{
  "schema_version": "1.1",
  "id": "archive:https://github.com/alchaincyf/huashu-design",
  "slug": "huashu-design-1tyg5ud",
  "url": "https://feed7.dev/p/huashu-design-1tyg5ud",
  "title": "alchaincyf/huashu-design",
  "why_included": "Huashu Design packages a multi-agent-friendly design workflow as an HTML-native skill: generate six directions, develop three, then check deliverables and design history. It supports editable PPTX and media exports, with limits around complex animation and blank-brand work.",
  "summary": "Version **3.0** offers an 84-style library with samples and first creates six thumbnails, then develops three directions for review. It can produce clickable app prototypes, HTML decks, editable-text PPTX, infographics, and animation exports. Local preference notes and a visual ledger stay on the user's machine.\nBuilders who want design work inside coding-agent sessions can use its staged review flow to compare directions before polishing one. The factual lint checks issues such as broken images, unreadable text, low contrast, and console errors; the ledger helps flag repeated visual patterns across projects.\nThe workflow is HTML-native and does not support complex 3D or physics-based animation. Blank-brand work is described as lower quality, and the PPTX export preserves editable text boxes but does not make designs Figma-layer editable.",
  "practical_implication": "",
  "agent_context": "Version **3.0** offers an 84-style library with samples and first creates six thumbnails, then develops three directions for review. It can produce clickable app prototypes, HTML decks, editable-text PPTX, infographics, and animation exports. Local preference notes and a visual ledger stay on the user's machine.\nBuilders who want design work inside coding-agent sessions can use its staged review flow to compare directions before polishing one. The factual lint checks issues such as broken images, unreadable text, low contrast, and console errors; the ledger helps flag repeated visual patterns across projects.\nThe workflow is HTML-native and does not support complex 3D or physics-based animation. Blank-brand work is described as lower quality, and the PPTX export preserves editable text boxes but does not make designs Figma-layer editable.",
  "source": {
    "name": "GitHub",
    "url": "https://github.com/alchaincyf/huashu-design",
    "published_at": null
  },
  "source_class": "tool",
  "content_type": "GitHub Repo",
  "layer": "agent",
  "domains": [
    "image",
    "video"
  ],
  "topics": [
    "skills",
    "generative-media",
    "design-engineering"
  ],
  "verification": {
    "status": "needs_review",
    "label": "Needs Review",
    "method": "unverified",
    "verified_at": null
  },
  "uncertainty": [],
  "connected_context": {
    "meaning": "Huashu turns agent-assisted design into a staged review workflow: compare six thumbnails, develop three directions, then refine and lint outputs. Its local preference notes and visual ledger support continuity across projects, while HTML-native production, weaker blank-brand results, and limited PPTX editability bound where the workflow fits.",
    "corpus_size": 910,
    "generated_at": "2026-10-26T11:00:55.610Z",
    "connections": [
      {
        "title": "Leonxlnx/taste-skill",
        "source_name": "GitHub",
        "source_url": "https://github.com/Leonxlnx/taste-skill",
        "feed7_url": "https://feed7.dev/p/taste-skill-15nf4kv",
        "reason": "Both encode design judgment for coding agents; Huashu adds a staged visual comparison and linting workflow, while taste-skill focuses on inferred design language and adjustable style choices."
      },
      {
        "title": "How our agents build on-brand pages with design.md",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/blog/how-our-agents-build-on-brand-pages-with-design-md",
        "feed7_url": "https://feed7.dev/p/how-our-agents-build-on-brand-pages-with-design-md-1gt2ft4",
        "reason": "Vercel separates brand guidance, CSS primitives, and repeatable evaluation; Huashu adds persistent local preferences and factual visual lint, giving concrete complementary mechanisms for consistency and review."
      },
      {
        "title": "cathrynlavery/diagram-design",
        "source_name": "GitHub",
        "source_url": "https://github.com/cathrynlavery/diagram-design",
        "feed7_url": "https://feed7.dev/p/diagram-design-1456lje",
        "reason": "Diagram Design applies reusable guidance to accessible HTML and SVG diagrams, whereas Huashu covers broader HTML-native design outputs; their constraints help identify when a focused diagram workflow is more appropriate."
      },
      {
        "title": "The Missing Layer: Design Taste in AI Agents — Hassan El Mghari, Together AI",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=7GMKdpLsxwU",
        "feed7_url": "https://feed7.dev/p/the-missing-layer-design-taste-in-ai-agents-hassan-el-mghari-together-ai-00err2g",
        "reason": "The talk recommends references, focused prompts, and iteration to improve agent-made UI; Huashu operationalizes part of that approach with multiple candidate directions and a review stage, without establishing that its checks settle subjective quality."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/huashu-design-1tyg5ud",
    "json": "https://feed7.dev/p/huashu-design-1tyg5ud.json",
    "markdown": "https://feed7.dev/p/huashu-design-1tyg5ud.md"
  }
}