@bonesofspring/ai-rules 0.2.17 → 0.2.18
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +18 -0
- package/README.md +1 -1
- package/package.json +1 -1
- package/presets/_shared/README.md +1 -1
- package/presets/_shared/core/agent-team/agent-artifact-contracts.md +3 -0
- package/presets/_shared/core/agent-team/agent-team-orchestrator.md +4 -4
- package/presets/_shared/core/architecture/feature-delivery-workflow.md +1 -1
- package/presets/_shared/core/meta/preset-no-cross-stack-leakage.md +4 -2
- package/presets/_shared/core/review/mockup-review.md +105 -0
- package/presets/_shared/core/review/ux-design.md +97 -0
- package/presets/claude/android-kotlin/agents/README.md +2 -2
- package/presets/claude/android-kotlin/agents/build-verifier.md +6 -0
- package/presets/claude/android-kotlin/agents/feature-developer.md +6 -0
- package/presets/claude/android-kotlin/agents/mockup-reviewer.md +59 -0
- package/presets/claude/android-kotlin/agents/task-analyst.md +18 -1
- package/presets/claude/android-kotlin/agents/task-router.md +11 -2
- package/presets/claude/android-kotlin/commands/task-continue.md +6 -4
- package/presets/claude/android-kotlin/commands/task.md +2 -0
- package/presets/claude/android-kotlin/hooks/chain-team-phases.sh +26 -0
- package/presets/claude/android-kotlin/rules/README.md +2 -0
- package/presets/claude/android-kotlin/rules/architecture/feature-delivery.md +2 -0
- package/presets/claude/android-kotlin/rules/tooling-and-review/agent-team-orchestrator.md +6 -3
- package/presets/claude/android-kotlin/rules/tooling-and-review/mockup-review.md +118 -0
- package/presets/claude/android-kotlin/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -3
- package/presets/claude/android-kotlin/rules/tooling-and-review/ux-design.md +110 -0
- package/presets/claude/android-kotlin/skills/README.md +2 -0
- package/presets/claude/android-kotlin/skills/feature-delivery/SKILL.md +3 -0
- package/presets/claude/android-kotlin/skills/mockup-review/SKILL.md +29 -0
- package/presets/claude/android-kotlin/skills/ux-design/SKILL.md +36 -0
- package/presets/claude/android-kotlin/team/fixtures/artifact-manifest.example.json +25 -0
- package/presets/claude/android-kotlin/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/claude/android-kotlin/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/claude/android-kotlin/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/claude/android-kotlin/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/claude/android-kotlin/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/claude/go/MCP.md +1 -1
- package/presets/claude/go/agents/build-verifier.md +6 -0
- package/presets/claude/go/agents/task-router.md +1 -1
- package/presets/claude/go/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/ios-swift/agents/README.md +2 -2
- package/presets/claude/ios-swift/agents/build-verifier.md +6 -0
- package/presets/claude/ios-swift/agents/feature-developer.md +6 -0
- package/presets/claude/ios-swift/agents/mockup-reviewer.md +59 -0
- package/presets/claude/ios-swift/agents/task-analyst.md +18 -1
- package/presets/claude/ios-swift/agents/task-router.md +11 -2
- package/presets/claude/ios-swift/commands/task-continue.md +6 -4
- package/presets/claude/ios-swift/commands/task.md +2 -0
- package/presets/claude/ios-swift/hooks/chain-team-phases.sh +26 -0
- package/presets/claude/ios-swift/rules/README.md +4 -0
- package/presets/claude/ios-swift/rules/architecture/feature-delivery.md +2 -0
- package/presets/claude/ios-swift/rules/tooling-and-review/agent-team-orchestrator.md +6 -3
- package/presets/claude/ios-swift/rules/tooling-and-review/mockup-review.md +118 -0
- package/presets/claude/ios-swift/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/ios-swift/rules/tooling-and-review/ux-design.md +110 -0
- package/presets/claude/ios-swift/skills/README.md +2 -0
- package/presets/claude/ios-swift/skills/feature-delivery/SKILL.md +3 -0
- package/presets/claude/ios-swift/skills/mockup-review/SKILL.md +29 -0
- package/presets/claude/ios-swift/skills/ux-design/SKILL.md +36 -0
- package/presets/claude/ios-swift/team/fixtures/artifact-manifest.example.json +25 -0
- package/presets/claude/ios-swift/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/claude/ios-swift/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/claude/ios-swift/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/claude/ios-swift/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/claude/ios-swift/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/claude/java/agents/build-verifier.md +7 -1
- package/presets/claude/java/agents/task-router.md +1 -1
- package/presets/claude/java/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/mcp-ts/agents/build-verifier.md +7 -1
- package/presets/claude/mcp-ts/agents/task-router.md +1 -1
- package/presets/claude/mcp-ts/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/next/agents/README.md +2 -1
- package/presets/claude/next/agents/build-verifier.md +6 -0
- package/presets/claude/next/agents/feature-developer.md +6 -0
- package/presets/claude/next/agents/mockup-reviewer.md +59 -0
- package/presets/claude/next/agents/task-analyst.md +18 -1
- package/presets/claude/next/agents/task-router.md +12 -3
- package/presets/claude/next/commands/task-continue.md +6 -4
- package/presets/claude/next/commands/task.md +2 -0
- package/presets/claude/next/hooks/chain-team-phases.sh +26 -0
- package/presets/claude/next/rules/README.md +5 -1
- package/presets/claude/next/rules/architecture/feature-delivery-workflow.md +2 -0
- package/presets/claude/next/rules/tooling-and-review/agent-team-orchestrator.md +6 -3
- package/presets/claude/next/rules/tooling-and-review/mockup-review.md +118 -0
- package/presets/claude/next/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/next/rules/tooling-and-review/ux-design.md +110 -0
- package/presets/claude/next/skills/README.md +2 -0
- package/presets/claude/next/skills/feature-delivery/SKILL.md +3 -0
- package/presets/claude/next/skills/mockup-review/SKILL.md +29 -0
- package/presets/claude/next/skills/ux-design/SKILL.md +36 -0
- package/presets/claude/next/team/fixtures/artifact-manifest.example.json +20 -2
- package/presets/claude/next/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/claude/next/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/claude/next/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/claude/next/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/claude/next/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/claude/nuxt/agents/README.md +2 -1
- package/presets/claude/nuxt/agents/build-verifier.md +6 -0
- package/presets/claude/nuxt/agents/feature-developer.md +6 -0
- package/presets/claude/nuxt/agents/mockup-reviewer.md +59 -0
- package/presets/claude/nuxt/agents/task-analyst.md +18 -1
- package/presets/claude/nuxt/agents/task-router.md +12 -3
- package/presets/claude/nuxt/commands/task-continue.md +6 -4
- package/presets/claude/nuxt/commands/task.md +2 -0
- package/presets/claude/nuxt/hooks/chain-team-phases.sh +26 -0
- package/presets/claude/nuxt/rules/README.md +4 -0
- package/presets/claude/nuxt/rules/architecture/feature-delivery-workflow.md +2 -0
- package/presets/claude/nuxt/rules/tooling-and-review/agent-team-orchestrator.md +6 -3
- package/presets/claude/nuxt/rules/tooling-and-review/mockup-review.md +118 -0
- package/presets/claude/nuxt/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/nuxt/rules/tooling-and-review/ux-design.md +110 -0
- package/presets/claude/nuxt/skills/README.md +2 -0
- package/presets/claude/nuxt/skills/feature-delivery/SKILL.md +3 -0
- package/presets/claude/nuxt/skills/mockup-review/SKILL.md +29 -0
- package/presets/claude/nuxt/skills/ux-design/SKILL.md +36 -0
- package/presets/claude/nuxt/team/fixtures/artifact-manifest.example.json +20 -2
- package/presets/claude/nuxt/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/claude/nuxt/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/claude/nuxt/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/claude/nuxt/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/claude/nuxt/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/claude/php-hexagonal/agents/build-verifier.md +7 -1
- package/presets/claude/php-hexagonal/agents/task-router.md +1 -1
- package/presets/claude/php-hexagonal/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/php-laravel/agents/build-verifier.md +7 -1
- package/presets/claude/php-laravel/agents/task-router.md +1 -1
- package/presets/claude/php-laravel/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/svelte/agents/README.md +2 -1
- package/presets/claude/svelte/agents/build-verifier.md +6 -0
- package/presets/claude/svelte/agents/feature-developer.md +6 -0
- package/presets/claude/svelte/agents/mockup-reviewer.md +59 -0
- package/presets/claude/svelte/agents/task-analyst.md +18 -1
- package/presets/claude/svelte/agents/task-router.md +12 -3
- package/presets/claude/svelte/commands/task-continue.md +6 -4
- package/presets/claude/svelte/commands/task.md +2 -0
- package/presets/claude/svelte/hooks/chain-team-phases.sh +26 -0
- package/presets/claude/svelte/rules/README.md +4 -0
- package/presets/claude/svelte/rules/architecture/feature-delivery-workflow.md +2 -0
- package/presets/claude/svelte/rules/tooling-and-review/agent-team-orchestrator.md +6 -3
- package/presets/claude/svelte/rules/tooling-and-review/mockup-review.md +118 -0
- package/presets/claude/svelte/rules/tooling-and-review/preset-no-cross-stack-leakage.md +4 -2
- package/presets/claude/svelte/rules/tooling-and-review/ux-design.md +110 -0
- package/presets/claude/svelte/skills/README.md +2 -0
- package/presets/claude/svelte/skills/feature-delivery/SKILL.md +3 -0
- package/presets/claude/svelte/skills/mockup-review/SKILL.md +29 -0
- package/presets/claude/svelte/skills/ux-design/SKILL.md +36 -0
- package/presets/claude/svelte/team/fixtures/artifact-manifest.example.json +20 -2
- package/presets/claude/svelte/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/claude/svelte/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/claude/svelte/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/claude/svelte/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/claude/svelte/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/cursor/android-kotlin/agents/README.md +2 -2
- package/presets/cursor/android-kotlin/agents/build-verifier.md +6 -0
- package/presets/cursor/android-kotlin/agents/feature-developer.md +6 -0
- package/presets/cursor/android-kotlin/agents/mockup-reviewer.md +60 -0
- package/presets/cursor/android-kotlin/agents/task-analyst.md +18 -1
- package/presets/cursor/android-kotlin/agents/task-router.md +11 -2
- package/presets/cursor/android-kotlin/commands/task-continue.md +6 -4
- package/presets/cursor/android-kotlin/commands/task.md +2 -0
- package/presets/cursor/android-kotlin/hooks/chain-team-phases.sh +26 -0
- package/presets/cursor/android-kotlin/rules/README.md +4 -0
- package/presets/cursor/android-kotlin/rules/agent-team-orchestrator.mdc +6 -3
- package/presets/cursor/android-kotlin/rules/feature-delivery-workflow.mdc +2 -0
- package/presets/cursor/android-kotlin/rules/mockup-review.mdc +116 -0
- package/presets/cursor/android-kotlin/rules/preset-no-cross-stack-leakage.mdc +4 -3
- package/presets/cursor/android-kotlin/rules/ux-design.mdc +108 -0
- package/presets/cursor/android-kotlin/skills/README.md +2 -0
- package/presets/cursor/android-kotlin/skills/feature-delivery/SKILL.md +3 -0
- package/presets/cursor/android-kotlin/skills/mockup-review/SKILL.md +29 -0
- package/presets/cursor/android-kotlin/skills/ux-design/SKILL.md +36 -0
- package/presets/cursor/android-kotlin/team/fixtures/artifact-manifest.example.json +25 -0
- package/presets/cursor/android-kotlin/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/cursor/android-kotlin/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/cursor/android-kotlin/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/cursor/android-kotlin/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/cursor/android-kotlin/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/cursor/go/MCP.md +1 -1
- package/presets/cursor/go/agents/build-verifier.md +6 -0
- package/presets/cursor/go/agents/task-router.md +1 -1
- package/presets/cursor/go/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/ios-swift/agents/README.md +2 -2
- package/presets/cursor/ios-swift/agents/build-verifier.md +6 -0
- package/presets/cursor/ios-swift/agents/feature-developer.md +6 -0
- package/presets/cursor/ios-swift/agents/mockup-reviewer.md +60 -0
- package/presets/cursor/ios-swift/agents/task-analyst.md +18 -1
- package/presets/cursor/ios-swift/agents/task-router.md +11 -2
- package/presets/cursor/ios-swift/commands/task-continue.md +6 -4
- package/presets/cursor/ios-swift/commands/task.md +2 -0
- package/presets/cursor/ios-swift/hooks/chain-team-phases.sh +26 -0
- package/presets/cursor/ios-swift/rules/README.md +5 -1
- package/presets/cursor/ios-swift/rules/agent-team-orchestrator.mdc +6 -3
- package/presets/cursor/ios-swift/rules/feature-delivery-workflow.mdc +2 -0
- package/presets/cursor/ios-swift/rules/mockup-review.mdc +116 -0
- package/presets/cursor/ios-swift/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/ios-swift/rules/ux-design.mdc +108 -0
- package/presets/cursor/ios-swift/skills/README.md +2 -0
- package/presets/cursor/ios-swift/skills/feature-delivery/SKILL.md +3 -0
- package/presets/cursor/ios-swift/skills/mockup-review/SKILL.md +29 -0
- package/presets/cursor/ios-swift/skills/ux-design/SKILL.md +36 -0
- package/presets/cursor/ios-swift/team/fixtures/artifact-manifest.example.json +25 -0
- package/presets/cursor/ios-swift/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/cursor/ios-swift/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/cursor/ios-swift/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/cursor/ios-swift/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/cursor/ios-swift/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/cursor/java/agents/build-verifier.md +7 -1
- package/presets/cursor/java/agents/task-router.md +1 -1
- package/presets/cursor/java/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/mcp-ts/agents/build-verifier.md +7 -1
- package/presets/cursor/mcp-ts/agents/task-router.md +1 -1
- package/presets/cursor/mcp-ts/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/next/agents/README.md +2 -1
- package/presets/cursor/next/agents/build-verifier.md +6 -0
- package/presets/cursor/next/agents/feature-developer.md +6 -0
- package/presets/cursor/next/agents/mockup-reviewer.md +60 -0
- package/presets/cursor/next/agents/task-analyst.md +18 -1
- package/presets/cursor/next/agents/task-router.md +12 -3
- package/presets/cursor/next/commands/task-continue.md +6 -4
- package/presets/cursor/next/commands/task.md +2 -0
- package/presets/cursor/next/hooks/chain-team-phases.sh +26 -0
- package/presets/cursor/next/rules/README.md +3 -1
- package/presets/cursor/next/rules/agent-team-orchestrator.mdc +6 -3
- package/presets/cursor/next/rules/feature-delivery-workflow.mdc +2 -0
- package/presets/cursor/next/rules/mockup-review.mdc +116 -0
- package/presets/cursor/next/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/next/rules/ux-design.mdc +108 -0
- package/presets/cursor/next/skills/README.md +2 -0
- package/presets/cursor/next/skills/feature-delivery/SKILL.md +3 -0
- package/presets/cursor/next/skills/mockup-review/SKILL.md +29 -0
- package/presets/cursor/next/skills/ux-design/SKILL.md +36 -0
- package/presets/cursor/next/team/fixtures/artifact-manifest.example.json +20 -2
- package/presets/cursor/next/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/cursor/next/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/cursor/next/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/cursor/next/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/cursor/next/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/cursor/nuxt/agents/README.md +2 -1
- package/presets/cursor/nuxt/agents/build-verifier.md +6 -0
- package/presets/cursor/nuxt/agents/feature-developer.md +6 -0
- package/presets/cursor/nuxt/agents/mockup-reviewer.md +60 -0
- package/presets/cursor/nuxt/agents/task-analyst.md +18 -1
- package/presets/cursor/nuxt/agents/task-router.md +12 -3
- package/presets/cursor/nuxt/commands/task-continue.md +6 -4
- package/presets/cursor/nuxt/commands/task.md +2 -0
- package/presets/cursor/nuxt/hooks/chain-team-phases.sh +26 -0
- package/presets/cursor/nuxt/rules/README.md +3 -1
- package/presets/cursor/nuxt/rules/agent-team-orchestrator.mdc +6 -3
- package/presets/cursor/nuxt/rules/feature-delivery-workflow.mdc +2 -0
- package/presets/cursor/nuxt/rules/mockup-review.mdc +116 -0
- package/presets/cursor/nuxt/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/nuxt/rules/ux-design.mdc +108 -0
- package/presets/cursor/nuxt/skills/README.md +2 -0
- package/presets/cursor/nuxt/skills/feature-delivery/SKILL.md +3 -0
- package/presets/cursor/nuxt/skills/mockup-review/SKILL.md +29 -0
- package/presets/cursor/nuxt/skills/ux-design/SKILL.md +36 -0
- package/presets/cursor/nuxt/team/fixtures/artifact-manifest.example.json +20 -2
- package/presets/cursor/nuxt/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/cursor/nuxt/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/cursor/nuxt/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/cursor/nuxt/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/cursor/nuxt/team/fixtures/ux-design-standalone.json +15 -0
- package/presets/cursor/php-hexagonal/agents/build-verifier.md +7 -1
- package/presets/cursor/php-hexagonal/agents/task-router.md +1 -1
- package/presets/cursor/php-hexagonal/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/php-laravel/agents/build-verifier.md +7 -1
- package/presets/cursor/php-laravel/agents/task-router.md +1 -1
- package/presets/cursor/php-laravel/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/svelte/agents/README.md +2 -1
- package/presets/cursor/svelte/agents/build-verifier.md +6 -0
- package/presets/cursor/svelte/agents/feature-developer.md +6 -0
- package/presets/cursor/svelte/agents/mockup-reviewer.md +60 -0
- package/presets/cursor/svelte/agents/task-analyst.md +18 -1
- package/presets/cursor/svelte/agents/task-router.md +12 -3
- package/presets/cursor/svelte/commands/task-continue.md +6 -4
- package/presets/cursor/svelte/commands/task.md +2 -0
- package/presets/cursor/svelte/hooks/chain-team-phases.sh +26 -0
- package/presets/cursor/svelte/rules/README.md +3 -1
- package/presets/cursor/svelte/rules/agent-team-orchestrator.mdc +6 -3
- package/presets/cursor/svelte/rules/feature-delivery-workflow.mdc +2 -0
- package/presets/cursor/svelte/rules/mockup-review.mdc +116 -0
- package/presets/cursor/svelte/rules/preset-no-cross-stack-leakage.mdc +4 -2
- package/presets/cursor/svelte/rules/ux-design.mdc +108 -0
- package/presets/cursor/svelte/skills/README.md +2 -0
- package/presets/cursor/svelte/skills/feature-delivery/SKILL.md +3 -0
- package/presets/cursor/svelte/skills/mockup-review/SKILL.md +29 -0
- package/presets/cursor/svelte/skills/ux-design/SKILL.md +36 -0
- package/presets/cursor/svelte/team/fixtures/artifact-manifest.example.json +20 -2
- package/presets/cursor/svelte/team/fixtures/feature-with-figma-url.json +17 -0
- package/presets/cursor/svelte/team/fixtures/feature-with-ux-no-figma.json +17 -0
- package/presets/cursor/svelte/team/fixtures/mockup-review-fail-embedded-status.json +8 -0
- package/presets/cursor/svelte/team/fixtures/mockup-review-standalone.json +14 -0
- package/presets/cursor/svelte/team/fixtures/ux-design-standalone.json +15 -0
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: mockup-reviewer
|
|
3
|
+
description: Figma mockup review specialist. Audits design-system usage, tokens, mockup quality, feature coverage, and viewport matrix. Writes mockup-review.md only; never edits production code or Figma.
|
|
4
|
+
readonly: false
|
|
5
|
+
model: claude-opus-4-8[effort=high]
|
|
6
|
+
---
|
|
7
|
+
|
|
8
|
+
You are a Figma mockup reviewer for an iOS SwiftUI / UIKit frontend.
|
|
9
|
+
|
|
10
|
+
You write **only** `.cursor/team/tasks/<slug>/mockup-review.md` (and the owned manifest receipt). Never edit production code, `packages/**`, app sources, or Figma (no `use_figma` writes).
|
|
11
|
+
|
|
12
|
+
## Inputs
|
|
13
|
+
|
|
14
|
+
1. `.cursor/team/tasks/<slug>/artifact-manifest.json`.
|
|
15
|
+
2. Prompt Figma URL(s); `brief.md` / `decomposition.md` when present.
|
|
16
|
+
3. Requestable skill `mockup-review` and rule `mockup-review` (core checklist — do not inline it here).
|
|
17
|
+
4. If plugin skills `figma-use` / `figma-design-to-code` are installed: **reference** them for URL parse and MCP invocation only — do not copy their bodies; do not run design-to-code.
|
|
18
|
+
|
|
19
|
+
## MCP tools
|
|
20
|
+
|
|
21
|
+
**Required when MCP is up:** `get_metadata`, `get_design_context`, `search_design_system`, `get_variable_defs`, `get_screenshot`.
|
|
22
|
+
|
|
23
|
+
**Optional:** `get_libraries`, `get_code_connect_map`.
|
|
24
|
+
|
|
25
|
+
**Forbidden:** `use_figma`, `create_new_file`, `generate_*`, `weave_*`, `upload_assets`, `send_code_connect_mappings`. FigJam URL → `BLOCKED_MCP`.
|
|
26
|
+
|
|
27
|
+
Cite `fileKey` + node IDs. Screenshot is supporting evidence, not a second reviewer.
|
|
28
|
+
|
|
29
|
+
**Node caps:** ≤12 screen-level frames; `get_metadata` depth ≤3; ≤3 screenshots (prefer one per small/medium/large). `search_design_system` once; `get_variable_defs` once per file. Unbounded file without a frame link → `BLOCKED_MCP` (do not dump the whole file).
|
|
30
|
+
|
|
31
|
+
MCP unavailable or OAuth fail → verdict `BLOCKED_MCP`. Do not invent DS claims.
|
|
32
|
+
|
|
33
|
+
## Review dimensions
|
|
34
|
+
|
|
35
|
+
Follow the requestable `mockup-review` checklist (DS components, tokens, quality, coverage, viewports). Do not duplicate that checklist here.
|
|
36
|
+
|
|
37
|
+
## Output
|
|
38
|
+
|
|
39
|
+
Write `.cursor/team/tasks/<slug>/mockup-review.md` using the report headings in the `mockup-review` rule.
|
|
40
|
+
|
|
41
|
+
## Verdicts and receipts
|
|
42
|
+
|
|
43
|
+
Report verdict: `PASS | PASS_WITH_NOTES | FAIL | BLOCKED_MCP`.
|
|
44
|
+
|
|
45
|
+
| Verdict | Standalone receipt | Embedded receipt | Artifact `status` |
|
|
46
|
+
|---------|--------------------|------------------|-------------------|
|
|
47
|
+
| `PASS` / `PASS_WITH_NOTES` | `completed` | `completed` | `completed` |
|
|
48
|
+
| `FAIL` | `completed` (report-only, like `perf-audit`) | `changes_requested` | `blocked` |
|
|
49
|
+
| `BLOCKED_MCP` | `blocked` | `blocked` | `blocked` |
|
|
50
|
+
|
|
51
|
+
Standalone FAIL must **not** set `changes_requested`. Embedded FAIL is a FAIL-only hook gate — resume **only** via `/task-continue` (hook must not `scheduleRetry('feature-developer')`).
|
|
52
|
+
|
|
53
|
+
## Artifact contract
|
|
54
|
+
|
|
55
|
+
- **Authoritative inputs:** read `.cursor/team/tasks/<slug>/artifact-manifest.json` first; consume handoff `artifactInputIds` when supplied, otherwise consume the manifest entries for routing + analysis when present (standalone may have only the prompt + URL).
|
|
56
|
+
- **Owned outputs:** `mockup-review.md`; upsert only the manifest entry assigned by handoff (`artifactOutputId`; fallback `mockup-review`) and preserve all foreign entries.
|
|
57
|
+
- **Terminal receipt:** cover applicable AC/task IDs, list authoritative evidence paths, and emit `completed`, `changes_requested`, or `blocked` per the table above. Bind it to the supplied `attemptId` when present.
|
|
58
|
+
- **Shared state:** never create or mutate `status.json` or `metrics.json`; the orchestration runtime/hook owns lifecycle, gates, retries, attempts, and timestamps.
|
|
59
|
+
|
|
60
|
+
Do not modify production code or tests.
|
|
@@ -47,9 +47,26 @@ Add to `brief.md`:
|
|
|
47
47
|
```
|
|
48
48
|
|
|
49
49
|
|
|
50
|
+
## UX design (behavioral)
|
|
51
|
+
|
|
52
|
+
Load requestable skill **`ux-design`** and rule **`ux-design`** when:
|
|
53
|
+
- standalone router intent `ux-design`, or
|
|
54
|
+
- **required-signal:** the user asked for UX, **or** AC explicitly require flows/states, **or** `spec-gen` / `/spec-start` for a **page/feature**, or
|
|
55
|
+
- advisory UI AC on this UI stack (notes only; skip if no UI surface).
|
|
56
|
+
|
|
57
|
+
**Order:** write `ux-design.md` **before** author mode / skill `spec-authoring` when both apply. You remain the only INDEX writer.
|
|
58
|
+
|
|
59
|
+
Write `.cursor/team/tasks/<slug>/ux-design.md` with the headings in rule `ux-design` (Mode, Verdict, Scope, IA, Entry/actors, Primary flows, States, Interaction notes, Microcopy direction, Accessibility floor, Spec feed, Open probes). Modes: `synthesize` | `review`.
|
|
60
|
+
|
|
61
|
+
**Required vs advisory:** required-signal + missing named primary flows **or** empty/error/loading matrix → DoR not met (`open_questions` / blocked analysis). Isolated missing microcopy never blocks. Advisory `INCOMPLETE` → notes only. Do **not** copy the mockup FAIL-only hook.
|
|
62
|
+
|
|
63
|
+
**Forbidden:** Figma MCP tools (`get_metadata`, `get_design_context`, `get_screenshot`, `search_design_system`, `get_variable_defs`, `use_figma`, `create_new_file`, `generate_*`). When Figma is present and required-signal fires, emit a **thin** `ux-design.md` from AC only (no visual claims). Only `mockup-reviewer` reads Figma.
|
|
64
|
+
|
|
65
|
+
When produced, append `ux-design.md` to this step's **`analysis`** `authoritativePaths` / `evidencePaths`. No new manifest producer row.
|
|
66
|
+
|
|
50
67
|
## Artifact contract
|
|
51
68
|
|
|
52
69
|
- **Authoritative inputs:** read `.cursor/team/tasks/<slug>/artifact-manifest.json` first; consume `pipeline.json`, the manifest routing entry, user-approved decisions, and any authoritative architecture/approval entries.
|
|
53
|
-
- **Owned outputs:** `brief.md` and `decomposition.md
|
|
70
|
+
- **Owned outputs:** `brief.md` and `decomposition.md` (plus `ux-design.md` when produced); upsert only the manifest entry assigned by handoff (`artifactOutputId`; fallback `analysis`) and preserve all foreign entries.
|
|
54
71
|
- **Terminal receipt:** cover applicable AC/task IDs, list authoritative evidence paths, and emit `completed` or `blocked`. Bind it to the supplied `attemptId` when present.
|
|
55
72
|
- **Shared state:** never create or mutate `status.json` or `metrics.json`; the orchestration runtime/hook owns lifecycle, gates, retries, attempts, and timestamps.
|
|
@@ -23,6 +23,8 @@ You are a task router for an **iOS Swift/SwiftUI** agent team. You **do not** im
|
|
|
23
23
|
| `migration` | “migration”, “upgrade”, “update Xcode/SPM/iOS” | task-analyst → migration-specialist → feature-developer → build-verifier → code-reviewer |
|
|
24
24
|
| `perf-audit` | “performance”, “Instruments”, “launch”, “slow” | performance-auditor |
|
|
25
25
|
| `a11y` | “a11y”, “VoiceOver”, “Dynamic Type”, “accessibility” | task-analyst → feature-developer → build-verifier → accessibility-reviewer → code-reviewer |
|
|
26
|
+
| `mockup-review` | “mockup review”, “check Figma”, “figma review”, mockup + review verb, `figma.com` + review-not-implement | mockup-reviewer |
|
|
27
|
+
| `ux-design` | «разработай UX» (design UX), «спроектируй» (design) flows, “journey”, “IA”, “state matrix”, «ревью UX» (UX review) without Figma | task-analyst | <!-- i18n-keep: E4 -->
|
|
26
28
|
| `review-only` | “review”, “review MR”, “check the diff” | code-reviewer |
|
|
27
29
|
| `test-only` | “cover with tests” (unit+UI, no impl) | task-analyst → qa-tester |
|
|
28
30
|
| `unit-only` | “unit”, “XCTest”, “cover mapper” | unit-test-planner → unit-test-generator, or unit-test-healer |
|
|
@@ -33,10 +35,15 @@ You are a task router for an **iOS Swift/SwiftUI** agent team. You **do not** im
|
|
|
33
35
|
| `retro` | “retro”, “postmortem” | (orchestrator → `/technical-retro`) |
|
|
34
36
|
|
|
35
37
|
**Never schedule Playwright agents** (`playwright-test-*`). If a next template mentions them, put in `skipped` with reason "iOS uses XCUITest" and use xcuitest trio.
|
|
38
|
+
**Light by intent:** `mockup-review` → only `mockup-reviewer` (`model: "strong"`, never `cheap`). `ux-design` → only `task-analyst` (skill `ux-design`; analyst default model, not `strong`). Classify `mockup-review` **before** `ux-design` **before** `review-only`. A `figma.com` URL with review-not-implement language remains `mockup-review` even if the user said «ревью UX». <!-- i18n-keep: E4 -->
|
|
39
|
+
**Embed UX:** on `feature` / `refactor` / `spike` / `spec-gen` with required-signal or advisory UI AC, instruct **task-analyst** to load skill `ux-design` (no new pipeline step).
|
|
40
|
+
|
|
41
|
+
**Embed `figma.com`:** on `feature` / `refactor` / `spike` / `spec-gen`, insert `mockup-reviewer` after `task-analyst` (when present) and before `solution-architect` and `feature-developer`. Do **not** add static `humanGates: ["after:mockup-reviewer"]` (FAIL-only gate is a hook exception). Never put `mockup-reviewer` in a `parallel: true` step.
|
|
42
|
+
|
|
36
43
|
|
|
37
44
|
## Pipeline profiles
|
|
38
45
|
|
|
39
|
-
`"profile": "full" | "standard" | "light"`. Default: **standard** for feature/refactor/bugfix; **light** for review-only/perf; **full** when cross-layer or UI-test AC.
|
|
46
|
+
`"profile": "full" | "standard" | "light"`. Default: **standard** for feature/refactor/bugfix; **light** for review-only/perf/mockup-review/ux-design; **full** when cross-layer or UI-test AC.
|
|
40
47
|
|
|
41
48
|
**Never skip `build-verifier`** after developer when Swift/Xcode sources changed.
|
|
42
49
|
|
|
@@ -66,7 +73,7 @@ Keep top-level `profile` and emit this top-level object in every new `pipeline.j
|
|
|
66
73
|
Optional: `"model": "cheap" | "standard" | "strong"`. Same policy as **cursor/next** `task-router.md`:
|
|
67
74
|
|
|
68
75
|
- `light` → `cheap` on all steps (debugger unclear root cause → `strong`)
|
|
69
|
-
- `full` / `spike` / security|perf specialists → `strong` on architect, migration, security, perf steps
|
|
76
|
+
- `full` / `spike` / security|perf|mockup specialists → `strong` on architect, migration, security, perf, and `mockup-reviewer` steps
|
|
70
77
|
- never `strong` on build-verifier / tech-writer / task-router
|
|
71
78
|
- omit on `standard` → agent frontmatter (`fast` / `inherit` / `claude-opus-4-8[effort=high]`)
|
|
72
79
|
|
|
@@ -81,6 +88,8 @@ Fixtures: `.cursor/team/fixtures/` (feature-full, feature-light, bugfix-standard
|
|
|
81
88
|
| unit-only | `["after:unit-test-planner"]` when new plan |
|
|
82
89
|
| e2e-only | `["after:xcuitest-test-planner"]` when new plan |
|
|
83
90
|
| bugfix, review-only, ci-fix | `[]` |
|
|
91
|
+
| mockup-review | `[]` |
|
|
92
|
+
| ux-design | `[]` |
|
|
84
93
|
| spike | `["after:solution-architect"]` |
|
|
85
94
|
|
|
86
95
|
## Output
|
|
@@ -32,17 +32,19 @@ printf '%s\n' '{"status":"completed","action":"end_human_gate","activateNext":tr
|
|
|
32
32
|
|
|
33
33
|
3. Re-read `status.json` (and the hook `followup_message`).
|
|
34
34
|
4. Invoke the subagent named in `status.currentAgent` / followup — do **not** advance the pipeline a second time.
|
|
35
|
-
3. **Review `changes_requested`** (not a human gate): set `currentAgent` to `feature-developer` (same index / find developer in steps), `state: in_progress`, then invoke developer. Do **not** call `end_human_gate` unless `activeHumanGateEventId` is set.
|
|
36
|
-
4.
|
|
37
|
-
5.
|
|
35
|
+
3. **Review `changes_requested`** (not a human gate): if `currentAgent` is **`mockup-reviewer`**, this is the FAIL-only mockup gate — do **not** retry `feature-developer`. Read `mockup-review.md` and resume via the human-gate path (`end_human_gate` / `activateNext`). Otherwise: set `currentAgent` to `feature-developer` (same index / find developer in steps), `state: in_progress`, then invoke developer. Do **not** call `end_human_gate` unless `activeHumanGateEventId` is set.
|
|
36
|
+
4. **`blocked` + `currentAgent: mockup-reviewer`** (`BLOCKED_MCP`): skip-forward via the same `end_human_gate`/`activateNext` path (explicit «proceed without MCP»). Do not invent DS claims.
|
|
37
|
+
5. **Other resume**: restore `pipelineIndex` / `currentAgent` from status and invoke that agent.
|
|
38
|
+
6. After the invoked agent completes, `chain-team-phases.sh` on `subagentStop` continues the chain when `autoChain: true`.
|
|
38
39
|
|
|
39
40
|
## Artifacts for handoff
|
|
40
41
|
|
|
41
42
|
| Agent | Read |
|
|
42
43
|
|-------|------|
|
|
43
|
-
| feature-developer | brief.md (incl. **Related specs**), decomposition.md, validation-report.md (if retry), review.md (if retry), architecture.md; if `docs/specs/INDEX.md` exists → load **`product-specs`** |
|
|
44
|
+
| feature-developer | brief.md (incl. **Related specs**), decomposition.md, ux-design.md (if present), mockup-review.md (if present), validation-report.md (if retry), review.md (if retry), architecture.md; if `docs/specs/INDEX.md` exists → load **`product-specs`** |
|
|
44
45
|
| build-verifier | git diff, decomposition.md |
|
|
45
46
|
| code-reviewer | brief.md, validation-report.md, git diff |
|
|
47
|
+
| mockup-reviewer | mockup-review.md |
|
|
46
48
|
| qa-tester | brief.md, decomposition.md, scope from pipeline step |
|
|
47
49
|
|
|
48
50
|
## Product specs (docs/specs)
|
|
@@ -22,6 +22,8 @@ Examples:
|
|
|
22
22
|
- `/task Write a changelog for the filters release`
|
|
23
23
|
- `/task Review my changes in Features/Orders`
|
|
24
24
|
- `/task Write an XCUITest for the payment flow`
|
|
25
|
+
- `/task Review mockup https://figma.com/design/...`
|
|
26
|
+
- `/task Design UX flows for Order History` (no Figma)
|
|
25
27
|
|
|
26
28
|
## Algorithm
|
|
27
29
|
|
|
@@ -135,6 +135,7 @@ const DEFAULT_ARTIFACT_OUTPUT_IDS = {
|
|
|
135
135
|
'security-reviewer': 'security-review',
|
|
136
136
|
'accessibility-reviewer': 'a11y-review',
|
|
137
137
|
'performance-auditor': 'perf-report',
|
|
138
|
+
'mockup-reviewer': 'mockup-review',
|
|
138
139
|
'api-contract-reviewer': 'api-contract-review',
|
|
139
140
|
'tech-writer': 'documentation',
|
|
140
141
|
};
|
|
@@ -313,6 +314,8 @@ const AGENT_HANDOFF = {
|
|
|
313
314
|
`Invoke accessibility-reviewer (readonly) for slug "${s}". Review Presentation/SwiftUI (or UIKit) diff for VoiceOver/Dynamic Type/accessibilityIdentifier; write a11y-review.md. Upsert the owned terminal receipt in artifact-manifest.json; do not mutate status.json lifecycle fields.`,
|
|
314
315
|
'performance-auditor': (s) =>
|
|
315
316
|
`Invoke performance-auditor (readonly) for slug "${s}". Audit launch/SwiftUI performance risks; write perf-report.md. Upsert the owned terminal receipt in artifact-manifest.json; do not mutate status.json lifecycle fields.`,
|
|
317
|
+
'mockup-reviewer': (s) =>
|
|
318
|
+
`Invoke mockup-reviewer (readonly) for slug "${s}". Write mockup-review.md. Load requestable mockup-review skill/rule. Upsert the owned terminal receipt in artifact-manifest.json; do not mutate status.json lifecycle fields.`,
|
|
316
319
|
'code-reviewer': (s) =>
|
|
317
320
|
`Invoke code-reviewer subagent (readonly) for slug "${s}". Review git diff vs brief.md per code-review-mr.mdc. ` +
|
|
318
321
|
`Upsert the owned terminal receipt in artifact-manifest.json; do not mutate status.json lifecycle fields.`,
|
|
@@ -597,6 +600,18 @@ if (currentStep?.parallel && stepAgents.length > 1) {
|
|
|
597
600
|
}
|
|
598
601
|
|
|
599
602
|
const retryReviewer = stepAgents.find((agent) => outcomes[agent]?.outcome === 'changes_requested');
|
|
603
|
+
if (retryReviewer === 'mockup-reviewer') {
|
|
604
|
+
beginHumanGate();
|
|
605
|
+
writeStatus({
|
|
606
|
+
awaitingHumanGate: true,
|
|
607
|
+
state: 'awaiting_approval',
|
|
608
|
+
currentAgent: 'mockup-reviewer',
|
|
609
|
+
parallelCompleted: [],
|
|
610
|
+
parallelOutcomes: {},
|
|
611
|
+
});
|
|
612
|
+
out(`Mockup review FAIL for slug "${slug}". Read mockup-review.md. Resume only via /task-continue. Do not retry feature-developer.`);
|
|
613
|
+
process.exit(0);
|
|
614
|
+
}
|
|
600
615
|
if (retryReviewer) {
|
|
601
616
|
const retryAfterFixStepIndex = idx;
|
|
602
617
|
const predecessor = outcomes[retryReviewer]
|
|
@@ -628,6 +643,17 @@ if (status.state === 'blocked') {
|
|
|
628
643
|
process.exit(0);
|
|
629
644
|
}
|
|
630
645
|
|
|
646
|
+
if (status.state === 'changes_requested' && (completedAgent === 'mockup-reviewer' || status.currentAgent === 'mockup-reviewer')) {
|
|
647
|
+
beginHumanGate();
|
|
648
|
+
writeStatus({
|
|
649
|
+
awaitingHumanGate: true,
|
|
650
|
+
state: 'awaiting_approval',
|
|
651
|
+
currentAgent: 'mockup-reviewer',
|
|
652
|
+
});
|
|
653
|
+
out(`Mockup review FAIL for slug "${slug}". Read mockup-review.md. Resume only via /task-continue. Do not retry feature-developer.`);
|
|
654
|
+
process.exit(0);
|
|
655
|
+
}
|
|
656
|
+
|
|
631
657
|
if (status.state === 'changes_requested') {
|
|
632
658
|
const reviewer = status.currentAgent || finishedAttempt?.entry?.agent;
|
|
633
659
|
if (!reviewer) {
|
|
@@ -31,6 +31,8 @@ Cursor Rule format:
|
|
|
31
31
|
| `reference-features.mdc` | globs Features/** | Reference Features + dogfood |
|
|
32
32
|
| `product-specs.mdc` | globs docs/specs/** | Product specs INDEX discovery (requestable) |
|
|
33
33
|
| `technical-retro.mdc` | requestable | Alias → `/technical-retro` |
|
|
34
|
+
| `mockup-review.mdc` | requestable | Figma mockup checklist + Stack notes breakpoints |
|
|
35
|
+
| `ux-design.mdc` | requestable | Behavioral UX checklist + Stack notes form-factor |
|
|
34
36
|
| `preset-layering.mdc` (+ `preset-*`) | globs presets/** | Author meta (never alwaysApply) |
|
|
35
37
|
| `swiftui-ui.mdc` | Presentation, DesignSystem | SwiftUI, a11y |
|
|
36
38
|
| `navigation-coordinators.mdc` | Navigation / App | NavigationStack, deep links |
|
|
@@ -43,7 +45,7 @@ Cursor Rule format:
|
|
|
43
45
|
| `tests-unit.mdc` | `*Tests` | Unit |
|
|
44
46
|
| `tests-ui.mdc` | `*UITests` | XCUITest (+ pointer to xcuitest agents/skill) |
|
|
45
47
|
|
|
46
|
-
**Topic `.mdc` total:**
|
|
48
|
+
**Topic `.mdc` total:** 24 domain + 5 preset-meta (excluding README).
|
|
47
49
|
|
|
48
50
|
**Twin depth (Cursor↔Claude):** domain rules ≥15 body lines. Thin requestable **aliases** (`agent-team-intake`, `technical-retro`) may be shorter — as in next (soft AC-19).
|
|
49
51
|
|
|
@@ -64,6 +66,8 @@ SoT prose: `packages/ai-rules/presets/_shared/core/**`. Adapters: `<!-- shared-c
|
|
|
64
66
|
| `architecture/product-specs-authoring.md` | `product-specs-authoring.mdc` | Generate/Bootstrap contract; requestable |
|
|
65
67
|
| `review/code-review-mr.md` | `code-review-mr.mdc` | iOS checklist |
|
|
66
68
|
| `review/technical-retro.md` | `technical-retro.mdc` | thin alias |
|
|
69
|
+
| `review/mockup-review.md` | `mockup-review.mdc` | Stack notes breakpoints; requestable |
|
|
70
|
+
| `review/ux-design.md` | `ux-design.mdc` | Stack notes form-factor; requestable |
|
|
67
71
|
| `meta/preset-*.md` | `preset-*.mdc` | author-only globs |
|
|
68
72
|
|
|
69
73
|
Claude map: `presets/claude/ios-swift/rules/README.md`. Taxonomy: `presets/_shared/README.md`.
|
|
@@ -28,7 +28,7 @@ Work request without `/task` — see **`agent-team-intake.mdc`**.
|
|
|
28
28
|
| Agent | Prod writes | Typical intent |
|
|
29
29
|
|-------|-------------|----------------|
|
|
30
30
|
| `task-router` | no (team) | Every `/task` |
|
|
31
|
-
| `task-analyst` | no | feature, refactor, test-only, a11y, docs, migration |
|
|
31
|
+
| `task-analyst` | no | feature, refactor, test-only, a11y, docs, migration, ux-design |
|
|
32
32
|
| `solution-architect` | no | spike, cross-layer Feature |
|
|
33
33
|
| `migration-specialist` | no | Xcode/SPM/iOS upgrades |
|
|
34
34
|
| `api-contract-reviewer` | no | OpenAPI / Swift codegen contracts |
|
|
@@ -38,6 +38,7 @@ Work request without `/task` — see **`agent-team-intake.mdc`**.
|
|
|
38
38
|
| `build-verifier` | no | xcodebuild + SwiftLint/Format + unit smoke; preset-structure for preset PRs |
|
|
39
39
|
| `accessibility-reviewer` | no | VoiceOver / Dynamic Type |
|
|
40
40
|
| `performance-auditor` | no | launch / Instruments |
|
|
41
|
+
| `mockup-reviewer` | no (team only) | mockup-review, feature/refactor/spike/spec-gen with `figma.com` |
|
|
41
42
|
| `code-reviewer` | no | most pipelines, review-only |
|
|
42
43
|
| `security-reviewer` | no | Keychain, ATS, PII |
|
|
43
44
|
| `qa-tester` | tests | feature, bugfix, test-only |
|
|
@@ -51,6 +52,8 @@ Work request without `/task` — see **`agent-team-intake.mdc`**.
|
|
|
51
52
|
|
|
52
53
|
Full prompts: `.cursor/agents/*.md`. Artifact conventions: `.cursor/team/README.md`; schema SoT: **agent-artifact-contracts**.
|
|
53
54
|
|
|
55
|
+
**Behavioral UX:** `task-analyst` loads requestable skill `ux-design` for standalone intent `ux-design` and embedded required-signal / advisory UI AC. No `ux-designer` agent in v1.
|
|
56
|
+
|
|
54
57
|
**Product specs:** When `/task`, `/feature-start`, or `/spec-start` touches pages/features/`docs/specs`: if INDEX exists and no generate intent → instruct next agent to load requestable **`product-specs`** (consume; soft-fail; never invent). If generate/bootstrap/`spec-gen` → load **`product-specs-authoring`** + skill **`spec-authoring`** inside **task-analyst** (not a separate pipeline step); pass created spec paths + INDEX diff in handoff; human gate must approve before feature-developer. No-op if INDEX absent and no author intent.
|
|
55
58
|
|
|
56
59
|
When editing `packages/ai-rules/presets/**`, follow **`preset-pr-checklist.mdc`** (+ twin-sync / layering / token-budget / leakage meta-rules).
|
|
@@ -100,8 +103,8 @@ On each `subagentStop`, the hook reconciles `status.state` from the completing p
|
|
|
100
103
|
2. Read `pipeline.json` before every subagent invocation.
|
|
101
104
|
3. One role per Task call — except parallel steps.
|
|
102
105
|
4. **Never** skip `humanGates` without `/task-continue` or explicit approval.
|
|
103
|
-
5. Persist handoffs to disk under `.cursor/team/tasks/<slug>/` via **Write** (not Shell `mkdir`).
|
|
104
|
-
6. On `changes_requested`: developer → same reviewer.
|
|
106
|
+
5. Persist handoffs to disk under `.cursor/team/tasks/<slug>/` via **Write** (not Shell `mkdir`), including `mockup-review.md` / `ux-design.md` when those producers ran.
|
|
107
|
+
6. On `changes_requested`: developer → same reviewer. Exception: embedded `mockup-reviewer` FAIL → `awaiting_approval` / `/task-continue` only (no developer retry).
|
|
105
108
|
7. On `validation_failed`: developer → build-verifier.
|
|
106
109
|
8. When all steps complete, suggest `/technical-retro <slug>`.
|
|
107
110
|
9. If `autoChain: false`, do not rely on hook.
|
|
@@ -9,6 +9,8 @@ alwaysApply: false
|
|
|
9
9
|
|
|
10
10
|
## Stack notes
|
|
11
11
|
|
|
12
|
+
When the prompt or `brief.md` contains a `figma.com` URL, **mockup review** (`mockup-reviewer` / skill `mockup-review`) must complete — or the user must continue past FAIL/`BLOCKED_MCP` via `/task-continue` — **before UI implementation**. Non-UI tasks no-op this gate. When required-signal and **no** `figma.com`, **`ux-design.md`** (on the analysis manifest entry) must exist and not be `INCOMPLETE` before UI work — else **blocked**, hand back to `task-analyst`. Parallel to the mockup gate.
|
|
13
|
+
|
|
12
14
|
Typical feature with data and UI. Layer details — `architecture-boundaries.mdc`, `ios-app-core.mdc`.
|
|
13
15
|
|
|
14
16
|
## Checklist (work order)
|
|
@@ -0,0 +1,116 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Figma mockup review checklist (DS, coverage, viewports). On-demand — load via mockup-reviewer / skill mockup-review.
|
|
3
|
+
alwaysApply: false
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
<!-- shared-core: review/mockup-review.md -->
|
|
7
|
+
|
|
8
|
+
# Mockup review checklist
|
|
9
|
+
|
|
10
|
+
On-demand reviewer checklist for Figma mockups. **Procedure:** skill `mockup-review`. **Agent:** `mockup-reviewer`. Do not inline this checklist into the agent prompt.
|
|
11
|
+
|
|
12
|
+
Stack-agnostic: no app-source globs, Playwright, or `xcodebuild`. Breakpoint **examples** live in adapter **Stack notes** only — do not FAIL on exact pixels.
|
|
13
|
+
|
|
14
|
+
## When to load
|
|
15
|
+
|
|
16
|
+
- Pipeline step `mockup-reviewer` (standalone intent `mockup-review` or embedded after analyst)
|
|
17
|
+
- Prompt or `brief.md` contains a `figma.com` URL on a UI-capable stack
|
|
18
|
+
- User asks to review a mockup / Figma file (not a code MR)
|
|
19
|
+
|
|
20
|
+
## Inputs
|
|
21
|
+
|
|
22
|
+
1. Task `artifact-manifest.json`, then prompt Figma URL(s); `brief.md` / `decomposition.md` when present
|
|
23
|
+
2. Skill `mockup-review` + this rule
|
|
24
|
+
3. If plugin skills `figma-use` / `figma-design-to-code` are installed: **reference** them for URL parse and MCP invocation only — do not copy their bodies; do not run design-to-code
|
|
25
|
+
|
|
26
|
+
## MCP-first
|
|
27
|
+
|
|
28
|
+
Required when MCP is up: `get_metadata`, `get_design_context`, `search_design_system`, `get_variable_defs`, `get_screenshot`. Optional: `get_libraries`, `get_code_connect_map`.
|
|
29
|
+
|
|
30
|
+
**Forbidden:** `use_figma`, `create_new_file`, `generate_*`, `weave_*`, `upload_assets`, `send_code_connect_mappings`. FigJam URL → `BLOCKED_MCP` / out of scope (do not call `get_figjam` unless the URL is a FigJam board — then still `BLOCKED_MCP`).
|
|
31
|
+
|
|
32
|
+
Cite `fileKey` + node IDs. Screenshots are supporting evidence, not a second reviewer. No screenshot-only path.
|
|
33
|
+
|
|
34
|
+
**Node caps:** ≤12 screen-level frames; `get_metadata` depth ≤3 named-frame levels; ≤3 screenshots (prefer one per small/medium/large). `search_design_system` once; `get_variable_defs` once per file. No node-id on URL: pick top-level frames matching the feature name; if still unbounded → `BLOCKED_MCP` (or `PASS_WITH_NOTES` only if MCP returned a tiny file) — do not dump the whole file.
|
|
35
|
+
|
|
36
|
+
**Degradation:** MCP unavailable or OAuth fail → verdict `BLOCKED_MCP`. Do **not** invent DS compliance claims.
|
|
37
|
+
|
|
38
|
+
## Review dimensions
|
|
39
|
+
|
|
40
|
+
### DS components (AC-4)
|
|
41
|
+
|
|
42
|
+
When an attached library is detectable (`search_design_system` / `get_metadata`): list **library component instances vs custom frames** with file/node references. Flag substitutions where a DS equivalent exists.
|
|
43
|
+
|
|
44
|
+
- Critical DS reimplementation (custom frame where an attached-library component exists) → **FAIL**
|
|
45
|
+
- One-off frame, no DS equivalent; mixed/unpublished library → WARN or notes (`PASS_WITH_NOTES`)
|
|
46
|
+
- No attached library detectable → notes only; do not invent DS claims (`PASS_WITH_NOTES`)
|
|
47
|
+
|
|
48
|
+
Confidence: `high` (MCP library match) / `low` (unpublished or mixed) — prefer `PASS_WITH_NOTES` over FAIL when confidence is low.
|
|
49
|
+
|
|
50
|
+
### Tokens (AC-5)
|
|
51
|
+
|
|
52
|
+
When variables/styles are available (`get_variable_defs`, style metadata): flag fills, strokes, spacing, or typography that use raw values instead of bound variables/styles.
|
|
53
|
+
|
|
54
|
+
- Isolated unbound values → **WARN** (`PASS_WITH_NOTES`)
|
|
55
|
+
- Wholesale token ignore on a library-attached file (systemic; treat as critical DS with AC-4) → **FAIL**
|
|
56
|
+
|
|
57
|
+
### Quality (AC-6)
|
|
58
|
+
|
|
59
|
+
Cover at minimum, each item PASS / WARN / FAIL eligible:
|
|
60
|
+
|
|
61
|
+
- Layer/frame naming hygiene
|
|
62
|
+
- Auto-layout vs absolute positioning for responsive regions
|
|
63
|
+
- Text style usage
|
|
64
|
+
- Component variant/property correctness
|
|
65
|
+
- Detached or orphaned component instances
|
|
66
|
+
|
|
67
|
+
Naming hygiene, minor detached instances, text-style drift → **WARN**. Detached **core** DS component that is a substitution → **FAIL** (same as AC-4 critical). Absolute layout on a region that is the only «responsive» evidence → WARN unless it also fails viewports.
|
|
68
|
+
|
|
69
|
+
### Feature coverage (AC-7)
|
|
70
|
+
|
|
71
|
+
Map **flows → screens/frames**, **actions → interactive elements**, and **states** (empty, loading, error, success, disabled/validation). List explicit **missing** items. Label scope **`inferred`** when only a URL is provided (no brief AC).
|
|
72
|
+
|
|
73
|
+
- Missing **core** flow or primary action from brief AC (or labeled `inferred` primary flow from the URL) → **FAIL**
|
|
74
|
+
- Missing empty/loading/error/success on a form/list called out in AC → **FAIL**
|
|
75
|
+
- Missing secondary states (disabled/validation) not in AC → **WARN**
|
|
76
|
+
|
|
77
|
+
### Viewports (AC-8)
|
|
78
|
+
|
|
79
|
+
Verify **≥3 viewport representations** (small / medium / large) via dedicated frames, Figma viewport presets, or responsive component variants.
|
|
80
|
+
|
|
81
|
+
- Fewer than 3 → **FAIL**
|
|
82
|
+
- 3 exist but sizes ≠ stack example buckets → **WARN** only (no exact pixel enforcement in core)
|
|
83
|
+
|
|
84
|
+
## Severity (v1)
|
|
85
|
+
|
|
86
|
+
Isolated **WARN** never blocks. Overall verdict = worst FAIL > BLOCKED_MCP > PASS_WITH_NOTES > PASS. Multiple WARNs without FAIL → `PASS_WITH_NOTES`, not FAIL.
|
|
87
|
+
|
|
88
|
+
## Report headings
|
|
89
|
+
|
|
90
|
+
Write `mockup-review.md` with these headings (must match the agent template):
|
|
91
|
+
|
|
92
|
+
```markdown
|
|
93
|
+
# Mockup review: <slug>
|
|
94
|
+
|
|
95
|
+
## Verdict
|
|
96
|
+
PASS | PASS_WITH_NOTES | FAIL | BLOCKED_MCP
|
|
97
|
+
|
|
98
|
+
## Scope
|
|
99
|
+
- Figma fileKey / node IDs
|
|
100
|
+
- MCP: available | unavailable (reason)
|
|
101
|
+
- Feature scope source: brief AC | prompt | inferred
|
|
102
|
+
|
|
103
|
+
## Critical (must fix)
|
|
104
|
+
## Warnings (should fix)
|
|
105
|
+
## Suggestions
|
|
106
|
+
## DS compliance (AC-4, AC-5)
|
|
107
|
+
## Quality (AC-6)
|
|
108
|
+
## Feature coverage (AC-7)
|
|
109
|
+
## Viewport matrix (AC-8)
|
|
110
|
+
## AC coverage
|
|
111
|
+
| Criterion | Status | Notes |
|
|
112
|
+
```
|
|
113
|
+
|
|
114
|
+
## Stack notes
|
|
115
|
+
|
|
116
|
+
Illustrative iOS size classes (not enforced pixels): compact / regular (e.g. small iPhone, large iPhone, iPad) mapped to small / medium / large.
|
|
@@ -70,7 +70,8 @@ Shared backend-stack bans (`go`, `java`, `php-hexagonal`, and `php-laravel`):
|
|
|
70
70
|
- `playwright-test-`, `playwright-e2e`, `user-playwright`, `app/__tests__/e2e`
|
|
71
71
|
- Positive yarn recipes `lint:js` / `lint:css`
|
|
72
72
|
- `xcuitest-test-`, `instrumentation-test-`, `xcodebuild`, `SwiftLint` as required handoffs
|
|
73
|
-
- Agent
|
|
73
|
+
- Agent files `accessibility-reviewer`, `mockup-reviewer`, `ux-designer` (no UI surface)
|
|
74
|
+
- Required `skills/ux-design`, required `rules/ux-design`, or required pipeline handoff stem `ux-design`
|
|
74
75
|
|
|
75
76
|
Required instead: `integration-test-*`; build-verifier / `post-change-test` plus stack tooling — `go-tooling` (`go test`, `go vet`), `java-tooling` (`mvn test` / `./gradlew test`), or `php-tooling` (`php artisan test` / `composer test` / `vendor/bin/phpunit`).
|
|
76
77
|
|
|
@@ -82,7 +83,8 @@ Same UI/mobile bans as backend stacks, plus:
|
|
|
82
83
|
- Positive yarn recipes `lint:js` / `lint:css` as required gates
|
|
83
84
|
- `xcuitest-test-`, `instrumentation-test-`, `xcodebuild`, `SwiftLint` as required handoffs
|
|
84
85
|
- Go tool commands as required MCP delivery gates: `go test`, `go vet`, `golangci-lint`
|
|
85
|
-
- Agent files: `playwright-test-*`, `xcuitest-test-*`, `instrumentation-test-*`, `integration-test-*`, `accessibility-reviewer`
|
|
86
|
+
- Agent files: `playwright-test-*`, `xcuitest-test-*`, `instrumentation-test-*`, `integration-test-*`, `accessibility-reviewer`, `mockup-reviewer`, `ux-designer`
|
|
87
|
+
- Required `skills/ux-design`, required `rules/ux-design`, or required pipeline handoff stem `ux-design`
|
|
86
88
|
|
|
87
89
|
Required instead: package-manager–discovered typecheck/test (`mcp-ts-tooling`, `post-change-test`); Phase 1 gates `build-verifier` + `security-reviewer`.
|
|
88
90
|
|
|
@@ -0,0 +1,108 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Behavioral UX design checklist (IA, flows, states). On-demand — load via task-analyst / skill ux-design.
|
|
3
|
+
alwaysApply: false
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
<!-- shared-core: review/ux-design.md -->
|
|
7
|
+
|
|
8
|
+
# UX design checklist
|
|
9
|
+
|
|
10
|
+
On-demand behavioral UX checklist (IA, named flows, state matrix). **Procedure:** skill `ux-design`. **Producer:** `task-analyst` (not a pipeline agent). Do not inline this checklist into the analyst prompt.
|
|
11
|
+
|
|
12
|
+
Stack-agnostic: no app-source globs, Playwright, or `xcodebuild`. Form-factor **examples** live in adapter **Stack notes** only.
|
|
13
|
+
|
|
14
|
+
## When to load
|
|
15
|
+
|
|
16
|
+
- Standalone `/task` intent `ux-design` (modes `synthesize` | `review`; profile `light`; steps only `task-analyst`)
|
|
17
|
+
- Embedded on a UI-capable stack when **required-signal** or advisory UI AC fires on `feature` / `refactor` / `spike` / `spec-gen`
|
|
18
|
+
- Required-signal (any one): the user asked for UX, **or** AC explicitly require flows/states, **or** intent is `spec-gen` / `/spec-start` for a **page/feature**. Else **advisory** (notes only; skip if no UI surface)
|
|
19
|
+
- **Do not** load for backend-only AC even on a UI stack. Classify `mockup-review` (Figma) before `ux-design` before `review-only`
|
|
20
|
+
|
|
21
|
+
## Inputs
|
|
22
|
+
|
|
23
|
+
1. Task `artifact-manifest.json`, then prompt / `brief.md` / `decomposition.md` when present
|
|
24
|
+
2. Skill `ux-design` + this rule
|
|
25
|
+
3. Approved `docs/specs` only as product-behavior SoT **after** UX synthesis maps via Spec feed — do not write INDEX here
|
|
26
|
+
|
|
27
|
+
## Forbidden Figma MCP
|
|
28
|
+
|
|
29
|
+
Do **not** call Figma MCP. Only `mockup-reviewer` reads Figma. Forbidden by name: `get_metadata`, `get_design_context`, `get_screenshot`, `search_design_system`, `get_variable_defs`, `use_figma`, `create_new_file`, `generate_*`.
|
|
30
|
+
|
|
31
|
+
When `figma.com` is present and required-signal fires, emit a **thin** `ux-design.md` from AC only (IA/flows the mockup must cover; no visual or DS claims). If the user only pasted a URL and AC are visual, the UX file may be omitted; `mockup-review.md` coverage stands.
|
|
32
|
+
|
|
33
|
+
Do **not** write BMAD-style `DESIGN.md` or a second visual spine. One experience artifact: `ux-design.md`.
|
|
34
|
+
|
|
35
|
+
## Modes
|
|
36
|
+
|
|
37
|
+
| Mode | When |
|
|
38
|
+
|------|------|
|
|
39
|
+
| `synthesize` | Design UX from a brief/AC (standalone «разработай UX» / embedded required-signal) | <!-- i18n-keep: E4 -->
|
|
40
|
+
| `review` | Critique a brief/wireframe/description **without** Figma («ревью UX»). Figma + review-not-implement remains intent `mockup-review` | <!-- i18n-keep: E4 -->
|
|
41
|
+
|
|
42
|
+
## Required vs advisory
|
|
43
|
+
|
|
44
|
+
- **Required** when required-signal fires (user-asked-ux / ac-requires-flows-states / spec-gen-page-feature)
|
|
45
|
+
- **Advisory** otherwise (UI AC without those signals). Advisory `INCOMPLETE` → notes only; DoR may complete
|
|
46
|
+
- Skip the skill when there is no UI surface or the prompt is empty of UX-relevant AC
|
|
47
|
+
|
|
48
|
+
## Verdicts
|
|
49
|
+
|
|
50
|
+
`PASS` | `PASS_WITH_NOTES` | `INCOMPLETE`. Never copy the mockup FAIL-only hook (`changes_requested` + do-not-retry-developer). Incomplete UX is an analyst/DoR problem.
|
|
51
|
+
|
|
52
|
+
| Verdict | Required step | Advisory step | Standalone intent `ux-design` |
|
|
53
|
+
|---------|---------------|---------------|-------------------------------|
|
|
54
|
+
| `PASS` / `PASS_WITH_NOTES` | Analysis may complete DoR | Analysis may complete | `completed` |
|
|
55
|
+
| `INCOMPLETE` | DoR **not** met: `open_questions` / blocked analysis; existing `after:task-analyst` gate | Notes only; DoR may complete | `completed` (report-only) |
|
|
56
|
+
|
|
57
|
+
**Block (`INCOMPLETE` as DoR failure) only when the step was required and primary flows *or* the empty/error/loading matrix are missing.** Isolated missing microcopy or optional protagonist names never block.
|
|
58
|
+
|
|
59
|
+
## Surface-closure
|
|
60
|
+
|
|
61
|
+
Each stated need → a surface; each surface → a flow that lands there. If closure fails, list probes under **Open probes** — **do not invent** screens, flows, or copy to fill gaps.
|
|
62
|
+
|
|
63
|
+
## Spec feed
|
|
64
|
+
|
|
65
|
+
Analyst remains the **only** writer of `docs/specs` INDEX and page/feature files. Map `ux-design.md` → templates **after** UX synthesis (UX before `spec-authoring` author mode):
|
|
66
|
+
|
|
67
|
+
| `ux-design.md` heading | Page template | Feature template |
|
|
68
|
+
|------------------------|---------------|------------------|
|
|
69
|
+
| Scope + IA | **Overview** | **Overview** |
|
|
70
|
+
| Entry / actors | **Entry / actors** | — (page-level) |
|
|
71
|
+
| Primary flows | **Primary flows** | **Shared behavior / constraints** when a flow is cross-page |
|
|
72
|
+
| States | **States** (loading/empty/error/success) | **Cross-cutting states** when shared |
|
|
73
|
+
| Interaction notes + microcopy direction | Inform **Acceptance criteria**; leftover → **Edge cases** | Shared constraints |
|
|
74
|
+
| Accessibility floor (behavioral) | Testable AC without pixels; else Edge cases | Shared constraints |
|
|
75
|
+
| Surface-closure probes | Analyst `open_questions` — **do not** invent spec rows | Same |
|
|
76
|
+
|
|
77
|
+
## Manifest
|
|
78
|
+
|
|
79
|
+
When produced, append `ux-design.md` to the **`analysis`** entry `authoritativePaths` and `evidencePaths`. Do **not** add a new default producer row for v1 (`ux-designer` is deferred).
|
|
80
|
+
|
|
81
|
+
## Report headings
|
|
82
|
+
|
|
83
|
+
Write `ux-design.md` with these headings (must match the architecture artifact contract):
|
|
84
|
+
|
|
85
|
+
```markdown
|
|
86
|
+
# UX design: <slug>
|
|
87
|
+
## Mode
|
|
88
|
+
synthesize | review
|
|
89
|
+
## Verdict
|
|
90
|
+
PASS | PASS_WITH_NOTES | INCOMPLETE
|
|
91
|
+
## Scope
|
|
92
|
+
- Form factor: web | ios | android | mixed
|
|
93
|
+
- Figma present: yes | no
|
|
94
|
+
- Required-signal: user-asked-ux | ac-requires-flows-states | spec-gen-page-feature | advisory
|
|
95
|
+
## Information architecture
|
|
96
|
+
## Entry / actors
|
|
97
|
+
## Primary flows
|
|
98
|
+
## States
|
|
99
|
+
## Interaction notes
|
|
100
|
+
## Microcopy direction
|
|
101
|
+
## Accessibility floor (behavioral)
|
|
102
|
+
## Spec feed
|
|
103
|
+
## Open probes
|
|
104
|
+
```
|
|
105
|
+
|
|
106
|
+
## Stack notes
|
|
107
|
+
|
|
108
|
+
Form-factor **ios**: navigation chrome, system gestures (swipe-back), Dynamic Type / VoiceOver intent. Same `ux-design.md` schema as web; put size-class examples here only — do not FAIL on exact points.
|
|
@@ -3,6 +3,8 @@
|
|
|
3
3
|
| Skill | Purpose |
|
|
4
4
|
|-------|---------|
|
|
5
5
|
| `feature-delivery` | Domain → Data → VM → View → tests → post-change-build |
|
|
6
|
+
| `mockup-review` | Figma mockup review: DS, coverage, viewports (standalone or embedded) |
|
|
7
|
+
| `ux-design` | Behavioral UX synthesis/review via task-analyst (standalone or embedded; no Figma MCP) |
|
|
6
8
|
| `code-review` | iOS MR checklist |
|
|
7
9
|
| `unit-testing` | XCTest / Swift Testing |
|
|
8
10
|
| `xcuitest-e2e` | XCUITest plan/generate/heal (← next `playwright-e2e`) |
|
|
@@ -19,6 +19,9 @@ description: Delivers iOS Swift/SwiftUI features end-to-end across Domain, Data,
|
|
|
19
19
|
- **Don't** introduce TCA/SwiftData/etc. unless the repo already uses them.
|
|
20
20
|
- **Don't** use yarn, Playwright, or `app/src` paths — wrong stack.
|
|
21
21
|
|
|
22
|
+
- If the prompt or brief contains a `figma.com` URL, load requestable skill `mockup-review` and do not start UI work until the mockup-reviewer step is completed or the user continued past FAIL/`BLOCKED_MCP`.
|
|
23
|
+
- When required-signal (user asked UX, AC require flows/states, or spec-gen page/feature) and **no** `figma.com` URL: `ux-design.md` must exist on the analysis manifest entry (verdict not `INCOMPLETE`) before UI work. If missing, **blocked** — hand back to `task-analyst`. Parallel to the mockup gate when Figma exists.
|
|
24
|
+
|
|
22
25
|
## Scope discipline
|
|
23
26
|
|
|
24
27
|
Implement only the current AC / decomposition task. Clarify ambiguity before coding; do not add unrelated hardening, polish, or drive-by refactors. See `feature-developer` → **Zero improvisation**.
|
|
@@ -0,0 +1,29 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: mockup-review
|
|
3
|
+
description: Reviews a Figma mockup for design-system compliance, feature coverage, and viewport matrix via Figma MCP. Use for standalone mockup-review intent or when a feature/refactor/spike/spec-gen task includes a figma.com URL.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Mockup review
|
|
7
|
+
|
|
8
|
+
Requestable procedure for agent `mockup-reviewer`. Checklist lives in rule `mockup-review` — do not duplicate it here.
|
|
9
|
+
|
|
10
|
+
## When to run
|
|
11
|
+
|
|
12
|
+
- Standalone `/task` intent `mockup-review` (report-only; profile `light`; steps only `mockup-reviewer`).
|
|
13
|
+
- Embedded: `feature` / `refactor` / `spike` / `spec-gen` whose prompt or `brief.md` contains a `figma.com` URL on a UI stack — after `task-analyst` (when present), before architect and developer.
|
|
14
|
+
|
|
15
|
+
## MCP OAuth preflight
|
|
16
|
+
|
|
17
|
+
Confirm Figma MCP is configured (see `MCP.md`). Do not ship secrets. If MCP is down or auth fails, write `mockup-review.md` with verdict `BLOCKED_MCP` and receipt `blocked`. Do not invent DS claims. Embedded skip-forward is `/task-continue` (explicit «proceed without MCP»).
|
|
18
|
+
|
|
19
|
+
## Plugin skills
|
|
20
|
+
|
|
21
|
+
If plugin skills `figma-design-to-code` / `figma-use` are installed, load them for MCP invocation recipes; do not paste their bodies; do not run design-to-code. Preset owns the checklist, agent, and routing; plugin owns MCP recipes.
|
|
22
|
+
|
|
23
|
+
## Load the checklist
|
|
24
|
+
|
|
25
|
+
Load requestable rule `mockup-review` and follow its review dimensions, node caps, and report headings.
|
|
26
|
+
|
|
27
|
+
## Output
|
|
28
|
+
|
|
29
|
+
Write `.cursor/team/tasks/<slug>/mockup-review.md` and upsert manifest entry id `mockup-review` (producer `mockup-reviewer`). Receipt mapping is in the agent prompt.
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ux-design
|
|
3
|
+
description: Behavioral UX synthesis and review for task-analyst. Modes synthesize|review. Standalone intent ux-design or embedded required-signal / advisory UI AC. No Figma MCP; no DESIGN.md.
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# UX design
|
|
7
|
+
|
|
8
|
+
Requestable procedure for **task-analyst** (not a pipeline agent). Checklist lives in rule `ux-design` — do not duplicate it here.
|
|
9
|
+
|
|
10
|
+
**Not** a Figma workflow: do not call Figma MCP; do not write `DESIGN.md`. Visual/DS/viewport audit stays with `mockup-reviewer` / skill `mockup-review`.
|
|
11
|
+
|
|
12
|
+
## When to run
|
|
13
|
+
|
|
14
|
+
- Standalone `/task` intent `ux-design` (report-only; profile `light`; steps only `task-analyst`; modes `synthesize` | `review`; `humanGates: []`).
|
|
15
|
+
- Embedded: `feature` / `refactor` / `spike` / `spec-gen` on a UI stack when required-signal or advisory UI AC fires — inside the analyst step (no new pipeline agent). Required-signal: user asked UX, or AC require flows/states, or spec-gen page/feature.
|
|
16
|
+
|
|
17
|
+
## Modes
|
|
18
|
+
|
|
19
|
+
- `synthesize` — elicit IA, named primary flows, empty/error/loading matrix from the brief/AC.
|
|
20
|
+
- `review` — critique a brief/wireframe/description **without** Figma. A `figma.com` URL with review-not-implement language is intent `mockup-review`, not this skill.
|
|
21
|
+
|
|
22
|
+
## Order
|
|
23
|
+
|
|
24
|
+
UX synthesis **before** skill `spec-authoring` / author mode when both apply. Analyst remains the only INDEX writer. Map headings via the rule's Spec feed table; do not paste the whole UX file into `docs/specs`.
|
|
25
|
+
|
|
26
|
+
## Forbidden Figma MCP
|
|
27
|
+
|
|
28
|
+
Do not call `get_metadata`, `get_design_context`, `get_screenshot`, `search_design_system`, `get_variable_defs`, `use_figma`, `create_new_file`, `generate_*`. Only `mockup-reviewer` reads Figma.
|
|
29
|
+
|
|
30
|
+
## Load the checklist
|
|
31
|
+
|
|
32
|
+
Load requestable rule `ux-design` and follow its required-signal vs advisory rules, forbidden MCP list, verdicts, surface-closure, and report headings.
|
|
33
|
+
|
|
34
|
+
## Output
|
|
35
|
+
|
|
36
|
+
Write `.cursor/team/tasks/<slug>/ux-design.md` and append that path to the **`analysis`** manifest entry (`authoritativePaths` / `evidencePaths`). Do **not** create a new producer row. Receipt stays on `analysis`: required `INCOMPLETE` (missing primary flows or empty/error/loading matrix) → DoR not met; advisory `INCOMPLETE` → notes only. Never copy the mockup FAIL-only hook.
|