[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CS6R0D3TMW70TGCBZGH42W":3,"skill-same:01M7CS6R0D3TMW70TGCBZGH42W":68},{"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":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":36,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M7CS6R0D3TMW70TGCBZGH42W","glmv-pdf-to-web",null,"Convert a PDF (research paper, technical report, or project document) into a beautiful single-page academic\u002Fproject website with a structured outline JSON. Trigger this skill when the user wants to make a paper page, project homepage, or academic website from a PDF — in Chinese or English.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills-v4\u002Fglmv-pdf-to-web\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: glmv-pdf-to-web\ndescription:\n  Convert a PDF (research paper, technical report, or project document) into a beautiful\n  single-page academic\u002Fproject website with a structured outline JSON. Trigger this\n  skill when the user wants to make a paper page, project homepage, or academic website\n  from a PDF — in Chinese or English.\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - python\n    emoji: \"🌐\"\n    homepage: https:\u002F\u002Fgithub.com\u002Fzai-org\u002FGLM-V\u002Ftree\u002Fmain\u002Fskills\u002Fglmv-pdf-to-web\n---\n\n# PDF → Academic Project Website Skill\n\nConvert a research paper or technical document PDF into a polished single-page project website — the kind used for NeurIPS\u002FCVPR\u002FICLR paper releases. Pages are converted locally at DPI 120, a structured `outline.json` is saved, images are cropped locally, and the final page is saved with `generate_web.py`.\n\n**Scripts are in:** `{SKILL_DIR}\u002Fscripts\u002F`\n\n## Dependencies\n\nPython packages (install once):\n```bash\npip install pymupdf pillow\n```\n\nSystem tools: `curl` (pre-installed on macOS\u002FLinux).\n\n## When to Use\n\nTrigger when the user asks to create a webpage or project page from a PDF — phrases like:\n\"make a project page from a PDF\", \"create a paper website\", \"build an academic website for this paper\", \"论文主页\", \"做项目主页\", \"根据pdf做网页\", \"把论文做成主页\", or any similar intent in Chinese or English.\n\n## Output Directory Convention\n\nAll output goes under `{WORKSPACE}\u002Fweb\u002F\u003Cpdf_stem>_\u003Ctimestamp>\u002F`:\n\n```\nweb\u002F\n└── \u003Cpdf_stem>_\u003Ctimestamp>\u002F\n    ├── outline.json        ← structured web plan (WebPlan schema)\n    ├── crops\u002F              ← locally-saved cropped images\n    │   ├── fig_arch_crop.png\n    │   ├── table_results_crop.png\n    │   └── ...\n    └── index.html          ← the website\n```\n\n- `\u003Cpdf_stem>` = PDF filename without extension\n- `\u003Ctimestamp>` = format `YYYYMMDD_HHMMSS`\n- HTML references images via relative path `crops\u002F\u003Cname>_crop.png`\n\n## Input\n\n`$ARGUMENTS` is the path to the PDF file (local) or an HTTP\u002FHTTPS URL.\n\n- If user provides a **URL**: download with curl first, then convert\n- If user provides a **local PDF path**: convert directly\n\n---\n\n## Workflow\n\n### Phase 0 — Create Output Directory\n\n```python\nimport os, datetime\npdf_stem = os.path.splitext(os.path.basename(pdf_path))[0]\ntimestamp = datetime.datetime.now().strftime(\"%Y%m%d_%H%M%S\")\nout_dir = os.path.join(workspace, \"web\", f\"{pdf_stem}_{timestamp}\")\n```\n\n```bash\nmkdir -p \"\u003Cout_dir>\u002Fcrops\"\n```\n\n---\n\n### Phase 1 — Convert PDF Pages to Images (DPI 120)\n\nIf the input is a URL, download it first:\n```bash\npdf_stem=$(basename \"$ARGUMENTS\" .pdf)\ncurl -L -o \"\u002Ftmp\u002F${pdf_stem}.pdf\" \"$ARGUMENTS\"\n```\nThen convert (pass either the downloaded path or the original local path):\n```bash\npython {SKILL_DIR}\u002Fscripts\u002Fpdf_to_images.py \"\u003Cpdf_path>\" --dpi 120\n```\n\nOutputs JSON to stdout:\n```json\n[{\"page\": 1, \"path\": \"\u002Fabs\u002Fpath\u002Fpage_001.png\"}, ...]\n```\n\nParse and store the full `page → path` map.\n\n---\n\n### Phase 2 — Read All Pages in Order\n\nView **all page images** sequentially before planning. Goal: pure understanding of the document's content, figures, and structure.\n\nWhile reading, note:\n- Title, authors, affiliations, venue, year\n- Abstract text (verbatim)\n- Key contributions\n- Paper\u002FCode\u002FDataset links (arXiv, GitHub, etc.)\n- Figures, tables, diagrams — which pages, rough regions\n- Teaser\u002Fhero figure if present\n\nDo NOT plan sections yet — read everything first.\n\n---\n\n### Phase 3 — Plan Sections & Save outline.json\n\nPlan the website sections. Standard structure for academic papers (adapt as needed):\n\n| `section_id` | Purpose |\n|---|---|\n| `hero` | Title, authors, venue badge, link buttons |\n| `abstract` | Full abstract text |\n| `contributions` | 3–5 key contribution cards |\n| `method` | Architecture figure + method explanation |\n| `results` | Quantitative table + qualitative figures |\n| `conclusion` | Brief conclusion |\n| `citation` | BibTeX block |\n\nFor each section that needs an image, identify:\n- Which page it comes from (the local page path from Phase 1)\n- A description of what the visual shows and why it belongs in this section\n\n**Save as `\u003Cout_dir>\u002Foutline.json`** using exactly this schema:\n\n```json\n{\n  \"project_title\": \"Paper Title\",\n  \"lang\": \"English\",\n  \"authors\": [\"Author One\", \"Author Two\"],\n  \"sections_plan\": [\n    {\n      \"section_index\": 1,\n      \"section_id\": \"hero\",\n      \"title\": \"Hero\",\n      \"content\": \"Title, authors, venue, teaser figure description\",\n      \"required_images\": [\n        {\n          \"url\": \"\u003Clocal_page_path_from_phase1>\",\n          \"visual_description\": \"Figure 1: teaser showing input-output examples\",\n          \"usage_reason\": \"Hero section visual to immediately show the paper's output\"\n        }\n      ]\n    }\n  ]\n}\n```\n\nField notes:\n- `lang`: `\"Chinese\"` or `\"English\"` — match the PDF language\n- `required_images`: empty array `[]` if section needs no images\n- `url`: the **local file path** of the source page (from Phase 1 `path` field)\n- For images that need cropping, note the approximate region — exact crop boxes are determined in Phase 4\n\nWrite `outline.json` using the Write tool to `\u003Cout_dir>\u002Foutline.json`.\n\n---\n\n### Phase 4 — Crop Required Images (Grounding + Subagent)\n\n**IMPORTANT: You MUST delegate ALL cropping to a clean subagent using the Agent tool.** By this phase your context is very long (all page images + outline), which degrades visual coordinate accuracy. A fresh subagent with only the target image produces much more precise coordinates.\n\n**IMPORTANT: You MUST use the provided `{SKILL_DIR}\u002Fscripts\u002Fcrop.py` script for ALL image cropping. Do NOT write your own cropping code, do NOT use PIL\u002FPillow directly, do NOT use any other method.**\n\nRead `outline.json`. Collect all crops needed, then launch **one subagent per source page** (or one per crop if pages differ). The subagent uses **grounding-style localization** — it views the image, locates the target element, and outputs a precise bounding box in normalized 0–999 coordinates.\n\nUse the Agent tool like this:\n\n```\nAgent tool call:\n  description: \"Grounding crop page N\"\n  prompt: |\n    You are a visual grounding and cropping assistant. Your task is to precisely\n    locate specified visual elements in a page image and crop them out.\n\n    ## Grounding method\n\n    Use visual grounding to locate each target:\n    1. Read the source image using the Read tool to view it\n    2. Identify the target element described below\n    3. Determine its bounding box as normalized coordinates in the 0–999 range:\n       - 0 = left\u002Ftop edge of the image\n       - 999 = right\u002Fbottom edge of the image\n       - These are thousandths, NOT pixels, NOT percentages (0–100)\n       - Format: [x1, y1, x2, y2] where (x1,y1) is top-left, (x2,y2) is bottom-right\n       - Example: [0, 0, 500, 500] = top-left quarter of the image\n    4. Be precise: tightly bound the target element with a small margin (~10–20 units)\n       around it. Do NOT crop too wide or too narrow.\n\n    ## Source image\n    \u003Cpage_image_path>\n\n    ## Crops needed\n\n    For each crop below, first do grounding (locate the element), then crop:\n\n    1. Name: \"\u003Cdescriptive_name>\"\n       Target: \"\u003Cvisual_description from outline.json>\"\n       Context: \"\u003Cusage_reason from outline.json>\"\n\n    ## Crop command\n\n    After determining the bounding box [X1, Y1, X2, Y2] for each target, run:\n    ```bash\n    python \u003CSKILL_DIR>\u002Fscripts\u002Fcrop.py \\\n        --path \"\u003Cpage_image_path>\" \\\n        --box X1 Y1 X2 Y2 \\\n        --name \"\u003Ccrop_name>\" \\\n        --out-dir \"\u003Cout_dir>\u002Fcrops\"\n    ```\n\n    ## Verification\n\n    After each crop, READ the output image to visually verify the correct region\n    was captured. If the crop missed the target or is too wide\u002Fnarrow, adjust the\n    coordinates and re-run crop.py.\n\n    ## Output\n\n    Report the final results as a list:\n    - crop_name: \u003Cname>, file: \u003Coutput_filename>, box: [X1, Y1, X2, Y2]\n```\n\nReplace `\u003Cpage_image_path>`, `\u003CSKILL_DIR>`, `\u003Cout_dir>`, and crop details with actual values from your context.\n\nThe crop.py script outputs JSON: `{\"path\": \"\u002Fabs\u002Fpath\u002F\u003Cname>_crop.png\"}`\n\nCollect results from all subagents and build the mapping: `section_id → [crop filename, ...]` to reference in HTML.\n\n**Launch subagents for independent pages in parallel** when possible. Wait for all to complete before proceeding.\n\n---\n\n### Phase 5 — Measure Cropped Image Dimensions\n\n```bash\npython3 -c \"\nfrom PIL import Image; import os, json\nd = '\u003Cout_dir>\u002Fcrops'\nsizes = {}\nfor f in sorted(os.listdir(d)):\n    if f.endswith('.png'):\n        w, h = Image.open(os.path.join(d, f)).size\n        sizes[f] = {'width': w, 'height': h, 'aspect': round(w\u002Fh, 2)}\nprint(json.dumps(sizes, indent=2))\n\"\n```\n\n| Aspect ratio | Layout recommendation |\n|---|---|\n| **\u003C 0.7** (tall\u002Fnarrow) | `max-width: 400–500px`, centered |\n| **0.7 – 1.3** (square-ish) | `max-width: 600–700px` |\n| **> 1.3** (wide) | Full-width, `max-width: 100%` |\n| **> 2.0** (very wide, e.g. tables) | Full-width with horizontal scroll fallback |\n\n---\n\n### Phase 6 — Generate the Single-Page HTML\n\n**Step A — Write HTML** to `\u002Ftmp\u002Fwebsite.html`\n\n- All `\u003Cimg src=\"...\">` must use **relative paths**: `crops\u002F\u003Cname>_crop.png`\n- Do NOT use absolute paths\n\n**Step B — Save:**\n```bash\npython {SKILL_DIR}\u002Fscripts\u002Fgenerate_web.py \\\n    --html-file \u002Ftmp\u002Fwebsite.html \\\n    --title \"\u003Cpaper title>\" \\\n    --out-dir \"\u003Cout_dir>\u002F\"\n```\n\n---\n\n## HTML Spec\n\nA **single self-contained HTML file** — embedded CSS, minimal vanilla JS only. No external JS frameworks. Google Fonts CDN is fine.\n\n**Page layout:**\n- Max content width: `900px`, centered, comfortable side padding\n- Sticky top nav with section anchor links + smooth scroll\n- Looks good at 1200px wide; readable at 768px\n\n**Typography:**\n- Two Google Fonts: one for headings, one for body\u002FUI\n- Body: 17–18px, line-height 1.7\n- Strong heading hierarchy (h1 >> h2 >> h3)\n\n**Visual style:**\n- If the user specifies a style, follow it exactly\n- Otherwise, infer an appropriate aesthetic from the paper's domain and tone (e.g. CV\u002FML paper → clean modern academic; systems paper → dark technical; humanities → warm editorial serif)\n- Define colors and fonts as CSS variables; no fixed palette or font choices are required\n\n**Section guidelines:**\n\n`hero`:\n- Large title (2–3rem), authors list with affiliation superscripts, venue badge pill\n- Link buttons: `[📄 Paper] [💻 Code] [🗄️ Dataset]` — grey out if no URL\n- Teaser figure below (if found)\n\n`abstract`:\n- Verbatim text with subtle left border accent\n\n`contributions`:\n- Cards in a 2–3 column CSS grid, each with Unicode symbol + heading + description\n\n`method`:\n- Full-width architecture figure (`\u003Cfigure>\u003Cimg>\u003Cfigcaption>`) + prose explanation\n\n`results`:\n- **Quantitative table** as real `\u003Ctable>` — use actual numbers from the PDF, best numbers **bolded**\n- **Qualitative figures** in a grid (2–4 images with captions)\n\n`conclusion`:\n- 2–3 paragraphs\n\n`citation`:\n- `\u003Cpre>\u003Ccode>` BibTeX block reconstructed from PDF metadata\n- \"Copy\" button using `navigator.clipboard` vanilla JS\n\n**Images:**\n- All `\u003Cimg>` use relative paths: `crops\u002F\u003Cname>_crop.png`\n- Add `loading=\"lazy\"` and descriptive `alt`\n- Wrap in `\u003Cfigure>` with `\u003Cfigcaption>`\n\n**Animations (subtle only):**\n- Fade-in on scroll via `IntersectionObserver` + CSS transitions\n- Hover states on buttons\u002Fcards\n\n---\n\n---\n\n## Quality Checklist\n\n- [ ] Output directory named `\u003Cpdf_stem>_\u003Ctimestamp>\u002F`\n- [ ] `outline.json` saved with valid WebPlan schema\n- [ ] All crops saved to `crops\u002F` (local only)\n- [ ] All metadata (title, authors, venue, year) from the PDF\n- [ ] Abstract is verbatim\n- [ ] Quantitative table has real numbers from the paper\n- [ ] All crop images referenced via `crops\u002F\u003Cname>_crop.png`\n- [ ] BibTeX block accurate and copyable\n- [ ] Nav anchors scroll to correct sections\n- [ ] `generate_web.py` called and confirmed success\n\n---\n\n## Language\n\nMatch the PDF language. English paper → English website. Chinese paper → Chinese. No mixing.\n","# PDF → Academic Project Website Skill\n\nConvert a research paper or technical document PDF into a polished single-page project website — the kind used for NeurIPS\u002FCVPR\u002FICLR paper releases. Pages are converted locally at DPI 120, a structured `outline.json` is saved, images are cropped locally, and the final page is saved with `generate_web.py`.\n\n**Scripts are in:** `{SKILL_DIR}\u002Fscripts\u002F`\n\n## Dependencies\n\nPython packages (install once):\n```bash\npip install pymupdf pillow\n```\n\nSystem tools: `curl` (pre-installed on macOS\u002FLinux).\n\n## When to Use\n\nTrigger when the user asks to create a webpage or project page from a PDF — phrases like:\n\"make a project page from a PDF\", \"create a paper website\", \"build an academic website for this paper\", \"论文主页\", \"做项目主页\", \"根据pdf做网页\", \"把论文做成主页\", or any similar intent in Chinese or English.\n\n## Output Directory Convention\n\nAll output goes under `{WORKSPACE}\u002Fweb\u002F\u003Cpdf_stem>_\u003Ctimestamp>\u002F`:\n\n```\nweb\u002F\n└── \u003Cpdf_stem>_\u003Ctimestamp>\u002F\n    ├── outline.json        ← structured web plan (WebPlan schema)\n    ├── crops\u002F              ← locally-saved cropped images\n    │   ├── fig_arch_crop.png\n    │   ├── table_results_crop.png\n    │   └── ...\n    └── index.html          ← the website\n```\n\n- `\u003Cpdf_stem>` = PDF filename without extension\n- `\u003Ctimestamp>` = format `YYYYMMDD_HHMMSS`\n- HTML references images via relative path `crops\u002F\u003Cname>_crop.png`\n\n## Input\n\n`$ARGUMENTS` is the path to the PDF file (local) or an HTTP\u002FHTTPS URL.\n\n- If user provides a **URL**: download with curl first, then convert\n- If user provides a **local PDF path**: convert directly\n\n---\n\n## Workflow\n\n### Phase 0 — Create Output Directory\n\n```python\nimport os, datetime\npdf_stem = os.path.splitext(os.path.basename(pdf_path))[0]\ntimestamp = datetime.datetime.now().strftime(\"%Y%m%d_%H%M%S\")\nout_dir = os.path.join(workspace, \"web\", f\"{pdf_stem}_{timestamp}\")\n```\n\n```bash\nmkdir -p \"\u003Cout_dir>\u002Fcrops\"\n```\n\n---\n\n### Phase 1 — Convert PDF Pages to Images (DPI 120)\n\nIf the input is a URL, download it first:\n```bash\npdf_stem=$(basename \"$ARGUMENTS\" .pdf)\ncurl -L -o \"\u002Ftmp\u002F${pdf_stem}.pdf\" \"$ARGUMENTS\"\n```\nThen convert (pass either the downloaded path or the original local path):\n```bash\npython {SKILL_DIR}\u002Fscripts\u002Fpdf_to_images.py \"\u003Cpdf_path>\" --dpi 120\n```\n\nOutputs JSON to stdout:\n```json\n[{\"page\": 1, \"path\": \"\u002Fabs\u002Fpath\u002Fpage_001.png\"}, ...]\n```\n\nParse and store the full `page → path` map.\n\n---\n\n### Phase 2 — Read All Pages in Order\n\nView **all page images** sequentially before planning. Goal: pure understanding of the document's content, figures, and structure.\n\nWhile reading, note:\n- Title, authors, affiliations, venue, year\n- Abstract text (verbatim)\n- Key contributions\n- Paper\u002FCode\u002FDataset links (arXiv, GitHub, etc.)\n- Figures, tables, diagrams — which pages, rough regions\n- Teaser\u002Fhero figure if present\n\nDo NOT plan sections yet — read everything first.\n\n---\n\n### Phase 3 — Plan Sections & Save outline.json\n\nPlan the website sections. Standard structure for academic papers (adapt as needed):\n\n| `section_id` | Purpose |\n|---|---|\n| `hero` | Title, authors, venue badge, link buttons |\n| `abstract` | Full abstract text |\n| `contributions` | 3–5 key contribution cards |\n| `method` | Architecture figure + method explanation |\n| `results` | Quantitative table + qualitative figures |\n| `conclusion` | Brief conclusion |\n| `citation` | BibTeX block |\n\nFor each section that needs an image, identify:\n- Which page it comes from (the local page path from Phase 1)\n- A description of what the visual shows and why it belongs in this section\n\n**Save as `\u003Cout_dir>\u002Foutline.json`** using exactly this schema:\n\n```json\n{\n  \"project_title\": \"Paper Title\",\n  \"lang\": \"English\",\n  \"authors\": [\"Author One\", \"Author Two\"],\n  \"sections_plan\": [\n    {\n      \"section_index\": 1,\n      \"section_id\": \"hero\",\n      \"title\": \"Hero\",\n      \"content\": \"Title, authors, venue, teaser figure description\",\n      \"required_images\": [\n        {\n          \"url\": \"\u003Clocal_page_path_from_phase1>\",\n          \"visual_description\": \"Figure 1: teaser showing input-output examples\",\n          \"usage_reason\": \"Hero section visual to immediately show the paper's output\"\n        }\n      ]\n    }\n  ]\n}\n```\n\nField notes:\n- `lang`: `\"Chinese\"` or `\"English\"` — match the PDF language\n- `required_images`: empty array `[]` if section needs no images\n- `url`: the **local file path** of the source page (from Phase 1 `path` field)\n- For images that need cropping, note the approximate region — exact crop boxes are determined in Phase 4\n\nWrite `outline.json` using the Write tool to `\u003Cout_dir>\u002Foutline.json`.\n\n---\n\n### Phase 4 — Crop Required Images (Grounding + Subagent)\n\n**IMPORTANT: You MUST delegate ALL cropping to a clean subagent using the Agent tool.** By this phase your context is very long (all page images + outline), which degrades visual coordinate accuracy. A fresh subagent with only the target image produces much more precise coordinates.\n\n**IMPORTANT: You MUST use the provided `{SKILL_DIR}\u002Fscripts\u002Fcrop.py` script for ALL image cropping. Do NOT write your own cropping code, do NOT use PIL\u002FPillow directly, do NOT use any other method.**\n\nRead `outline.json`. Collect all crops needed, then launch **one subagent per source page** (or one per crop if pages differ). The subagent uses **grounding-style localization** — it views the image, locates the target element, and outputs a precise bounding box in normalized 0–999 coordinates.\n\nUse the Agent tool like this:\n\n```\nAgent tool call:\n  description: \"Grounding crop page N\"\n  prompt: |\n    You are a visual grounding and cropping assistant. Your task is to precisely\n    locate specified visual elements in a page image and crop them out.\n\n    ## Grounding method\n\n    Use visual grounding to locate each target:\n    1. Read the source image using the Read tool to view it\n    2. Identify the target element described below\n    3. Determine its bounding box as normalized coordinates in the 0–999 range:\n       - 0 = left\u002Ftop edge of the image\n       - 999 = right\u002Fbottom edge of the image\n       - These are thousandths, NOT pixels, NOT percentages (0–100)\n       - Format: [x1, y1, x2, y2] where (x1,y1) is top-left, (x2,y2) is bottom-right\n       - Example: [0, 0, 500, 500] = top-left quarter of the image\n    4. Be precise: tightly bound the target element with a small margin (~10–20 units)\n       around it. Do NOT crop too wide or too narrow.\n\n    ## Source image\n    \u003Cpage_image_path>\n\n    ## Crops needed\n\n    For each crop below, first do grounding (locate the element), then crop:\n\n    1. Name: \"\u003Cdescriptive_name>\"\n       Target: \"\u003Cvisual_description from outline.json>\"\n       Context: \"\u003Cusage_reason from outline.json>\"\n\n    ## Crop command\n\n    After determining the bounding box [X1, Y1, X2, Y2] for each target, run:\n    ```bash\n    python \u003CSKILL_DIR>\u002Fscripts\u002Fcrop.py \\\n        --path \"\u003Cpage_image_path>\" \\\n        --box X1 Y1 X2 Y2 \\\n        --name \"\u003Ccrop_name>\" \\\n        --out-dir \"\u003Cout_dir>\u002Fcrops\"\n    ```\n\n    ## Verification\n\n    After each crop, READ the output image to visually verify the correct region\n    was captured. If the crop missed the target or is too wide\u002Fnarrow, adjust the\n    coordinates and re-run crop.py.\n\n    ## Output\n\n    Report the final results as a list:\n    - crop_name: \u003Cname>, file: \u003Coutput_filename>, box: [X1, Y1, X2, Y2]\n```\n\nReplace `\u003Cpage_image_path>`, `\u003CSKILL_DIR>`, `\u003Cout_dir>`, and crop details with actual values from your context.\n\nThe crop.py script outputs JSON: `{\"path\": \"\u002Fabs\u002Fpath\u002F\u003Cname>_crop.png\"}`\n\nCollect results from all subagents and build the mapping: `section_id → [crop filename, ...]` to reference in HTML.\n\n**Launch subagents for independent pages in parallel** when possible. Wait for all to complete before proceeding.\n\n---\n\n### Phase 5 — Measure Cropped Image Dimensions\n\n```bash\npython3 -c \"\nfrom PIL import Image; import os, json\nd = '\u003Cout_dir>\u002Fcrops'\nsizes = {}\nfor f in sorted(os.listdir(d)):\n    if f.endswith('.png'):\n        w, h = Image.open(os.path.join(d, f)).size\n        sizes[f] = {'width': w, 'height': h, 'aspect': round(w\u002Fh, 2)}\nprint(json.dumps(sizes, indent=2))\n\"\n```\n\n| Aspect ratio | Layout recommendation |\n|---|---|\n| **\u003C 0.7** (tall\u002Fnarrow) | `max-width: 400–500px`, centered |\n| **0.7 – 1.3** (square-ish) | `max-width: 600–700px` |\n| **> 1.3** (wide) | Full-width, `max-width: 100%` |\n| **> 2.0** (very wide, e.g. tables) | Full-width with horizontal scroll fallback |\n\n---\n\n### Phase 6 — Generate the Single-Page HTML\n\n**Step A — Write HTML** to `\u002Ftmp\u002Fwebsite.html`\n\n- All `\u003Cimg src=\"...\">` must use **relative paths**: `crops\u002F\u003Cname>_crop.png`\n- Do NOT use absolute paths\n\n**Step B — Save:**\n```bash\npython {SKILL_DIR}\u002Fscripts\u002Fgenerate_web.py \\\n    --html-file \u002Ftmp\u002Fwebsite.html \\\n    --title \"\u003Cpaper title>\" \\\n    --out-dir \"\u003Cout_dir>\u002F\"\n```\n\n---\n\n## HTML Spec\n\nA **single self-contained HTML file** — embedded CSS, minimal vanilla JS only. No external JS frameworks. Google Fonts CDN is fine.\n\n**Page layout:**\n- Max content width: `900px`, centered, comfortable side padding\n- Sticky top nav with section anchor links + smooth scroll\n- Looks good at 1200px wide; readable at 768px\n\n**Typography:**\n- Two Google Fonts: one for headings, one for body\u002FUI\n- Body: 17–18px, line-height 1.7\n- Strong heading hierarchy (h1 >> h2 >> h3)\n\n**Visual style:**\n- If the user specifies a style, follow it exactly\n- Otherwise, infer an appropriate aesthetic from the paper's domain and tone (e.g. CV\u002FML paper → clean modern academic; systems paper → dark technical; humanities → warm editorial serif)\n- Define colors and fonts as CSS variables; no fixed palette or font choices are required\n\n**Section guidelines:**\n\n`hero`:\n- Large title (2–3rem), authors list with affiliation superscripts, venue badge pill\n- Link buttons: `[📄 Paper] [💻 Code] [🗄️ Dataset]` — grey out if no URL\n- Teaser figure below (if found)\n\n`abstract`:\n- Verbatim text with subtle left border accent\n\n`contributions`:\n- Cards in a 2–3 column CSS grid, each with Unicode symbol + heading + description\n\n`method`:\n- Full-width architecture figure (`\u003Cfigure>\u003Cimg>\u003Cfigcaption>`) + prose explanation\n\n`results`:\n- **Quantitative table** as real `\u003Ctable>` — use actual numbers from the PDF, best numbers **bolded**\n- **Qualitative figures** in a grid (2–4 images with captions)\n\n`conclusion`:\n- 2–3 paragraphs\n\n`citation`:\n- `\u003Cpre>\u003Ccode>` BibTeX block reconstructed from PDF metadata\n- \"Copy\" button using `navigator.clipboard` vanilla JS\n\n**Images:**\n- All `\u003Cimg>` use relative paths: `crops\u002F\u003Cname>_crop.png`\n- Add `loading=\"lazy\"` and descriptive `alt`\n- Wrap in `\u003Cfigure>` with `\u003Cfigcaption>`\n\n**Animations (subtle only):**\n- Fade-in on scroll via `IntersectionObserver` + CSS transitions\n- Hover states on buttons\u002Fcards\n\n---\n\n---\n\n## Quality Checklist\n\n- [ ] Output directory named `\u003Cpdf_stem>_\u003Ctimestamp>\u002F`\n- [ ] `outline.json` saved with valid WebPlan schema\n- [ ] All crops saved to `crops\u002F` (local only)\n- [ ] All metadata (title, authors, venue, year) from the PDF\n- [ ] Abstract is verbatim\n- [ ] Quantitative table has real numbers from the paper\n- [ ] All crop images referenced via `crops\u002F\u003Cname>_crop.png`\n- [ ] BibTeX block accurate and copyable\n- [ ] Nav anchors scroll to correct sections\n- [ ] `generate_web.py` called and confirmed success\n\n---\n\n## Language\n\nMatch the PDF language. English paper → English website. Chinese paper → Chinese. No mixing.\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"emoji":26,"homepage":27,"requires":28},"🌐","https:\u002F\u002Fgithub.com\u002Fzai-org\u002FGLM-V\u002Ftree\u002Fmain\u002Fskills\u002Fglmv-pdf-to-web",{"bins":29},[30],"python","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills-v4\u002Fglmv-pdf-to-web",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill glmv-pdf-to-web",{"tool":46,"command":47},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill glmv-pdf-to-web",{"tool":49,"command":50},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill glmv-pdf-to-web","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills-v4\u002Fglmv-pdf-to-web\u002FSKILL.md",true,[54,60,64],{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Fcrop.py","SCRIPT","脚本",2630,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills-v4\u002Fglmv-pdf-to-web\u002Fscripts\u002Fcrop.py",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Fgenerate_web.py",1089,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills-v4\u002Fglmv-pdf-to-web\u002Fscripts\u002Fgenerate_web.py",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Fpdf_to_images.py",2185,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-skills-v4\u002Fglmv-pdf-to-web\u002Fscripts\u002Fpdf_to_images.py",[69,76,83,90,97,104],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]