-patterns.md | you need token architecture, naming, theming, or design-system risk screening |
reference/ux-anti-patterns-ethics.md | you need dark-pattern, accessibility, or ethical-design checks |
reference/design-handoff-collaboration.md | you need handoff readiness, state coverage, or dev-collaboration rules |
reference/design-review-feedback.md | you need critique structure, review cadence, or feedback quality rules |
reference/brand-strategy.md | you need brand identity strategy, voice keyword definition, multi-brand orchestration, or brand-fit scoring |
reference/moodboard-curation.md | you are running ENVISION moodboard curation: directional axes, candidate-to-finalist narrowing, anti-keywords |
reference/design-audit-checklist.md | you are running REVIEW-mode audit: Nielsen heuristics, WCAG 2.2 AA pass-fail grid, token-drift detection, prioritized backlog |
reference/co-design-pair.md | you are running the pair recipe — driver/navigator roles, the SETUP → per-decision LOOP (propose options → choose → produce/delegate → confirm → checkpoint) → CLOSE flow, options-first evidence bar, no-code delegation, termination bounds, checkpoint-resume, and the pair VERIFY gate |
_common/BOUNDARIES.md | role boundaries are ambiguous |
reference/composition-principles.md | you need first-viewport rules, hero contract, layout restraint, image strategy, or page structure |
reference/linear-restraint-mode.md | you need Linear-style restraint: calm surfaces, minimal chrome, card usage rules, or app vs marketing guidance |
_common/OPERATIONAL.md | you need journal, activity log, AUTORUN, Nexus, or shared operational defaults |
_common/UX_TRENDS_2026.md | you need 2025-2026 web-sourced direction signals — OS design languages (Liquid Glass, M3 Expressive), brand-system case studies (Polaris Unified, Primer, Radix Themes 3.0), and current visual-language standards. Read §1 Design. |
_common/OPUS_5_AUTHORING.md | you are sizing the direction/critique report, deciding adaptive thinking depth at DIRECT/CRITIQUE, or front-loading brand/scope at SURVEY. Critical for Vision: P3, P5 |
_common/IMAGE_INPUT.md | you are reading brand assets, competitor screenshots, or mockups as input — apply the image pipeline (RECOGNIZE→PARSE→ANALYZE, describe-first, observed-vs-inferred) before direction or critique |
reference/tri-engine-direction.md | you are running the multi Recipe — tri-engine fan-out (Codex + Antigravity + Claude subagents), Concurrence-Divergence scoring, aesthetic-spectrum coverage rules, Portfolio (default) vs Compete (opt-in) merge strategies, JSON schema, subagent prompt skeletons, GROUND brand/persona/a11y/AI-disclosure checks, and downstream handoff stubs |
_common/SUBAGENT.md | you need the base MULTI_ENGINE protocol — engine dispatch table, loose prompt rules, Agent tool fan-out mechanics, fallback rules. Read before authoring multi Recipe subagent prompts |
_common/MULTI_ENGINE_RECIPE.md | you need the canonical Pattern D protocol (SCOPE → PREFLIGHT → FAN-OUT → NORMALIZE → CLUSTER → SCORE → GROUND/CALIBRATE → SYNTHESIZE → DELIVER), engine-attribution tag conventions, and degraded-mode rules shared across all multi Recipe skills |
_common/PROPORTION_AND_SPACING.md | you are justifying a direction's proportional system — modular/type scale ratio choice (1.2-1.25 product vs 1.333-1.618 editorial), grid column and container decisions, composition claims (optical vs geometric center, rule of thirds, F- vs Z-pattern evidence asymmetry). Read §1 and §10 before invoking the golden ratio in a direction rationale — φ-as-beauty-law is contested, and asserting it unqualified is a grounding failure. |
_common/PROOF_CARRYING.md | You issue brand_proof advisory in nexus acceptance Phase 4B (LLM-as-judge, non-blocking per Unspecifiable-Quality Carve-Out). Brand voice / illustration style / motion feel / emotional appropriateness route to G7 Unmeasurable-Quality Audit Gate for Tier-S UI human sign-off (≥10 min recorded). Avoid the "AI Design Reviewer" anti-pattern — operate as Design Compiler, not approver. |
reference/autorun-schema.md | You are emitting the AUTORUN _STEP_COMPLETE block — Vision-specific Output/Next schema. |
reference/apple-design-trends.md | you need Apple-platform design direction and taste — Liquid Glass adoption judgment, direction archetypes, Apple Design Award pattern analysis, macOS-specific direction, or cross-platform coherence (not HIG normative rules — those live in native/reference/ios-hig.md) |