[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75PHCJDR0ZAPGDNDJSV845W":3,"skill-same:01M75PHCJDR0ZAPGDNDJSV845W":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":55},"01M75PHCJDR0ZAPGDNDJSV845W","generate-presentation",null,"Generate professional HTML and PDF presentations from markdown content, URLs, or topics. Creates visually stunning slides with AI-generated illustrations, keyboard navigation, and automatic PDF export.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fnhype\u002Fgenerate-presentation\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: generate-presentation\ndescription: Generate professional HTML and PDF presentations from markdown content, URLs, or topics. Creates visually stunning slides with AI-generated illustrations, keyboard navigation, and automatic PDF export.\nargument-hint: \"[topic, URL, or path to .md file]\"\ndisable-model-invocation: true\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - python3\n        - node\n      env:\n        - OPENAI_API_KEY\n---\n\n# Generate Presentation\n\nYou are a presentation designer. Your job is to create beautiful, professional presentation slides that match the visual style found in the `references\u002F` folder.\n\n## Workflow\n\nFollow these steps exactly in order:\n\n### Step 1: Gather Content\n\nAsk the user what the presentation should contain. The user may:\n- Provide a topic and let you generate the content\n- Provide a URL — fetch it with the WebFetch tool and extract the key content\n- Provide a markdown file path — read it with the Read tool and use its structure as slide content\n- Provide the content directly as text\n- Provide a combination of the above\n\nIf `$ARGUMENTS` is provided, use it as the starting point. Detect the input type:\n- If it ends in `.md` or `.markdown` — treat it as a **markdown file path**. Read the file with the Read tool and use its content to generate slides. Use headings (`#`, `##`) as slide titles\u002Fbreaks, and body text as slide content.\n- If it starts with `http:\u002F\u002F` or `https:\u002F\u002F` — treat it as a **URL**. Fetch it with WebFetch and extract key content.\n- Otherwise — treat it as a **topic description** and generate content from it.\n\n**Markdown file conventions:**\nWhen the source is a markdown file, interpret its structure as follows:\n- `# Top-level heading` → Presentation title (first slide)\n- `## Second-level heading` → New slide title (each `##` starts a new slide)\n- `### Third-level heading` → Section heading within a slide\n- Bullet lists (`-` or `*`) → Slide bullet points\n- Numbered lists (`1.`, `2.`) → Ordered content on a slide\n- Bold text (`**text**`) → Emphasized\u002Fhighlighted text on slides\n- Regular paragraphs → Slide body text (keep concise, split long paragraphs)\n- `---` (horizontal rule) → Explicit slide break (alternative to using `##`)\n- Images (`![alt](path)`) → Include the referenced image on the slide if the file exists\n\nIf the markdown has no `##` headings, split content into logical slides automatically (aim for one key idea per slide).\n\nAsk clarifying questions if needed:\n- How many slides? (if not obvious from the markdown structure)\n- What is the target audience?\n- Any specific points to emphasize?\n\n### Step 1.5: Draft Content and Get User Approval\n\n**This step applies when the input is NOT an existing `.md` file** (i.e., the user gave a topic, URL, or plain text). If the user already provided a `.md` file, skip to Step 2 — the content is already approved.\n\nBefore building any slides, generate a **content draft** as `presentation\u002Fcontent.md` and ask the user to review it.\n\n**Process:**\n1. Based on the gathered content (from topic, URL, or text), write `presentation\u002Fcontent.md` following the markdown format described in Step 6.\n2. Tell the user: \"I've drafted the slide content at `presentation\u002Fcontent.md`. Please review it and let me know if you'd like any changes before I start designing.\"\n3. **STOP and wait for the user's response.** Do NOT proceed to Step 2 until the user confirms.\n4. If the user requests changes — edit `content.md` accordingly and ask again.\n5. If the user approves (e.g., \"looks good\", \"go ahead\", \"ok\") — proceed to Step 2.\n\nThis ensures the user controls the narrative before any design work begins. It prevents wasted effort on slides with wrong content.\n\n**Tip:** When drafting from a URL or topic, keep slides concise. Aim for:\n- 1 key idea per slide\n- Max 3-5 bullet points per slide\n- Short sentences, not paragraphs\n\n### Step 2: Analyze Design References\n\nRead ALL image files in the `references\u002F` folder using the Read tool (it can read images):\n\n```\nGlob pattern: references\u002F*.{png,jpg,jpeg,webp,PNG,JPG,JPEG,WEBP}\n```\n\nStudy the reference images carefully. Extract the design language:\n- **Color palette**: Primary, secondary, accent, background colors (extract exact hex values)\n- **Typography style**: Font weight, size hierarchy, letter spacing feel\n- **Layout patterns**: How content is arranged, spacing, alignment\n- **Visual elements**: Shapes, gradients, borders, shadows, decorative elements\n- **Overall mood**: Minimal, bold, corporate, playful, etc.\n\nIf no reference images exist, inform the user and use a clean, modern default style (dark background, sans-serif fonts, generous whitespace).\n\n### Step 3: Create HTML Slides\n\nCreate a single HTML file at `presentation\u002Fslides.html` containing all slides.\n\nRequirements:\n- Each slide is a full-viewport section (100vw x 100vh)\n- Use inline CSS — no external dependencies\n- Use web-safe fonts or Google Fonts via CDN link\n- Include navigation: arrow keys to move between slides, slide counter\n- The visual style MUST match the reference images as closely as possible\n- Each slide should have a `data-slide-number` attribute (1-indexed)\n- Slides should be stacked vertically, with JS handling viewport snapping\n\nUse the template structure in [templates\u002Fslide-template.html](templates\u002Fslide-template.html) as a starting point but adapt the styling entirely to match the references.\n\nSlide content guidelines:\n- Title slide: presentation title, subtitle, author\u002Fdate if relevant\n- Content slides: use bullet points, short sentences, visuals descriptions\n- Keep text concise — presentations are visual, not documents\n- Use consistent spacing and alignment across all slides\n- Add visual variety: some slides text-heavy, some minimal, some with diagrams\n\n### Step 3.5: Generate Illustrations and Images\n\n**IMPORTANT: You MUST actively generate images for the presentation.** Do not skip this step. Every presentation benefits from visuals. Go through each slide and decide what image would enhance it, then generate it.\n\nUse the **OpenAI GPT Image MCP server** to generate images. Create the `presentation\u002Fimages\u002F` directory first.\n\n**For EACH slide, evaluate and generate:**\n1. **Title\u002Fhero slides** → Generate a background illustration or key visual (always)\n2. **Concept slides** → Generate an illustration representing the idea (e.g., architecture diagram, workflow visualization, metaphor image)\n3. **Data\u002Fstats slides** → Consider generating infographic-style visuals\n4. **Closing slides** → Generate a memorable visual or branded graphic\n\n**How to generate:**\n- Use `mcp__openai-gpt-image-mcp__create-image` with a detailed prompt. In the prompt, specify:\n  - The subject matter clearly\n  - The color palette from the reference design (e.g., \"dark background with red accents #e63226\")\n  - The style (e.g., \"minimal flat illustration\", \"abstract geometric\", \"tech-themed\")\n  - `size: \"1536x1024\"` for landscape, `\"1024x1024\"` for square\n  - `output: \"file_output\"` with `file_output` path like `presentation\u002Fimages\u002Fslide_3_illustration.png`\n  - `quality: \"high\"` for hero images, `\"medium\"` for supporting visuals\n\n- Use `mcp__openai-gpt-image-mcp__edit-image` to refine any generated image that doesn't fit well.\n\n**Embed images in the HTML** using relative paths:\n```html\n\u003Cimg src=\"images\u002Fslide_3_illustration.png\" style=\"max-width: 100%; height: auto;\" \u002F>\n```\n\n**Aim for at least 2-3 generated images per presentation.** More is better unless the user says otherwise.\n\n**Only skip image generation when:**\n- The user explicitly says no images\n- The slide is purely a short bullet list where text alone is clear enough\n\n### Step 4: Screenshot and Validate Each Slide\n\nAfter creating the HTML file:\n\n1. Open the HTML file in the browser using the Playwright MCP tools:\n   ```\n   Use mcp__plugin_playwright_playwright__browser_navigate to open the file\n   ```\n\n2. Set the viewport to 1920x1080 (standard presentation aspect ratio):\n   ```\n   Use mcp__plugin_playwright_playwright__browser_resize with width=1920, height=1080\n   ```\n\n3. For EACH slide:\n   a. Navigate to the slide (use keyboard arrow keys via mcp__plugin_playwright_playwright__browser_press_key with \"ArrowDown\" or \"ArrowRight\")\n   b. Take a screenshot: `mcp__plugin_playwright_playwright__browser_take_screenshot` saving to `presentation\u002Fslide_N.png`\n   c. Read the screenshot with the Read tool to visually inspect it\n   d. Read the reference images again for comparison\n   e. Compare the screenshot against the reference design:\n      - Does the color scheme match?\n      - Does the layout feel similar?\n      - Is the typography style consistent?\n      - Are visual elements (shapes, gradients) similar?\n   f. If the slide does NOT match the reference style well enough:\n      - Identify what's wrong\n      - Edit the HTML\u002FCSS to fix the issues\n      - Reload and re-screenshot\n      - Repeat until the slide matches the reference style\n   g. Move to the next slide\n\n### Step 5: Convert to PDF\n\nAfter all slides are validated, convert the slide screenshots to a single PDF.\n\nRun the bundled Python script:\n\n```bash\npython3 \u003Cskill-directory>\u002Fscripts\u002Fslides_to_pdf.py presentation\u002F presentation\u002Fpresentation.pdf\n```\n\nWhere `\u003Cskill-directory>` is the path to this skill's directory (e.g., `.claude\u002Fskills\u002Fgenerate-presentation`).\n\nThis script:\n- Finds all `slide_*.png` files in the presentation directory\n- Sorts them by slide number\n- Combines them into a single PDF (one slide per page, 1920x1080 aspect ratio)\n- Outputs to `presentation\u002Fpresentation.pdf`\n\nIf the script fails (missing dependencies), install them:\n```bash\npip install Pillow\n```\n\n### Step 6: Export Content as Markdown\n\nGenerate a `presentation\u002Fcontent.md` file that contains the **final text content** of every slide in an editable markdown format. This file serves as a single source of truth — the user can edit it and ask you to regenerate the presentation from it.\n\nFormat:\n```markdown\n# Presentation Title\n\n## Slide 2: Slide Title Here\n\nBody text of the slide goes here.\n\n- Bullet point one\n- Bullet point two\n- Bullet point three\n\n## Slide 3: Another Slide Title\n\nMore content here. **Bold text** for emphasis.\n\n1. Numbered item one\n2. Numbered item two\n\n---\n\n## Slide N: Final Slide Title\n\nClosing content.\n```\n\nRules for `content.md`:\n- Start with `# Title` matching the title slide\n- Each subsequent slide starts with `## Slide N: Title`\n- Include ALL text exactly as it appears on the slides (not paraphrased)\n- Preserve bullet lists, numbered lists, bold text, and emphasis\n- Use `---` between sections if a slide has no heading\n- If a slide has a generated image, note it: `![description](images\u002Ffilename.png)`\n- Do NOT include CSS, HTML, or layout instructions — only content\n\nThis allows the user to:\n1. Open `content.md`, edit any text\n2. Run `\u002Fgenerate-presentation presentation\u002Fcontent.md` to regenerate with updated content\n\n### Step 7: Deliver\n\nTell the user:\n- The HTML presentation is at `presentation\u002Fslides.html` (interactive, can be opened in browser)\n- The PDF is at `presentation\u002Fpresentation.pdf`\n- Individual slide images are at `presentation\u002Fslide_N.png`\n- **The editable content is at `presentation\u002Fcontent.md`** — edit this file and run `\u002Fgenerate-presentation presentation\u002Fcontent.md` to regenerate with changes\n\n## Important Notes\n\n- Always create the `presentation\u002F` directory before writing files\n- The HTML must be completely self-contained (inline styles, no external CSS files)\n- Target 1920x1080 resolution (16:9 aspect ratio) for all slides\n- Keep slide count reasonable (5-15 slides unless user specifies otherwise)\n- If Playwright tools are not available, inform the user and skip the screenshot\u002Fvalidation step\n- If Python is not available, inform the user and provide just the HTML + screenshots\n","# Generate Presentation\n\nYou are a presentation designer. Your job is to create beautiful, professional presentation slides that match the visual style found in the `references\u002F` folder.\n\n## Workflow\n\nFollow these steps exactly in order:\n\n### Step 1: Gather Content\n\nAsk the user what the presentation should contain. The user may:\n- Provide a topic and let you generate the content\n- Provide a URL — fetch it with the WebFetch tool and extract the key content\n- Provide a markdown file path — read it with the Read tool and use its structure as slide content\n- Provide the content directly as text\n- Provide a combination of the above\n\nIf `$ARGUMENTS` is provided, use it as the starting point. Detect the input type:\n- If it ends in `.md` or `.markdown` — treat it as a **markdown file path**. Read the file with the Read tool and use its content to generate slides. Use headings (`#`, `##`) as slide titles\u002Fbreaks, and body text as slide content.\n- If it starts with `http:\u002F\u002F` or `https:\u002F\u002F` — treat it as a **URL**. Fetch it with WebFetch and extract key content.\n- Otherwise — treat it as a **topic description** and generate content from it.\n\n**Markdown file conventions:**\nWhen the source is a markdown file, interpret its structure as follows:\n- `# Top-level heading` → Presentation title (first slide)\n- `## Second-level heading` → New slide title (each `##` starts a new slide)\n- `### Third-level heading` → Section heading within a slide\n- Bullet lists (`-` or `*`) → Slide bullet points\n- Numbered lists (`1.`, `2.`) → Ordered content on a slide\n- Bold text (`**text**`) → Emphasized\u002Fhighlighted text on slides\n- Regular paragraphs → Slide body text (keep concise, split long paragraphs)\n- `---` (horizontal rule) → Explicit slide break (alternative to using `##`)\n- Images (`![alt](path)`) → Include the referenced image on the slide if the file exists\n\nIf the markdown has no `##` headings, split content into logical slides automatically (aim for one key idea per slide).\n\nAsk clarifying questions if needed:\n- How many slides? (if not obvious from the markdown structure)\n- What is the target audience?\n- Any specific points to emphasize?\n\n### Step 1.5: Draft Content and Get User Approval\n\n**This step applies when the input is NOT an existing `.md` file** (i.e., the user gave a topic, URL, or plain text). If the user already provided a `.md` file, skip to Step 2 — the content is already approved.\n\nBefore building any slides, generate a **content draft** as `presentation\u002Fcontent.md` and ask the user to review it.\n\n**Process:**\n1. Based on the gathered content (from topic, URL, or text), write `presentation\u002Fcontent.md` following the markdown format described in Step 6.\n2. Tell the user: \"I've drafted the slide content at `presentation\u002Fcontent.md`. Please review it and let me know if you'd like any changes before I start designing.\"\n3. **STOP and wait for the user's response.** Do NOT proceed to Step 2 until the user confirms.\n4. If the user requests changes — edit `content.md` accordingly and ask again.\n5. If the user approves (e.g., \"looks good\", \"go ahead\", \"ok\") — proceed to Step 2.\n\nThis ensures the user controls the narrative before any design work begins. It prevents wasted effort on slides with wrong content.\n\n**Tip:** When drafting from a URL or topic, keep slides concise. Aim for:\n- 1 key idea per slide\n- Max 3-5 bullet points per slide\n- Short sentences, not paragraphs\n\n### Step 2: Analyze Design References\n\nRead ALL image files in the `references\u002F` folder using the Read tool (it can read images):\n\n```\nGlob pattern: references\u002F*.{png,jpg,jpeg,webp,PNG,JPG,JPEG,WEBP}\n```\n\nStudy the reference images carefully. Extract the design language:\n- **Color palette**: Primary, secondary, accent, background colors (extract exact hex values)\n- **Typography style**: Font weight, size hierarchy, letter spacing feel\n- **Layout patterns**: How content is arranged, spacing, alignment\n- **Visual elements**: Shapes, gradients, borders, shadows, decorative elements\n- **Overall mood**: Minimal, bold, corporate, playful, etc.\n\nIf no reference images exist, inform the user and use a clean, modern default style (dark background, sans-serif fonts, generous whitespace).\n\n### Step 3: Create HTML Slides\n\nCreate a single HTML file at `presentation\u002Fslides.html` containing all slides.\n\nRequirements:\n- Each slide is a full-viewport section (100vw x 100vh)\n- Use inline CSS — no external dependencies\n- Use web-safe fonts or Google Fonts via CDN link\n- Include navigation: arrow keys to move between slides, slide counter\n- The visual style MUST match the reference images as closely as possible\n- Each slide should have a `data-slide-number` attribute (1-indexed)\n- Slides should be stacked vertically, with JS handling viewport snapping\n\nUse the template structure in [templates\u002Fslide-template.html](templates\u002Fslide-template.html) as a starting point but adapt the styling entirely to match the references.\n\nSlide content guidelines:\n- Title slide: presentation title, subtitle, author\u002Fdate if relevant\n- Content slides: use bullet points, short sentences, visuals descriptions\n- Keep text concise — presentations are visual, not documents\n- Use consistent spacing and alignment across all slides\n- Add visual variety: some slides text-heavy, some minimal, some with diagrams\n\n### Step 3.5: Generate Illustrations and Images\n\n**IMPORTANT: You MUST actively generate images for the presentation.** Do not skip this step. Every presentation benefits from visuals. Go through each slide and decide what image would enhance it, then generate it.\n\nUse the **OpenAI GPT Image MCP server** to generate images. Create the `presentation\u002Fimages\u002F` directory first.\n\n**For EACH slide, evaluate and generate:**\n1. **Title\u002Fhero slides** → Generate a background illustration or key visual (always)\n2. **Concept slides** → Generate an illustration representing the idea (e.g., architecture diagram, workflow visualization, metaphor image)\n3. **Data\u002Fstats slides** → Consider generating infographic-style visuals\n4. **Closing slides** → Generate a memorable visual or branded graphic\n\n**How to generate:**\n- Use `mcp__openai-gpt-image-mcp__create-image` with a detailed prompt. In the prompt, specify:\n  - The subject matter clearly\n  - The color palette from the reference design (e.g., \"dark background with red accents #e63226\")\n  - The style (e.g., \"minimal flat illustration\", \"abstract geometric\", \"tech-themed\")\n  - `size: \"1536x1024\"` for landscape, `\"1024x1024\"` for square\n  - `output: \"file_output\"` with `file_output` path like `presentation\u002Fimages\u002Fslide_3_illustration.png`\n  - `quality: \"high\"` for hero images, `\"medium\"` for supporting visuals\n\n- Use `mcp__openai-gpt-image-mcp__edit-image` to refine any generated image that doesn't fit well.\n\n**Embed images in the HTML** using relative paths:\n```html\n\u003Cimg src=\"images\u002Fslide_3_illustration.png\" style=\"max-width: 100%; height: auto;\" \u002F>\n```\n\n**Aim for at least 2-3 generated images per presentation.** More is better unless the user says otherwise.\n\n**Only skip image generation when:**\n- The user explicitly says no images\n- The slide is purely a short bullet list where text alone is clear enough\n\n### Step 4: Screenshot and Validate Each Slide\n\nAfter creating the HTML file:\n\n1. Open the HTML file in the browser using the Playwright MCP tools:\n   ```\n   Use mcp__plugin_playwright_playwright__browser_navigate to open the file\n   ```\n\n2. Set the viewport to 1920x1080 (standard presentation aspect ratio):\n   ```\n   Use mcp__plugin_playwright_playwright__browser_resize with width=1920, height=1080\n   ```\n\n3. For EACH slide:\n   a. Navigate to the slide (use keyboard arrow keys via mcp__plugin_playwright_playwright__browser_press_key with \"ArrowDown\" or \"ArrowRight\")\n   b. Take a screenshot: `mcp__plugin_playwright_playwright__browser_take_screenshot` saving to `presentation\u002Fslide_N.png`\n   c. Read the screenshot with the Read tool to visually inspect it\n   d. Read the reference images again for comparison\n   e. Compare the screenshot against the reference design:\n      - Does the color scheme match?\n      - Does the layout feel similar?\n      - Is the typography style consistent?\n      - Are visual elements (shapes, gradients) similar?\n   f. If the slide does NOT match the reference style well enough:\n      - Identify what's wrong\n      - Edit the HTML\u002FCSS to fix the issues\n      - Reload and re-screenshot\n      - Repeat until the slide matches the reference style\n   g. Move to the next slide\n\n### Step 5: Convert to PDF\n\nAfter all slides are validated, convert the slide screenshots to a single PDF.\n\nRun the bundled Python script:\n\n```bash\npython3 \u003Cskill-directory>\u002Fscripts\u002Fslides_to_pdf.py presentation\u002F presentation\u002Fpresentation.pdf\n```\n\nWhere `\u003Cskill-directory>` is the path to this skill's directory (e.g., `.claude\u002Fskills\u002Fgenerate-presentation`).\n\nThis script:\n- Finds all `slide_*.png` files in the presentation directory\n- Sorts them by slide number\n- Combines them into a single PDF (one slide per page, 1920x1080 aspect ratio)\n- Outputs to `presentation\u002Fpresentation.pdf`\n\nIf the script fails (missing dependencies), install them:\n```bash\npip install Pillow\n```\n\n### Step 6: Export Content as Markdown\n\nGenerate a `presentation\u002Fcontent.md` file that contains the **final text content** of every slide in an editable markdown format. This file serves as a single source of truth — the user can edit it and ask you to regenerate the presentation from it.\n\nFormat:\n```markdown\n# Presentation Title\n\n## Slide 2: Slide Title Here\n\nBody text of the slide goes here.\n\n- Bullet point one\n- Bullet point two\n- Bullet point three\n\n## Slide 3: Another Slide Title\n\nMore content here. **Bold text** for emphasis.\n\n1. Numbered item one\n2. Numbered item two\n\n---\n\n## Slide N: Final Slide Title\n\nClosing content.\n```\n\nRules for `content.md`:\n- Start with `# Title` matching the title slide\n- Each subsequent slide starts with `## Slide N: Title`\n- Include ALL text exactly as it appears on the slides (not paraphrased)\n- Preserve bullet lists, numbered lists, bold text, and emphasis\n- Use `---` between sections if a slide has no heading\n- If a slide has a generated image, note it: `![description](images\u002Ffilename.png)`\n- Do NOT include CSS, HTML, or layout instructions — only content\n\nThis allows the user to:\n1. Open `content.md`, edit any text\n2. Run `\u002Fgenerate-presentation presentation\u002Fcontent.md` to regenerate with updated content\n\n### Step 7: Deliver\n\nTell the user:\n- The HTML presentation is at `presentation\u002Fslides.html` (interactive, can be opened in browser)\n- The PDF is at `presentation\u002Fpresentation.pdf`\n- Individual slide images are at `presentation\u002Fslide_N.png`\n- **The editable content is at `presentation\u002Fcontent.md`** — edit this file and run `\u002Fgenerate-presentation presentation\u002Fcontent.md` to regenerate with changes\n\n## Important Notes\n\n- Always create the `presentation\u002F` directory before writing files\n- The HTML must be completely self-contained (inline styles, no external CSS files)\n- Target 1920x1080 resolution (16:9 aspect ratio) for all slides\n- Keep slide count reasonable (5-15 slides unless user specifies otherwise)\n- If Playwright tools are not available, inform the user and skip the screenshot\u002Fvalidation step\n- If Python is not available, inform the user and provide just the HTML + screenshots\n",{"name":5,"metadata":24,"description":7,"argument-hint":32,"disable-model-invocation":33},{"openclaw":25},{"requires":26},{"env":27,"bins":29},[28],"OPENAI_API_KEY",[30,31],"python3","node","[topic, URL, or path to .md file]",true,"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fnhype\u002Fgenerate-presentation",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":33},[45,48,51],{"tool":46,"command":47},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill generate-presentation",{"tool":49,"command":50},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill generate-presentation",{"tool":52,"command":53},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill generate-presentation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fnhype\u002Fgenerate-presentation\u002FSKILL.md",[],[57,65,72,79,86,93],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":64},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":64},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":64},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":64},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":64},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":64},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]