Update to WZRD

{
  "description": "Review, create, or refine WZRD rooms, product flows, visual design, and interface copy using the WZRD brand system and product-trust principles. Use for WZRD brand checks, UX writing, room critiques, launch-readiness audits, guest-sharing flows, AI behavior, and implementation decisions. Do not use for unrelated products or generic wizard-themed work.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 200
    },
    {
      "relative_path": "references/brand-system.md",
      "size_in_bytes": 4294
    },
    {
      "relative_path": "references/product-trust.md",
      "size_in_bytes": 5223
    }
  ],
  "name": "wzrd-review",
  "skill_md_contents": "---\nname: wzrd-review\ndescription: Review, create, or refine WZRD rooms, product flows, visual design, and interface copy using the WZRD brand system and product-trust principles. Use for WZRD brand checks, UX writing, room critiques, launch-readiness audits, guest-sharing flows, AI behavior, and implementation decisions. Do not use for unrelated products or generic wizard-themed work.\n---\n\n# WZRD Review\n\nHelp make WZRD feel like one calm, attentive intelligence across every surface. Ground conclusions in the artifact the user supplied or the behavior you can inspect; treat the references as decision criteria, not as evidence that a current defect still exists.\n\n## Route the work\n\n- Read [references/brand-system.md](references/brand-system.md) for visual design, interaction, naming, or copy work.\n- Read [references/product-trust.md](references/product-trust.md) for room reviews, guest journeys, sharing, permissions, AI behavior, launch readiness, mobile, accessibility, analytics, or reliability.\n- Read both when reviewing an end-to-end experience or creating a product surface.\n\n## Review method\n\n1. Identify the artifact, audience, user goal, and stage of the journey. Ask only when a missing choice would materially change the result.\n2. Inspect the actual artifact or behavior. Separate observed evidence from inference and from recommendations.\n3. Check the relevant brand and product-trust criteria. Preserve the user's explicit product direction unless it creates a concrete trust, safety, accessibility, or brand conflict.\n4. Prioritize findings:\n   - **P0:** misleading success, broken primary actions, unsafe sharing or permissions, lost work, false AI claims, or blockers to the core journey.\n   - **P1:** material beta risk in comprehension, mobile use, accessibility, grounding, recovery, or measurement.\n   - **P2:** polish, consistency, and optimization.\n5. Lead with the verdict and the smallest set of changes that materially improves the experience. For each issue, state the evidence, why it matters, and the recommended change.\n\n## Creating or editing\n\n- Apply WZRD's visual and language system without turning every surface into a brand showcase. Calmness and clarity come before decoration.\n- Use normal product language. Prefer short, spoken phrases and one idea at a time.\n- Keep AI claims exact. Do not imply that content was changed, a person was notified, an action completed, or data was retained unless that outcome is verified.\n- For implementation requests, make the requested change, then verify the rendered result and the relevant primary journey. Do not expand a review request into a live mutation.\n\n## Output defaults\n\nFor a review, use a compact structure:\n\n- Verdict\n- Findings grouped by P0, P1, and P2; omit empty groups\n- Recommended next move\n\nFor copy work, provide the finished copy first, followed by only the rationale needed to explain important choices.\n"
}