{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pptx-2",
    "name": "Pptx",
    "source": "tencent",
    "type": "skill",
    "category": "内容创作",
    "sourceUrl": "https://clawhub.ai/liuyingduo/pptx-2",
    "canonicalUrl": "https://clawhub.ai/liuyingduo/pptx-2",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/pptx-2",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pptx-2",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "LICENSE.txt",
      "SKILL.md",
      "editing.md",
      "pptxgenjs.md",
      "scripts/__init__.py",
      "scripts/add_slide.py"
    ],
    "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. 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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/pptx-2"
    },
    "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/pptx-2",
    "agentPageUrl": "https://openagent3.xyz/skills/pptx-2/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pptx-2/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pptx-2/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. 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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Quick Reference",
        "body": "TaskGuideRead/analyze contentpython -m markitdown presentation.pptxEdit or create from templateRead editing.mdCreate from scratchRead pptxgenjs.md"
      },
      {
        "title": "Reading Content",
        "body": "# Text extraction\npython -m markitdown presentation.pptx\n\n# Visual overview\npython scripts/thumbnail.py presentation.pptx\n\n# Raw XML\npython scripts/office/unpack.py presentation.pptx unpacked/"
      },
      {
        "title": "Editing Workflow",
        "body": "Read editing.md for full details.\n\nAnalyze template with thumbnail.py\nUnpack → manipulate slides → edit content → clean → pack"
      },
      {
        "title": "Creating from Scratch",
        "body": "Read pptxgenjs.md for full details.\n\nUse when no template or reference presentation is available."
      },
      {
        "title": "Design Ideas",
        "body": "Don't create boring slides. Plain bullets on a white background won't impress anyone. Consider ideas from this list for each slide."
      },
      {
        "title": "Before Starting",
        "body": "Pick a bold, content-informed color palette: The palette should feel designed for THIS topic. If swapping your colors into a completely different presentation would still \"work,\" you haven't made specific enough choices.\nDominance over equality: One color should dominate (60-70% visual weight), with 1-2 supporting tones and one sharp accent. Never give all colors equal weight.\nDark/light contrast: Dark backgrounds for title + conclusion slides, light for content (\"sandwich\" structure). Or commit to dark throughout for a premium feel.\nCommit to a visual motif: Pick ONE distinctive element and repeat it — rounded image frames, icons in colored circles, thick single-side borders. Carry it across every slide."
      },
      {
        "title": "Color Palettes",
        "body": "Choose colors that match your topic — don't default to generic blue. Use these palettes as inspiration:\n\nThemePrimarySecondaryAccentMidnight Executive1E2761 (navy)CADCFC (ice blue)FFFFFF (white)Forest & Moss2C5F2D (forest)97BC62 (moss)F5F5F5 (cream)Coral EnergyF96167 (coral)F9E795 (gold)2F3C7E (navy)Warm TerracottaB85042 (terracotta)E7E8D1 (sand)A7BEAE (sage)Ocean Gradient065A82 (deep blue)1C7293 (teal)21295C (midnight)Charcoal Minimal36454F (charcoal)F2F2F2 (off-white)212121 (black)Teal Trust028090 (teal)00A896 (seafoam)02C39A (mint)Berry & Cream6D2E46 (berry)A26769 (dusty rose)ECE2D0 (cream)Sage Calm84B59F (sage)69A297 (eucalyptus)50808E (slate)Cherry Bold990011 (cherry)FCF6F5 (off-white)2F3C7E (navy)"
      },
      {
        "title": "For Each Slide",
        "body": "Every slide needs a visual element — image, chart, icon, or shape. Text-only slides are forgettable.\n\nLayout options:\n\nTwo-column (text left, illustration on right)\nIcon + text rows (icon in colored circle, bold header, description below)\n2x2 or 2x3 grid (image on one side, grid of content blocks on other)\nHalf-bleed image (full left or right side) with content overlay\n\nData display:\n\nLarge stat callouts (big numbers 60-72pt with small labels below)\nComparison columns (before/after, pros/cons, side-by-side options)\nTimeline or process flow (numbered steps, arrows)\n\nVisual polish:\n\nIcons in small colored circles next to section headers\nItalic accent text for key stats or taglines"
      },
      {
        "title": "Typography",
        "body": "Choose an interesting font pairing — don't default to Arial. Pick a header font with personality and pair it with a clean body font.\n\nHeader FontBody FontGeorgiaCalibriArial BlackArialCalibriCalibri LightCambriaCalibriTrebuchet MSCalibriImpactArialPalatinoGaramondConsolasCalibri\n\nElementSizeSlide title36-44pt boldSection header20-24pt boldBody text14-16ptCaptions10-12pt muted"
      },
      {
        "title": "Spacing",
        "body": "0.5\" minimum margins\n0.3-0.5\" between content blocks\nLeave breathing room—don't fill every inch"
      },
      {
        "title": "Avoid (Common Mistakes)",
        "body": "Don't repeat the same layout — vary columns, cards, and callouts across slides\nDon't center body text — left-align paragraphs and lists; center only titles\nDon't skimp on size contrast — titles need 36pt+ to stand out from 14-16pt body\nDon't default to blue — pick colors that reflect the specific topic\nDon't mix spacing randomly — choose 0.3\" or 0.5\" gaps and use consistently\nDon't style one slide and leave the rest plain — commit fully or keep it simple throughout\nDon't create text-only slides — add images, icons, charts, or visual elements; avoid plain title + bullets\nDon't forget text box padding — when aligning lines or shapes with text edges, set margin: 0 on the text box or offset the shape to account for padding\nDon't use low-contrast elements — icons AND text need strong contrast against the background; avoid light text on light backgrounds or dark text on dark backgrounds\nNEVER use accent lines under titles — these are a hallmark of AI-generated slides; use whitespace or background color instead"
      },
      {
        "title": "QA (Required)",
        "body": "Assume there are problems. Your job is to find them.\n\nYour first render is almost never correct. Approach QA as a bug hunt, not a confirmation step. If you found zero issues on first inspection, you weren't looking hard enough."
      },
      {
        "title": "Content QA",
        "body": "python -m markitdown output.pptx\n\nCheck for missing content, typos, wrong order.\n\nWhen using templates, check for leftover placeholder text:\n\npython -m markitdown output.pptx | grep -iE \"xxxx|lorem|ipsum|this.*(page|slide).*layout\"\n\nIf grep returns results, fix them before declaring success."
      },
      {
        "title": "Visual QA",
        "body": "⚠️ USE SUBAGENTS — even for 2-3 slides. You've been staring at the code and will see what you expect, not what's there. Subagents have fresh eyes.\n\nConvert slides to images (see Converting to Images), then use this prompt:\n\nVisually inspect these slides. Assume there are issues — find them.\n\nLook for:\n- Overlapping elements (text through shapes, lines through words, stacked elements)\n- Text overflow or cut off at edges/box boundaries\n- Decorative lines positioned for single-line text but title wrapped to two lines\n- Source citations or footers colliding with content above\n- Elements too close (< 0.3\" gaps) or cards/sections nearly touching\n- Uneven gaps (large empty area in one place, cramped in another)\n- Insufficient margin from slide edges (< 0.5\")\n- Columns or similar elements not aligned consistently\n- Low-contrast text (e.g., light gray text on cream-colored background)\n- Low-contrast icons (e.g., dark icons on dark backgrounds without a contrasting circle)\n- Text boxes too narrow causing excessive wrapping\n- Leftover placeholder content\n\nFor each slide, list issues or areas of concern, even if minor.\n\nRead and analyze these images:\n1. /path/to/slide-01.jpg (Expected: [brief description])\n2. /path/to/slide-02.jpg (Expected: [brief description])\n\nReport ALL issues found, including minor ones."
      },
      {
        "title": "Verification Loop",
        "body": "Generate slides → Convert to images → Inspect\nList issues found (if none found, look again more critically)\nFix issues\nRe-verify affected slides — one fix often creates another problem\nRepeat until a full pass reveals no new issues\n\nDo not declare success until you've completed at least one fix-and-verify cycle."
      },
      {
        "title": "Converting to Images",
        "body": "Convert presentations to individual slide images for visual inspection:\n\npython scripts/office/soffice.py --headless --convert-to pdf output.pptx\npdftoppm -jpeg -r 150 output.pdf slide\n\nThis creates slide-01.jpg, slide-02.jpg, etc.\n\nTo re-render specific slides after fixes:\n\npdftoppm -jpeg -r 150 -f N -l N output.pdf slide-fixed"
      },
      {
        "title": "Dependencies",
        "body": "pip install \"markitdown[pptx]\" - text extraction\npip install Pillow - thumbnail grids\nnpm install -g pptxgenjs - creating from scratch\nLibreOffice (soffice) - PDF conversion (auto-configured for sandboxed environments via scripts/office/soffice.py)\nPoppler (pdftoppm) - PDF to images"
      }
    ],
    "body": "PPTX Skill\nQuick Reference\nTask\tGuide\nRead/analyze content\tpython -m markitdown presentation.pptx\nEdit or create from template\tRead editing.md\nCreate from scratch\tRead pptxgenjs.md\nReading Content\n# Text extraction\npython -m markitdown presentation.pptx\n\n# Visual overview\npython scripts/thumbnail.py presentation.pptx\n\n# Raw XML\npython scripts/office/unpack.py presentation.pptx unpacked/\n\nEditing Workflow\n\nRead editing.md for full details.\n\nAnalyze template with thumbnail.py\nUnpack → manipulate slides → edit content → clean → pack\nCreating from Scratch\n\nRead pptxgenjs.md for full details.\n\nUse when no template or reference presentation is available.\n\nDesign Ideas\n\nDon't create boring slides. Plain bullets on a white background won't impress anyone. Consider ideas from this list for each slide.\n\nBefore Starting\nPick a bold, content-informed color palette: The palette should feel designed for THIS topic. If swapping your colors into a completely different presentation would still \"work,\" you haven't made specific enough choices.\nDominance over equality: One color should dominate (60-70% visual weight), with 1-2 supporting tones and one sharp accent. Never give all colors equal weight.\nDark/light contrast: Dark backgrounds for title + conclusion slides, light for content (\"sandwich\" structure). Or commit to dark throughout for a premium feel.\nCommit to a visual motif: Pick ONE distinctive element and repeat it — rounded image frames, icons in colored circles, thick single-side borders. Carry it across every slide.\nColor Palettes\n\nChoose colors that match your topic — don't default to generic blue. Use these palettes as inspiration:\n\nTheme\tPrimary\tSecondary\tAccent\nMidnight Executive\t1E2761 (navy)\tCADCFC (ice blue)\tFFFFFF (white)\nForest & Moss\t2C5F2D (forest)\t97BC62 (moss)\tF5F5F5 (cream)\nCoral Energy\tF96167 (coral)\tF9E795 (gold)\t2F3C7E (navy)\nWarm Terracotta\tB85042 (terracotta)\tE7E8D1 (sand)\tA7BEAE (sage)\nOcean Gradient\t065A82 (deep blue)\t1C7293 (teal)\t21295C (midnight)\nCharcoal Minimal\t36454F (charcoal)\tF2F2F2 (off-white)\t212121 (black)\nTeal Trust\t028090 (teal)\t00A896 (seafoam)\t02C39A (mint)\nBerry & Cream\t6D2E46 (berry)\tA26769 (dusty rose)\tECE2D0 (cream)\nSage Calm\t84B59F (sage)\t69A297 (eucalyptus)\t50808E (slate)\nCherry Bold\t990011 (cherry)\tFCF6F5 (off-white)\t2F3C7E (navy)\nFor Each Slide\n\nEvery slide needs a visual element — image, chart, icon, or shape. Text-only slides are forgettable.\n\nLayout options:\n\nTwo-column (text left, illustration on right)\nIcon + text rows (icon in colored circle, bold header, description below)\n2x2 or 2x3 grid (image on one side, grid of content blocks on other)\nHalf-bleed image (full left or right side) with content overlay\n\nData display:\n\nLarge stat callouts (big numbers 60-72pt with small labels below)\nComparison columns (before/after, pros/cons, side-by-side options)\nTimeline or process flow (numbered steps, arrows)\n\nVisual polish:\n\nIcons in small colored circles next to section headers\nItalic accent text for key stats or taglines\nTypography\n\nChoose an interesting font pairing — don't default to Arial. Pick a header font with personality and pair it with a clean body font.\n\nHeader Font\tBody Font\nGeorgia\tCalibri\nArial Black\tArial\nCalibri\tCalibri Light\nCambria\tCalibri\nTrebuchet MS\tCalibri\nImpact\tArial\nPalatino\tGaramond\nConsolas\tCalibri\nElement\tSize\nSlide title\t36-44pt bold\nSection header\t20-24pt bold\nBody text\t14-16pt\nCaptions\t10-12pt muted\nSpacing\n0.5\" minimum margins\n0.3-0.5\" between content blocks\nLeave breathing room—don't fill every inch\nAvoid (Common Mistakes)\nDon't repeat the same layout — vary columns, cards, and callouts across slides\nDon't center body text — left-align paragraphs and lists; center only titles\nDon't skimp on size contrast — titles need 36pt+ to stand out from 14-16pt body\nDon't default to blue — pick colors that reflect the specific topic\nDon't mix spacing randomly — choose 0.3\" or 0.5\" gaps and use consistently\nDon't style one slide and leave the rest plain — commit fully or keep it simple throughout\nDon't create text-only slides — add images, icons, charts, or visual elements; avoid plain title + bullets\nDon't forget text box padding — when aligning lines or shapes with text edges, set margin: 0 on the text box or offset the shape to account for padding\nDon't use low-contrast elements — icons AND text need strong contrast against the background; avoid light text on light backgrounds or dark text on dark backgrounds\nNEVER use accent lines under titles — these are a hallmark of AI-generated slides; use whitespace or background color instead\nQA (Required)\n\nAssume there are problems. Your job is to find them.\n\nYour first render is almost never correct. Approach QA as a bug hunt, not a confirmation step. If you found zero issues on first inspection, you weren't looking hard enough.\n\nContent QA\npython -m markitdown output.pptx\n\n\nCheck for missing content, typos, wrong order.\n\nWhen using templates, check for leftover placeholder text:\n\npython -m markitdown output.pptx | grep -iE \"xxxx|lorem|ipsum|this.*(page|slide).*layout\"\n\n\nIf grep returns results, fix them before declaring success.\n\nVisual QA\n\n⚠️ USE SUBAGENTS — even for 2-3 slides. You've been staring at the code and will see what you expect, not what's there. Subagents have fresh eyes.\n\nConvert slides to images (see Converting to Images), then use this prompt:\n\nVisually inspect these slides. Assume there are issues — find them.\n\nLook for:\n- Overlapping elements (text through shapes, lines through words, stacked elements)\n- Text overflow or cut off at edges/box boundaries\n- Decorative lines positioned for single-line text but title wrapped to two lines\n- Source citations or footers colliding with content above\n- Elements too close (< 0.3\" gaps) or cards/sections nearly touching\n- Uneven gaps (large empty area in one place, cramped in another)\n- Insufficient margin from slide edges (< 0.5\")\n- Columns or similar elements not aligned consistently\n- Low-contrast text (e.g., light gray text on cream-colored background)\n- Low-contrast icons (e.g., dark icons on dark backgrounds without a contrasting circle)\n- Text boxes too narrow causing excessive wrapping\n- Leftover placeholder content\n\nFor each slide, list issues or areas of concern, even if minor.\n\nRead and analyze these images:\n1. /path/to/slide-01.jpg (Expected: [brief description])\n2. /path/to/slide-02.jpg (Expected: [brief description])\n\nReport ALL issues found, including minor ones.\n\nVerification Loop\nGenerate slides → Convert to images → Inspect\nList issues found (if none found, look again more critically)\nFix issues\nRe-verify affected slides — one fix often creates another problem\nRepeat until a full pass reveals no new issues\n\nDo not declare success until you've completed at least one fix-and-verify cycle.\n\nConverting to Images\n\nConvert presentations to individual slide images for visual inspection:\n\npython scripts/office/soffice.py --headless --convert-to pdf output.pptx\npdftoppm -jpeg -r 150 output.pdf slide\n\n\nThis creates slide-01.jpg, slide-02.jpg, etc.\n\nTo re-render specific slides after fixes:\n\npdftoppm -jpeg -r 150 -f N -l N output.pdf slide-fixed\n\nDependencies\npip install \"markitdown[pptx]\" - text extraction\npip install Pillow - thumbnail grids\nnpm install -g pptxgenjs - creating from scratch\nLibreOffice (soffice) - PDF conversion (auto-configured for sandboxed environments via scripts/office/soffice.py)\nPoppler (pdftoppm) - PDF to images"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/liuyingduo/pptx-2",
    "publisherUrl": "https://clawhub.ai/liuyingduo/pptx-2",
    "owner": "liuyingduo",
    "version": "0.1.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pptx-2",
    "downloadUrl": "https://openagent3.xyz/downloads/pptx-2",
    "agentUrl": "https://openagent3.xyz/skills/pptx-2/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pptx-2/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pptx-2/agent.md"
  }
}