{
  "schemaVersion": "1.0",
  "item": {
    "slug": "visual-prompt-engine",
    "name": "Visual Prompt Engine",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Abdullah4AI/visual-prompt-engine",
    "canonicalUrl": "https://clawhub.ai/Abdullah4AI/visual-prompt-engine",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/visual-prompt-engine",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=visual-prompt-engine",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "data/references.json",
      "data/style_cards.json",
      "references/prompt-patterns.md",
      "references/style-card-schema.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/visual-prompt-engine"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/visual-prompt-engine",
    "agentPageUrl": "https://openagent3.xyz/skills/visual-prompt-engine/agent",
    "manifestUrl": "https://openagent3.xyz/skills/visual-prompt-engine/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/visual-prompt-engine/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Visual Prompt Engine",
        "body": "Generate high-quality, diverse image prompts by feeding real visual references into a structured prompt pipeline."
      },
      {
        "title": "Problem",
        "body": "AI agents reuse the same visual patterns and clichés when writing image prompts. This skill breaks that cycle by grounding prompts in real, trending design work."
      },
      {
        "title": "Architecture",
        "body": "Dribbble Scraper → Style Cards → Prompt Generator → Quality Reviewer → Final Prompt"
      },
      {
        "title": "1. Collect Visual References",
        "body": "Recommended: Browser-based collection (Dribbble blocks automated requests)\n\nBrowse https://dribbble.com/shots/popular with a browser tool (Camofox, Playwright, etc.), collect shot URLs, titles, and image URLs, then save as JSON:\n\npython3 scripts/scrape_dribbble.py --method import --import-file manual_shots.json --output data/references.json\n\nAlternative: RSS/HTML (may be blocked by WAF)\n\npython3 scripts/scrape_dribbble.py --output data/references.json --count 20\n\nThe import JSON format: [{\"title\": \"...\", \"url\": \"https://dribbble.com/shots/...\", \"image_url\": \"...\"}]"
      },
      {
        "title": "2. Build Style Cards",
        "body": "Convert raw references into style cards:\n\npython3 scripts/style_card.py build --input data/references.json --output data/style_cards.json"
      },
      {
        "title": "3. Generate Prompts",
        "body": "When the user requests an image prompt:\n\nRead data/style_cards.json for available visual references\nSelect 1-3 cards relevant to the user's goal\nRead references/prompt-patterns.md for diverse prompt structures\nRead references/visual-vocabulary.md for precise design terminology\nCompose a prompt combining: user goal + style card elements + varied pattern\nCheck against recent prompts in data/prompt_history.json to prevent repetition\nAppend the new prompt to history"
      },
      {
        "title": "4. Review and Deliver",
        "body": "Before delivering, verify the prompt:\n\nUses specific visual language (not generic adjectives)\nReferences concrete design elements from the style card\nFollows a pattern different from the last 5 prompts\nIncludes composition, lighting, color palette, and mood"
      },
      {
        "title": "Style Card Schema",
        "body": "See references/style-card-schema.md for the full schema. A style card contains:\n\nFieldDescriptionpaletteHex colors extracted from the designcompositionLayout structure (grid, asymmetric, centered, etc.)typographyFont style and weight characteristicsmoodEmotional tone (bold, minimal, playful, etc.)texturesSurface qualities (glass, grain, matte, etc.)lightingLight direction and qualitysource_urlOriginal Dribbble shot URLtagsDesign categories"
      },
      {
        "title": "Prompt Patterns",
        "body": "See references/prompt-patterns.md for 12+ distinct prompt structures that prevent repetition. Rotate through patterns to keep outputs fresh."
      },
      {
        "title": "Visual Vocabulary",
        "body": "See references/visual-vocabulary.md for precise design terminology covering color, composition, lighting, texture, and typography. Use these terms instead of generic words like \"beautiful\" or \"nice\"."
      },
      {
        "title": "Automation (Optional)",
        "body": "Set up a daily cron to refresh visual references:\n\n# Run daily to keep references current\npython3 scripts/scrape_dribbble.py --output data/references.json --count 20\npython3 scripts/style_card.py build --input data/references.json --output data/style_cards.json"
      },
      {
        "title": "Data Directory",
        "body": "The skill stores working data in data/:\n\ndata/\n├── references.json      # Raw Dribbble scrape results\n├── style_cards.json     # Processed style cards\n└── prompt_history.json  # Generated prompts (for deduplication)\n\nCreate the data/ directory on first run if it does not exist."
      },
      {
        "title": "Dependencies",
        "body": "Python 3.9+ with standard library only. Optional: requests, beautifulsoup4 for live scraping (falls back to Dribbble RSS if not installed).\n\nInstall optional dependencies:\n\npip install requests beautifulsoup4"
      }
    ],
    "body": "Visual Prompt Engine\n\nGenerate high-quality, diverse image prompts by feeding real visual references into a structured prompt pipeline.\n\nProblem\n\nAI agents reuse the same visual patterns and clichés when writing image prompts. This skill breaks that cycle by grounding prompts in real, trending design work.\n\nArchitecture\nDribbble Scraper → Style Cards → Prompt Generator → Quality Reviewer → Final Prompt\n\nQuick Start\n1. Collect Visual References\n\nRecommended: Browser-based collection (Dribbble blocks automated requests)\n\nBrowse https://dribbble.com/shots/popular with a browser tool (Camofox, Playwright, etc.), collect shot URLs, titles, and image URLs, then save as JSON:\n\npython3 scripts/scrape_dribbble.py --method import --import-file manual_shots.json --output data/references.json\n\n\nAlternative: RSS/HTML (may be blocked by WAF)\n\npython3 scripts/scrape_dribbble.py --output data/references.json --count 20\n\n\nThe import JSON format: [{\"title\": \"...\", \"url\": \"https://dribbble.com/shots/...\", \"image_url\": \"...\"}]\n\n2. Build Style Cards\n\nConvert raw references into style cards:\n\npython3 scripts/style_card.py build --input data/references.json --output data/style_cards.json\n\n3. Generate Prompts\n\nWhen the user requests an image prompt:\n\nRead data/style_cards.json for available visual references\nSelect 1-3 cards relevant to the user's goal\nRead references/prompt-patterns.md for diverse prompt structures\nRead references/visual-vocabulary.md for precise design terminology\nCompose a prompt combining: user goal + style card elements + varied pattern\nCheck against recent prompts in data/prompt_history.json to prevent repetition\nAppend the new prompt to history\n4. Review and Deliver\n\nBefore delivering, verify the prompt:\n\nUses specific visual language (not generic adjectives)\nReferences concrete design elements from the style card\nFollows a pattern different from the last 5 prompts\nIncludes composition, lighting, color palette, and mood\nStyle Card Schema\n\nSee references/style-card-schema.md for the full schema. A style card contains:\n\nField\tDescription\npalette\tHex colors extracted from the design\ncomposition\tLayout structure (grid, asymmetric, centered, etc.)\ntypography\tFont style and weight characteristics\nmood\tEmotional tone (bold, minimal, playful, etc.)\ntextures\tSurface qualities (glass, grain, matte, etc.)\nlighting\tLight direction and quality\nsource_url\tOriginal Dribbble shot URL\ntags\tDesign categories\nPrompt Patterns\n\nSee references/prompt-patterns.md for 12+ distinct prompt structures that prevent repetition. Rotate through patterns to keep outputs fresh.\n\nVisual Vocabulary\n\nSee references/visual-vocabulary.md for precise design terminology covering color, composition, lighting, texture, and typography. Use these terms instead of generic words like \"beautiful\" or \"nice\".\n\nAutomation (Optional)\n\nSet up a daily cron to refresh visual references:\n\n# Run daily to keep references current\npython3 scripts/scrape_dribbble.py --output data/references.json --count 20\npython3 scripts/style_card.py build --input data/references.json --output data/style_cards.json\n\nData Directory\n\nThe skill stores working data in data/:\n\ndata/\n├── references.json      # Raw Dribbble scrape results\n├── style_cards.json     # Processed style cards\n└── prompt_history.json  # Generated prompts (for deduplication)\n\n\nCreate the data/ directory on first run if it does not exist.\n\nDependencies\n\nPython 3.9+ with standard library only. Optional: requests, beautifulsoup4 for live scraping (falls back to Dribbble RSS if not installed).\n\nInstall optional dependencies:\n\npip install requests beautifulsoup4"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Abdullah4AI/visual-prompt-engine",
    "publisherUrl": "https://clawhub.ai/Abdullah4AI/visual-prompt-engine",
    "owner": "Abdullah4AI",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/visual-prompt-engine",
    "downloadUrl": "https://openagent3.xyz/downloads/visual-prompt-engine",
    "agentUrl": "https://openagent3.xyz/skills/visual-prompt-engine/agent",
    "manifestUrl": "https://openagent3.xyz/skills/visual-prompt-engine/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/visual-prompt-engine/agent.md"
  }
}