[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73HTX67KG3WG6MT7KK5CYFJ":3,"skill-same:01M73HTX67KG3WG6MT7KK5CYFJ":53},{"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":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M73HTX67KG3WG6MT7KK5CYFJ","poster-presentation",null,"Create scientific conference posters as native, editable .pptx files using python-pptx. Handles A0\u002FA1 layouts, section placement, figure insertion, and academic color schemes. Exports editable .pptx and PDF. Use when the user wants a directly editable PowerPoint poster; for HTML\u002FCSS-based posters exported to PDF\u002FPPTX use pptx-posters, and for standard LaTeX posters use latex-posters.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fposter-presentation\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: poster-presentation\ndescription: Create scientific conference posters as native, editable .pptx files using python-pptx. Handles A0\u002FA1 layouts, section placement, figure insertion, and academic color schemes. Exports editable .pptx and PDF. Use when the user wants a directly editable PowerPoint poster; for HTML\u002FCSS-based posters exported to PDF\u002FPPTX use pptx-posters, and for standard LaTeX posters use latex-posters.\nallowed-tools: Read Write Bash\nversion: \"1.0.0\"\nlicense: MIT license\nmetadata:\n    skill-author: K-Dense Inc.\n---\n\n# Scientific Conference Poster — PowerPoint (.pptx)\n\n## Overview\n\nThis skill creates professional scientific conference posters as editable PowerPoint (.pptx) files using `python-pptx`. It supports standard conference poster sizes (A0, A1), landscape and portrait orientations, structured academic sections, figure insertion with captions, and publication-quality academic color schemes.\n\nThe generated `.pptx` is fully editable, allowing researchers to fine-tune layout, fonts, and colors using Microsoft PowerPoint, LibreOffice Impress, or any compatible application. PDF export is available via LibreOffice or PowerPoint.\n\n---\n\n## When to Use This Skill\n\nUse this skill when:\n- Creating a poster for an academic conference, symposium, or workshop\n- Converting a research paper or manuscript into poster format\n- Building a poster template for a research group or institution\n- Presenting preliminary results, thesis work, or funded project outcomes\n- Needing an editable (non-PDF) poster that collaborators can update\n\n**Trigger phrases:**\n- \"Create a conference poster as a PowerPoint \u002F .pptx\"\n- \"Make me a scientific poster I can edit in PowerPoint\"\n- \"Generate a poster for my paper \u002F conference \u002F symposium\"\n- \"Build an A0 \u002F A1 poster for [conference name]\"\n- \"Create a research poster with sections for methods, results, conclusions\"\n\n---\n\n## Prerequisites\n\nInstall required Python packages before running any poster generation code:\n\n```bash\npip install python-pptx Pillow\n```\n\nFor PDF export from the command line:\n\n```bash\n# macOS (via Homebrew)\nbrew install --cask libreoffice\n\n# Ubuntu \u002F Debian\nsudo apt-get install libreoffice\n\n# Windows — download from https:\u002F\u002Fwww.libreoffice.org\u002F\n```\n\n---\n\n## Standard Poster Dimensions\n\n| Format   | Orientation | Width (cm) | Height (cm) | Width (in) | Height (in) | Common use          |\n|----------|-------------|------------|-------------|------------|-------------|---------------------|\n| A0       | Portrait    | 84.1       | 118.9       | 33.11      | 46.81       | European conferences|\n| A0       | Landscape   | 118.9      | 84.1        | 46.81      | 33.11       | US \u002F mixed format   |\n| A1       | Portrait    | 59.4       | 84.1        | 23.39      | 33.11       | Smaller venues      |\n| A1       | Landscape   | 84.1       | 59.4        | 33.11      | 23.39       | Departmental events |\n| 36×48 in | Portrait    | 91.44      | 121.92      | 36.0       | 48.0        | US conferences      |\n| 48×36 in | Landscape   | 121.92     | 91.44       | 48.0       | 36.0        | US conferences      |\n\n**python-pptx uses EMUs (English Metric Units): 1 inch = 914400 EMU, 1 cm = 360000 EMU**\n\n---\n\n## Workflow Phases\n\n### Phase 1: Gather Content\n\nCollect all poster content from the user or source document:\n\n1. **Title** — full paper\u002Fposter title\n2. **Authors** — list with superscript affiliation numbers\n3. **Affiliations** — institution names linked to authors\n4. **Contact \u002F corresponding author** email\n5. **Abstract** — 150–250 words\n6. **Introduction \u002F Background** — key context and motivation (3–5 bullet points or short paragraphs)\n7. **Methods** — concise description with optional workflow figure\n8. **Results** — key findings, data visualizations, tables\n9. **Conclusions** — 4–6 bullet points\n10. **Acknowledgements** — funding sources, collaborators\n11. **References** — 5–10 key references (abbreviated format)\n12. **Figures** — file paths to images\u002Fplots to embed\n13. **Logo(s)** — institutional\u002Fconference logo paths\n14. **Color scheme** — preferred colors or institution palette (see schemes below)\n\n### Phase 2: Plan Layout\n\nStandard two- or three-column academic poster layout:\n\n```\n┌──────────────────────────────────────────────────────────┐\n│  LOGO  │           TITLE \u002F AUTHORS \u002F AFFILIATIONS         │  LOGO │\n├─────────────────┬────────────────┬────────────────────────┤\n│  Introduction   │   Methods      │   Results              │\n│                 │                │                        │\n│  Background     │   Workflow     │   Figure 1             │\n│                 │   Figure       │                        │\n├─────────────────┴────────────────┤   Figure 2             │\n│  [Optional middle spanning row]  │                        │\n├─────────────────┬────────────────┼────────────────────────┤\n│  Conclusions    │ Acknowledgements│  References            │\n└─────────────────┴────────────────┴────────────────────────┘\n```\n\n### Phase 3: Generate .pptx\n\nUse the code templates below to build the poster programmatically.\n\n### Phase 4: Export\n\n- Save as `.pptx` (primary deliverable — fully editable)\n- Export to PDF via LibreOffice or PowerPoint (see export section)\n- Verify layout at 100% zoom before delivering\n\n---\n\n## Core Code: Poster Foundation\n\n```python\n\"\"\"\nscientific_poster.py — Generate A0 landscape conference poster as .pptx\nRequires: python-pptx, Pillow\n\"\"\"\n\nfrom pptx import Presentation\nfrom pptx.util import Inches, Pt, Emu, Cm\nfrom pptx.dml.color import RGBColor\nfrom pptx.enum.text import PP_ALIGN\nfrom pptx.util import Inches, Pt\nimport os\n\n\n# ── Dimensions ────────────────────────────────────────────────────────────────\n# A0 Landscape: 118.9 cm × 84.1 cm\nPOSTER_WIDTH_CM  = 118.9\nPOSTER_HEIGHT_CM = 84.1\n\ndef cm(value):\n    \"\"\"Convert centimetres to EMUs.\"\"\"\n    return Cm(value)\n\n\ndef create_poster(output_path: str = \"poster.pptx\") -> Presentation:\n    \"\"\"Create and return a blank poster Presentation at A0 landscape size.\"\"\"\n    prs = Presentation()\n    prs.slide_width  = cm(POSTER_WIDTH_CM)\n    prs.slide_height = cm(POSTER_HEIGHT_CM)\n\n    # Remove all default placeholder layouts — use blank slide\n    slide_layout = prs.slide_layouts[6]  # index 6 = blank\n    slide = prs.slides.add_slide(slide_layout)\n\n    return prs, slide\n```\n\n---\n\n## Academic Color Schemes\n\n```python\n# ── Color Palettes ────────────────────────────────────────────────────────────\n\nSCHEMES = {\n    \"classic_blue\": {\n        \"header_bg\":    RGBColor(0x1A, 0x3A, 0x5C),   # dark navy\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),   # white\n        \"section_bg\":   RGBColor(0xD6, 0xE4, 0xF0),   # light blue\n        \"section_header\": RGBColor(0x1A, 0x3A, 0x5C),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0xE8, 0x8A, 0x00),   # amber\n        \"background\":   RGBColor(0xF5, 0xF7, 0xFA),\n    },\n    \"green_academic\": {\n        \"header_bg\":    RGBColor(0x1B, 0x4B, 0x36),   # forest green\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),\n        \"section_bg\":   RGBColor(0xD8, 0xED, 0xE3),   # light green\n        \"section_header\": RGBColor(0x1B, 0x4B, 0x36),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0xC0, 0x39, 0x2B),   # red\n        \"background\":   RGBColor(0xF4, 0xF9, 0xF6),\n    },\n    \"crimson_grey\": {\n        \"header_bg\":    RGBColor(0x8B, 0x00, 0x00),   # crimson\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),\n        \"section_bg\":   RGBColor(0xF0, 0xE8, 0xE8),   # blush\n        \"section_header\": RGBColor(0x8B, 0x00, 0x00),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0x2C, 0x3E, 0x50),   # slate\n        \"background\":   RGBColor(0xFA, 0xF9, 0xF9),\n    },\n    \"purple_modern\": {\n        \"header_bg\":    RGBColor(0x4A, 0x14, 0x8C),   # deep purple\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),\n        \"section_bg\":   RGBColor(0xED, 0xE7, 0xF6),   # lavender\n        \"section_header\": RGBColor(0x4A, 0x14, 0x8C),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0xF5, 0x7C, 0x00),   # orange\n        \"background\":   RGBColor(0xFA, 0xF8, 0xFF),\n    },\n    \"monochrome\": {\n        \"header_bg\":    RGBColor(0x21, 0x21, 0x21),\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),\n        \"section_bg\":   RGBColor(0xEE, 0xEE, 0xEE),\n        \"section_header\": RGBColor(0x21, 0x21, 0x21),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0x75, 0x75, 0x75),\n        \"background\":   RGBColor(0xFF, 0xFF, 0xFF),\n    },\n}\n\nDEFAULT_SCHEME = \"classic_blue\"\n```\n\n---\n\n## Helper Functions\n\n```python\n# ── Drawing helpers ────────────────────────────────────────────────────────────\n\nfrom pptx.oxml.ns import qn\nfrom lxml import etree\n\n\ndef set_background_color(slide, color: RGBColor):\n    \"\"\"Fill the slide background with a solid color.\"\"\"\n    background = slide.background\n    fill = background.fill\n    fill.solid()\n    fill.fore_color.rgb = color\n\n\ndef add_filled_rectangle(slide, left, top, width, height,\n                          fill_color: RGBColor, line_color=None, line_width_pt=0):\n    \"\"\"Add a solid filled rectangle shape (used for section boxes and header).\"\"\"\n    shape = slide.shapes.add_shape(\n        1,  # MSO_SHAPE_TYPE.RECTANGLE\n        left, top, width, height\n    )\n    shape.fill.solid()\n    shape.fill.fore_color.rgb = fill_color\n\n    if line_color:\n        shape.line.color.rgb = line_color\n        shape.line.width = Pt(line_width_pt)\n    else:\n        shape.line.fill.background()  # no border\n\n    return shape\n\n\ndef add_textbox(slide, left, top, width, height, text: str,\n                font_size: int, font_color: RGBColor,\n                bold=False, italic=False, alignment=PP_ALIGN.LEFT,\n                word_wrap=True, font_name=\"Calibri\"):\n    \"\"\"Add a text box with specified formatting.\"\"\"\n    txBox = slide.shapes.add_textbox(left, top, width, height)\n    tf = txBox.text_frame\n    tf.word_wrap = word_wrap\n\n    p = tf.paragraphs[0]\n    p.alignment = alignment\n    run = p.add_run()\n    run.text = text\n\n    font = run.font\n    font.name = font_name\n    font.size = Pt(font_size)\n    font.color.rgb = font_color\n    font.bold = bold\n    font.italic = italic\n\n    return txBox\n\n\ndef add_multiline_textbox(slide, left, top, width, height, lines: list,\n                           font_size: int, font_color: RGBColor,\n                           bold_first=False, font_name=\"Calibri\",\n                           bullet=False, line_spacing_pt=None):\n    \"\"\"\n    Add a text box with multiple paragraphs (one per item in `lines`).\n    If bullet=True, prepends '• ' to each line.\n    \"\"\"\n    txBox = slide.shapes.add_textbox(left, top, width, height)\n    tf = txBox.text_frame\n    tf.word_wrap = True\n\n    for i, line in enumerate(lines):\n        if i == 0:\n            p = tf.paragraphs[0]\n        else:\n            p = tf.add_paragraph()\n\n        p.alignment = PP_ALIGN.LEFT\n        run = p.add_run()\n        prefix = \"• \" if bullet else \"\"\n        run.text = prefix + line\n\n        font = run.font\n        font.name = font_name\n        font.size = Pt(font_size)\n        font.color.rgb = font_color\n        font.bold = (bold_first and i == 0)\n\n        if line_spacing_pt:\n            from pptx.util import Pt as pPt\n            from pptx.oxml.ns import qn\n            pPr = p._pPr\n            if pPr is None:\n                pPr = p._p.get_or_add_pPr()\n            lnSpc = etree.SubElement(pPr, qn(\"a:lnSpc\"))\n            spcPts = etree.SubElement(lnSpc, qn(\"a:spcPts\"))\n            spcPts.set(\"val\", str(int(line_spacing_pt * 100)))\n\n    return txBox\n\n\ndef add_image(slide, image_path: str, left, top, width, height=None):\n    \"\"\"\n    Insert an image at the specified position.\n    If height is None, python-pptx preserves the aspect ratio.\n    \"\"\"\n    if not os.path.exists(image_path):\n        print(f\"[WARNING] Image not found: {image_path} — skipping.\")\n        return None\n\n    if height is None:\n        pic = slide.shapes.add_picture(image_path, left, top, width=width)\n    else:\n        pic = slide.shapes.add_picture(image_path, left, top, width, height)\n\n    return pic\n\n\ndef add_section_header(slide, left, top, width, height,\n                        title: str, scheme: dict, font_size=24):\n    \"\"\"Draw a colored section header bar with white text.\"\"\"\n    add_filled_rectangle(slide, left, top, width, height,\n                         fill_color=scheme[\"section_header\"])\n    add_textbox(slide, left + Cm(0.3), top, width - Cm(0.3), height,\n                text=title,\n                font_size=font_size,\n                font_color=scheme[\"header_text\"],\n                bold=True,\n                alignment=PP_ALIGN.LEFT)\n```\n\n---\n\n## Poster Header Section\n\n```python\ndef build_header(slide, scheme: dict,\n                 title: str,\n                 authors: str,\n                 affiliations: str,\n                 logo_left_path: str = None,\n                 logo_right_path: str = None,\n                 poster_width_cm: float = POSTER_WIDTH_CM):\n    \"\"\"\n    Build the full-width header: logos on left\u002Fright, title\u002Fauthors\u002Faffiliations centre.\n    Header height = ~15% of poster height.\n    \"\"\"\n    HEADER_HEIGHT = cm(12)\n    LOGO_WIDTH    = cm(12)\n    PADDING       = cm(1)\n\n    # Background bar\n    add_filled_rectangle(slide,\n                         left=cm(0), top=cm(0),\n                         width=cm(poster_width_cm), height=HEADER_HEIGHT,\n                         fill_color=scheme[\"header_bg\"])\n\n    # Left logo\n    if logo_left_path and os.path.exists(logo_left_path):\n        add_image(slide, logo_left_path,\n                  left=PADDING, top=cm(1),\n                  width=LOGO_WIDTH, height=cm(10))\n\n    # Right logo\n    if logo_right_path and os.path.exists(logo_right_path):\n        add_image(slide, logo_right_path,\n                  left=cm(poster_width_cm) - LOGO_WIDTH - PADDING,\n                  top=cm(1),\n                  width=LOGO_WIDTH, height=cm(10))\n\n    # Title — centered\n    text_left  = LOGO_WIDTH + PADDING * 2\n    text_width = cm(poster_width_cm) - (LOGO_WIDTH + PADDING) * 2\n\n    add_textbox(slide,\n                left=text_left, top=cm(1),\n                width=text_width, height=cm(5),\n                text=title,\n                font_size=52,\n                font_color=scheme[\"header_text\"],\n                bold=True,\n                alignment=PP_ALIGN.CENTER)\n\n    add_textbox(slide,\n                left=text_left, top=cm(6),\n                width=text_width, height=cm(2.5),\n                text=authors,\n                font_size=28,\n                font_color=scheme[\"header_text\"],\n                bold=False,\n                alignment=PP_ALIGN.CENTER)\n\n    add_textbox(slide,\n                left=text_left, top=cm(8.5),\n                width=text_width, height=cm(2),\n                text=affiliations,\n                font_size=22,\n                font_color=scheme[\"header_text\"],\n                italic=True,\n                alignment=PP_ALIGN.CENTER)\n```\n\n---\n\n## Section Building Blocks\n\n```python\ndef build_text_section(slide, left, top, width, height,\n                        section_title: str,\n                        content_lines: list,\n                        scheme: dict,\n                        header_height_cm: float = 2.0,\n                        font_size: int = 20,\n                        bullet: bool = True):\n    \"\"\"\n    Draw a complete section box: colored header + white body with text lines.\n    \"\"\"\n    HDR = cm(header_height_cm)\n\n    # Section background\n    add_filled_rectangle(slide, left, top, width, height,\n                         fill_color=scheme[\"section_bg\"],\n                         line_color=scheme[\"section_header\"],\n                         line_width_pt=1.5)\n\n    # Section header bar\n    add_section_header(slide, left, top, width, HDR,\n                       title=section_title, scheme=scheme)\n\n    # Body text\n    add_multiline_textbox(slide,\n                          left=left + cm(0.5),\n                          top=top + HDR + cm(0.3),\n                          width=width - cm(1),\n                          height=height - HDR - cm(0.5),\n                          lines=content_lines,\n                          font_size=font_size,\n                          font_color=scheme[\"body_text\"],\n                          bullet=bullet)\n\n\ndef build_figure_section(slide, left, top, width, height,\n                          section_title: str,\n                          image_path: str,\n                          caption: str,\n                          scheme: dict,\n                          header_height_cm: float = 2.0,\n                          caption_height_cm: float = 2.5):\n    \"\"\"\n    Draw a section box containing a figure + caption below it.\n    \"\"\"\n    HDR     = cm(header_height_cm)\n    CAPTION = cm(caption_height_cm)\n    PAD     = cm(0.4)\n\n    # Background\n    add_filled_rectangle(slide, left, top, width, height,\n                         fill_color=scheme[\"section_bg\"],\n                         line_color=scheme[\"section_header\"],\n                         line_width_pt=1.5)\n\n    # Header\n    add_section_header(slide, left, top, width, HDR,\n                       title=section_title, scheme=scheme)\n\n    # Image area\n    img_top    = top + HDR + PAD\n    img_height = height - HDR - CAPTION - PAD * 2\n\n    if image_path:\n        add_image(slide, image_path,\n                  left=left + PAD,\n                  top=img_top,\n                  width=width - PAD * 2,\n                  height=img_height)\n    else:\n        # Placeholder grey box when no image provided\n        add_filled_rectangle(slide,\n                             left=left + PAD, top=img_top,\n                             width=width - PAD * 2, height=img_height,\n                             fill_color=RGBColor(0xCC, 0xCC, 0xCC))\n\n    # Caption\n    add_textbox(slide,\n                left=left + PAD,\n                top=top + HDR + PAD + img_height,\n                width=width - PAD * 2,\n                height=CAPTION,\n                text=caption,\n                font_size=18,\n                font_color=scheme[\"body_text\"],\n                italic=True,\n                alignment=PP_ALIGN.CENTER)\n```\n\n---\n\n## Full Poster Assembly — Three-Column A0 Landscape\n\n```python\ndef build_a0_landscape_poster(\n    title: str,\n    authors: str,\n    affiliations: str,\n    abstract_lines: list,\n    intro_lines: list,\n    methods_lines: list,\n    results_lines: list,\n    conclusions_lines: list,\n    acknowledgements: str,\n    references_lines: list,\n    figure1_path: str = None,\n    figure1_caption: str = \"Figure 1.\",\n    figure2_path: str = None,\n    figure2_caption: str = \"Figure 2.\",\n    methods_figure_path: str = None,\n    methods_figure_caption: str = \"Workflow.\",\n    logo_left: str = None,\n    logo_right: str = None,\n    color_scheme: str = \"classic_blue\",\n    output_path: str = \"poster.pptx\"\n):\n    \"\"\"\n    Build a complete three-column A0 landscape scientific poster.\n\n    Layout (all measurements in cm from top-left origin):\n      Header:  full width, 0–12 cm\n      Column 1 (left):   0–38 cm wide,  12–82 cm tall\n      Column 2 (middle): 40–78 cm wide, 12–82 cm tall\n      Column 3 (right):  80–118 cm wide, 12–82 cm tall\n      Footer:  full width, 82–84.1 cm\n    \"\"\"\n    scheme = SCHEMES.get(color_scheme, SCHEMES[DEFAULT_SCHEME])\n    prs, slide = create_poster(output_path)\n\n    # Poster background\n    set_background_color(slide, scheme[\"background\"])\n\n    # ── HEADER ──────────────────────────────────────────────────────────────\n    build_header(slide, scheme,\n                 title=title, authors=authors, affiliations=affiliations,\n                 logo_left_path=logo_left, logo_right_path=logo_right)\n\n    # ── LAYOUT CONSTANTS ────────────────────────────────────────────────────\n    COL_TOP    = cm(12.5)\n    COL_BOTTOM = cm(82)\n    COL_HEIGHT = COL_BOTTOM - COL_TOP\n    GAP        = cm(1.5)\n\n    C1_LEFT  = cm(1)\n    C1_WIDTH = cm(37)\n    C2_LEFT  = C1_LEFT + C1_WIDTH + GAP\n    C2_WIDTH = cm(37)\n    C3_LEFT  = C2_LEFT + C2_WIDTH + GAP\n    C3_WIDTH = cm(POSTER_WIDTH_CM) - C3_LEFT - cm(1)\n\n    # ── COLUMN 1: Abstract + Introduction ───────────────────────────────────\n    ABSTRACT_H = cm(22)\n    build_text_section(slide,\n                       left=C1_LEFT, top=COL_TOP,\n                       width=C1_WIDTH, height=ABSTRACT_H,\n                       section_title=\"Abstract\",\n                       content_lines=abstract_lines,\n                       scheme=scheme, bullet=False, font_size=19)\n\n    INTRO_H = COL_HEIGHT - ABSTRACT_H - GAP\n    build_text_section(slide,\n                       left=C1_LEFT, top=COL_TOP + ABSTRACT_H + GAP,\n                       width=C1_WIDTH, height=INTRO_H,\n                       section_title=\"Introduction & Background\",\n                       content_lines=intro_lines,\n                       scheme=scheme, bullet=True, font_size=20)\n\n    # ── COLUMN 2: Methods + Methods Figure ──────────────────────────────────\n    METHODS_TEXT_H  = cm(28)\n    METHODS_FIG_H   = COL_HEIGHT - METHODS_TEXT_H - GAP\n\n    build_text_section(slide,\n                       left=C2_LEFT, top=COL_TOP,\n                       width=C2_WIDTH, height=METHODS_TEXT_H,\n                       section_title=\"Methods\",\n                       content_lines=methods_lines,\n                       scheme=scheme, bullet=True, font_size=20)\n\n    build_figure_section(slide,\n                          left=C2_LEFT,\n                          top=COL_TOP + METHODS_TEXT_H + GAP,\n                          width=C2_WIDTH, height=METHODS_FIG_H,\n                          section_title=\"Workflow\",\n                          image_path=methods_figure_path,\n                          caption=methods_figure_caption,\n                          scheme=scheme)\n\n    # ── COLUMN 3: Results (2 figures) + Conclusions ─────────────────────────\n    FIG1_H        = cm(26)\n    FIG2_H        = cm(22)\n    CONCLUSIONS_H = COL_HEIGHT - FIG1_H - FIG2_H - GAP * 2\n\n    build_figure_section(slide,\n                          left=C3_LEFT, top=COL_TOP,\n                          width=C3_WIDTH, height=FIG1_H,\n                          section_title=\"Results\",\n                          image_path=figure1_path,\n                          caption=figure1_caption,\n                          scheme=scheme)\n\n    build_figure_section(slide,\n                          left=C3_LEFT, top=COL_TOP + FIG1_H + GAP,\n                          width=C3_WIDTH, height=FIG2_H,\n                          section_title=\"\",\n                          image_path=figure2_path,\n                          caption=figure2_caption,\n                          scheme=scheme)\n\n    build_text_section(slide,\n                       left=C3_LEFT,\n                       top=COL_TOP + FIG1_H + FIG2_H + GAP * 2,\n                       width=C3_WIDTH, height=CONCLUSIONS_H,\n                       section_title=\"Conclusions\",\n                       content_lines=conclusions_lines,\n                       scheme=scheme, bullet=True, font_size=20)\n\n    # ── FOOTER: Acknowledgements + References ───────────────────────────────\n    FOOTER_TOP = cm(82.5)\n    FOOTER_H   = cm(POSTER_HEIGHT_CM) - FOOTER_TOP\n    HALF_W     = (cm(POSTER_WIDTH_CM) - cm(2)) \u002F 2\n\n    build_text_section(slide,\n                       left=cm(1), top=FOOTER_TOP,\n                       width=HALF_W, height=FOOTER_H,\n                       section_title=\"Acknowledgements\",\n                       content_lines=[acknowledgements],\n                       scheme=scheme, bullet=False, font_size=16)\n\n    build_text_section(slide,\n                       left=cm(1) + HALF_W + GAP, top=FOOTER_TOP,\n                       width=HALF_W - GAP, height=FOOTER_H,\n                       section_title=\"References\",\n                       content_lines=references_lines,\n                       scheme=scheme, bullet=False, font_size=15)\n\n    # ── SAVE ────────────────────────────────────────────────────────────────\n    prs.save(output_path)\n    print(f\"[OK] Poster saved: {output_path}\")\n    return output_path\n```\n\n---\n\n## Example Usage\n\n```python\nif __name__ == \"__main__\":\n    build_a0_landscape_poster(\n        title=\"Deep Learning for Early Detection of Alzheimer's Disease\\nUsing Multimodal Neuroimaging\",\n        authors=\"J. Smith¹, A. Patel², R. Müller¹, L. Chen³\",\n        affiliations=\"¹Dept. of Neuroscience, University of Example | ²Brain Imaging Centre, City Hospital | ³ML Lab, Tech Institute\",\n\n        abstract_lines=[\n            \"Alzheimer's disease (AD) affects over 55 million people worldwide. \"\n            \"Early and accurate diagnosis remains a significant clinical challenge. \"\n            \"We present a multimodal deep learning framework integrating structural MRI, \"\n            \"FDG-PET, and cerebrospinal fluid biomarkers to improve early AD detection. \"\n            \"Our model achieves 94.2% accuracy on the ADNI dataset, outperforming \"\n            \"unimodal baselines by 8.3 percentage points. These results suggest \"\n            \"multimodal fusion substantially improves pre-clinical AD diagnosis.\"\n        ],\n\n        intro_lines=[\n            \"Alzheimer's disease is the leading cause of dementia, with costs exceeding $300B\u002Fyear in the US alone.\",\n            \"Current diagnostic methods rely on late-stage symptom presentation, missing the critical early treatment window.\",\n            \"Neuroimaging biomarkers (MRI atrophy, PET hypometabolism) show promise but are typically analysed in isolation.\",\n            \"Deep learning enables automated feature extraction from high-dimensional neuroimaging data.\",\n            \"We hypothesise that multimodal fusion will significantly outperform single-modality approaches for early AD classification.\",\n        ],\n\n        methods_lines=[\n            \"Dataset: 1,200 subjects from ADNI (400 CN, 400 MCI, 400 AD).\",\n            \"Modalities: T1-weighted MRI (3T), FDG-PET, CSF Aβ42\u002Ftau ratios.\",\n            \"Preprocessing: FreeSurfer cortical parcellation, SPM12 PET normalisation.\",\n            \"Architecture: Three-stream CNN encoders with cross-modal attention fusion.\",\n            \"Training: 5-fold cross-validation, AdamW optimiser, cosine LR schedule.\",\n            \"Evaluation: Accuracy, AUC-ROC, sensitivity\u002Fspecificity for CN vs. MCI vs. AD.\",\n        ],\n\n        results_lines=[\n            \"94.2% overall accuracy (vs. 86.1% MRI-only baseline).\",\n            \"AUC-ROC: 0.97 for AD vs. CN; 0.89 for MCI vs. CN.\",\n            \"Cross-modal attention identified hippocampus, entorhinal cortex, and precuneus as most predictive.\",\n            \"Model generalises across APOE-ε4 carrier subgroups (p > 0.05 for subgroup differences).\",\n        ],\n\n        conclusions_lines=[\n            \"Multimodal deep learning significantly improves early AD detection over single-modality approaches.\",\n            \"Cross-modal attention provides interpretable biomarker importance maps consistent with known AD pathology.\",\n            \"The framework is scanner-agnostic and generalises across genetic risk subgroups.\",\n            \"Future work: longitudinal modelling, external validation, prospective clinical study.\",\n        ],\n\n        acknowledgements=\"Funded by NIH R01-AG012345 and the Alzheimer's Association Research Grant #AARG-22-000123. \"\n                         \"Data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI). \"\n                         \"Computing resources from the National Center for Supercomputing Applications.\",\n\n        references_lines=[\n            \"[1] Jack et al. (2018). NIA-AA Research Framework. Alzheimer's & Dementia, 14, 535–562.\",\n            \"[2] Litjens et al. (2017). A survey on deep learning in medical image analysis. Med. Im. Analysis, 42, 60–88.\",\n            \"[3] Ngiam et al. (2011). Multimodal deep learning. ICML 2011.\",\n            \"[4] Zhang et al. (2022). Multimodal neuroimaging fusion for AD. NeuroImage, 249, 118907.\",\n            \"[5] Petersen et al. (2014). ADNI: 10 years. Arch Neurol, 71, 806–813.\",\n        ],\n\n        figure1_path=\"figures\u002Froc_curves.png\",\n        figure1_caption=\"Figure 1. ROC curves for AD vs. CN (AUC = 0.97), MCI vs. CN (AUC = 0.89), and AD vs. MCI (AUC = 0.91).\",\n        figure2_path=\"figures\u002Fattention_map.png\",\n        figure2_caption=\"Figure 2. Cross-modal attention heatmaps overlaid on MRI showing hippocampal and entorhinal activation.\",\n        methods_figure_path=\"figures\u002Farchitecture.png\",\n        methods_figure_caption=\"Figure 3. Three-stream CNN architecture with cross-modal attention fusion module.\",\n\n        logo_left=\"logos\u002Funiversity_logo.png\",\n        logo_right=\"logos\u002Ffunder_logo.png\",\n        color_scheme=\"classic_blue\",\n        output_path=\"poster_ad_multimodal.pptx\"\n    )\n```\n\n---\n\n## Portrait Poster (A0 \u002F A1)\n\nFor portrait orientation, adjust dimensions and use a two-column layout:\n\n```python\n# A0 Portrait: 84.1 cm × 118.9 cm\ndef create_portrait_poster(output_path=\"poster_portrait.pptx\"):\n    prs = Presentation()\n    prs.slide_width  = Cm(84.1)\n    prs.slide_height = Cm(118.9)\n    slide_layout = prs.slide_layouts[6]\n    slide = prs.slides.add_slide(slide_layout)\n    return prs, slide\n\n# A1 Landscape: 84.1 cm × 59.4 cm\ndef create_a1_landscape(output_path=\"poster_a1.pptx\"):\n    prs = Presentation()\n    prs.slide_width  = Cm(84.1)\n    prs.slide_height = Cm(59.4)\n    slide_layout = prs.slide_layouts[6]\n    slide = prs.slides.add_slide(slide_layout)\n    return prs, slide\n```\n\n---\n\n## PDF Export\n\n### Via LibreOffice (command line — cross-platform)\n\n```bash\n# Export .pptx to PDF using LibreOffice headless mode\nlibreoffice --headless --convert-to pdf poster_ad_multimodal.pptx --outdir .\u002F\n\n# Or specify output directory\nlibreoffice --headless --convert-to pdf:impress_pdf_Export poster.pptx --outdir output\u002F\n```\n\n### Via Python subprocess\n\n```python\nimport subprocess\nimport os\n\ndef export_to_pdf(pptx_path: str, output_dir: str = \".\") -> str:\n    \"\"\"Convert .pptx to PDF using LibreOffice.\"\"\"\n    os.makedirs(output_dir, exist_ok=True)\n    result = subprocess.run(\n        [\"libreoffice\", \"--headless\", \"--convert-to\", \"pdf\",\n         pptx_path, \"--outdir\", output_dir],\n        capture_output=True, text=True\n    )\n    if result.returncode != 0:\n        raise RuntimeError(f\"LibreOffice conversion failed:\\n{result.stderr}\")\n\n    pdf_name = os.path.splitext(os.path.basename(pptx_path))[0] + \".pdf\"\n    pdf_path = os.path.join(output_dir, pdf_name)\n    print(f\"[OK] PDF exported: {pdf_path}\")\n    return pdf_path\n```\n\n---\n\n## Verification Checklist\n\nBefore delivering the poster:\n\n- [ ] Title, authors, affiliations render correctly in header\n- [ ] All sections have content (no empty boxes)\n- [ ] All referenced image files exist and load without warnings\n- [ ] Text is not clipped or overflowing section boxes (check at 100% zoom)\n- [ ] Font sizes are legible at the target print size (≥18pt for body, ≥24pt for section headers)\n- [ ] Color scheme is consistent throughout\n- [ ] .pptx opens correctly in both PowerPoint and LibreOffice\n- [ ] PDF export renders without distortion\n\n---\n\n## Common Issues and Fixes\n\n| Problem | Likely cause | Fix |\n|---------|-------------|-----|\n| Text overflows section box | Font size too large \u002F too many lines | Reduce font size or split into two sections |\n| Image not inserted | File path wrong or file missing | Check `os.path.exists(path)` before calling `add_image` |\n| Wrong poster size | `slide_width`\u002F`slide_height` set in inches, not EMUs | Use `Cm()` or `Inches()` wrappers, not raw integers |\n| Logo appears stretched | Width and height both specified with wrong aspect ratio | Set only `width=` and let python-pptx auto-compute height |\n| PDF looks different from .pptx | Font not installed on LibreOffice machine | Embed fonts or use system fonts (Calibri → Liberation Sans) |\n| Columns misaligned | Arithmetic error in column left\u002Fwidth calculations | Print all `left`, `top`, `width`, `height` values and verify sum |\n\n---\n\n## Integration with Scientific Schematics\n\nFor high-quality figures to embed in the poster, use the `scientific-schematics` skill before generating the poster:\n\n```bash\n# Generate workflow diagram for Methods section\npython \u003Cpath-to-scientific-schematics-skill>\u002Fscripts\u002Fgenerate_schematic.py \\\n  \"Three-stream CNN architecture: MRI encoder, PET encoder, CSF encoder feeding into cross-modal attention fusion with final classification layer\" \\\n  -o figures\u002Farchitecture.png\n\n# Generate results figure\npython \u003Cpath-to-scientific-schematics-skill>\u002Fscripts\u002Fgenerate_schematic.py \\\n  \"ROC curves for three-class neuroimaging classification showing AD vs CN AUC 0.97, MCI vs CN AUC 0.89\" \\\n  -o figures\u002Froc_curves.png\n```\n\nThen pass the generated file paths as `figure1_path`, `figure2_path`, or `methods_figure_path` arguments to the poster builder.\n\n---\n\n## File Naming Conventions\n\n```\nposters\u002F\n└── YYYYMMDD_\u003Cshort_title>\u002F\n    ├── poster.pptx          # Primary deliverable\n    ├── poster.pdf           # PDF export\n    ├── generate_poster.py   # Generation script (reproducible)\n    └── figures\u002F             # Embedded images\n        ├── fig1_results.png\n        ├── fig2_attention.png\n        └── fig3_architecture.png\n```\n","# Scientific Conference Poster — PowerPoint (.pptx)\n\n## Overview\n\nThis skill creates professional scientific conference posters as editable PowerPoint (.pptx) files using `python-pptx`. It supports standard conference poster sizes (A0, A1), landscape and portrait orientations, structured academic sections, figure insertion with captions, and publication-quality academic color schemes.\n\nThe generated `.pptx` is fully editable, allowing researchers to fine-tune layout, fonts, and colors using Microsoft PowerPoint, LibreOffice Impress, or any compatible application. PDF export is available via LibreOffice or PowerPoint.\n\n---\n\n## When to Use This Skill\n\nUse this skill when:\n- Creating a poster for an academic conference, symposium, or workshop\n- Converting a research paper or manuscript into poster format\n- Building a poster template for a research group or institution\n- Presenting preliminary results, thesis work, or funded project outcomes\n- Needing an editable (non-PDF) poster that collaborators can update\n\n**Trigger phrases:**\n- \"Create a conference poster as a PowerPoint \u002F .pptx\"\n- \"Make me a scientific poster I can edit in PowerPoint\"\n- \"Generate a poster for my paper \u002F conference \u002F symposium\"\n- \"Build an A0 \u002F A1 poster for [conference name]\"\n- \"Create a research poster with sections for methods, results, conclusions\"\n\n---\n\n## Prerequisites\n\nInstall required Python packages before running any poster generation code:\n\n```bash\npip install python-pptx Pillow\n```\n\nFor PDF export from the command line:\n\n```bash\n# macOS (via Homebrew)\nbrew install --cask libreoffice\n\n# Ubuntu \u002F Debian\nsudo apt-get install libreoffice\n\n# Windows — download from https:\u002F\u002Fwww.libreoffice.org\u002F\n```\n\n---\n\n## Standard Poster Dimensions\n\n| Format   | Orientation | Width (cm) | Height (cm) | Width (in) | Height (in) | Common use          |\n|----------|-------------|------------|-------------|------------|-------------|---------------------|\n| A0       | Portrait    | 84.1       | 118.9       | 33.11      | 46.81       | European conferences|\n| A0       | Landscape   | 118.9      | 84.1        | 46.81      | 33.11       | US \u002F mixed format   |\n| A1       | Portrait    | 59.4       | 84.1        | 23.39      | 33.11       | Smaller venues      |\n| A1       | Landscape   | 84.1       | 59.4        | 33.11      | 23.39       | Departmental events |\n| 36×48 in | Portrait    | 91.44      | 121.92      | 36.0       | 48.0        | US conferences      |\n| 48×36 in | Landscape   | 121.92     | 91.44       | 48.0       | 36.0        | US conferences      |\n\n**python-pptx uses EMUs (English Metric Units): 1 inch = 914400 EMU, 1 cm = 360000 EMU**\n\n---\n\n## Workflow Phases\n\n### Phase 1: Gather Content\n\nCollect all poster content from the user or source document:\n\n1. **Title** — full paper\u002Fposter title\n2. **Authors** — list with superscript affiliation numbers\n3. **Affiliations** — institution names linked to authors\n4. **Contact \u002F corresponding author** email\n5. **Abstract** — 150–250 words\n6. **Introduction \u002F Background** — key context and motivation (3–5 bullet points or short paragraphs)\n7. **Methods** — concise description with optional workflow figure\n8. **Results** — key findings, data visualizations, tables\n9. **Conclusions** — 4–6 bullet points\n10. **Acknowledgements** — funding sources, collaborators\n11. **References** — 5–10 key references (abbreviated format)\n12. **Figures** — file paths to images\u002Fplots to embed\n13. **Logo(s)** — institutional\u002Fconference logo paths\n14. **Color scheme** — preferred colors or institution palette (see schemes below)\n\n### Phase 2: Plan Layout\n\nStandard two- or three-column academic poster layout:\n\n```\n┌──────────────────────────────────────────────────────────┐\n│  LOGO  │           TITLE \u002F AUTHORS \u002F AFFILIATIONS         │  LOGO │\n├─────────────────┬────────────────┬────────────────────────┤\n│  Introduction   │   Methods      │   Results              │\n│                 │                │                        │\n│  Background     │   Workflow     │   Figure 1             │\n│                 │   Figure       │                        │\n├─────────────────┴────────────────┤   Figure 2             │\n│  [Optional middle spanning row]  │                        │\n├─────────────────┬────────────────┼────────────────────────┤\n│  Conclusions    │ Acknowledgements│  References            │\n└─────────────────┴────────────────┴────────────────────────┘\n```\n\n### Phase 3: Generate .pptx\n\nUse the code templates below to build the poster programmatically.\n\n### Phase 4: Export\n\n- Save as `.pptx` (primary deliverable — fully editable)\n- Export to PDF via LibreOffice or PowerPoint (see export section)\n- Verify layout at 100% zoom before delivering\n\n---\n\n## Core Code: Poster Foundation\n\n```python\n\"\"\"\nscientific_poster.py — Generate A0 landscape conference poster as .pptx\nRequires: python-pptx, Pillow\n\"\"\"\n\nfrom pptx import Presentation\nfrom pptx.util import Inches, Pt, Emu, Cm\nfrom pptx.dml.color import RGBColor\nfrom pptx.enum.text import PP_ALIGN\nfrom pptx.util import Inches, Pt\nimport os\n\n\n# ── Dimensions ────────────────────────────────────────────────────────────────\n# A0 Landscape: 118.9 cm × 84.1 cm\nPOSTER_WIDTH_CM  = 118.9\nPOSTER_HEIGHT_CM = 84.1\n\ndef cm(value):\n    \"\"\"Convert centimetres to EMUs.\"\"\"\n    return Cm(value)\n\n\ndef create_poster(output_path: str = \"poster.pptx\") -> Presentation:\n    \"\"\"Create and return a blank poster Presentation at A0 landscape size.\"\"\"\n    prs = Presentation()\n    prs.slide_width  = cm(POSTER_WIDTH_CM)\n    prs.slide_height = cm(POSTER_HEIGHT_CM)\n\n    # Remove all default placeholder layouts — use blank slide\n    slide_layout = prs.slide_layouts[6]  # index 6 = blank\n    slide = prs.slides.add_slide(slide_layout)\n\n    return prs, slide\n```\n\n---\n\n## Academic Color Schemes\n\n```python\n# ── Color Palettes ────────────────────────────────────────────────────────────\n\nSCHEMES = {\n    \"classic_blue\": {\n        \"header_bg\":    RGBColor(0x1A, 0x3A, 0x5C),   # dark navy\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),   # white\n        \"section_bg\":   RGBColor(0xD6, 0xE4, 0xF0),   # light blue\n        \"section_header\": RGBColor(0x1A, 0x3A, 0x5C),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0xE8, 0x8A, 0x00),   # amber\n        \"background\":   RGBColor(0xF5, 0xF7, 0xFA),\n    },\n    \"green_academic\": {\n        \"header_bg\":    RGBColor(0x1B, 0x4B, 0x36),   # forest green\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),\n        \"section_bg\":   RGBColor(0xD8, 0xED, 0xE3),   # light green\n        \"section_header\": RGBColor(0x1B, 0x4B, 0x36),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0xC0, 0x39, 0x2B),   # red\n        \"background\":   RGBColor(0xF4, 0xF9, 0xF6),\n    },\n    \"crimson_grey\": {\n        \"header_bg\":    RGBColor(0x8B, 0x00, 0x00),   # crimson\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),\n        \"section_bg\":   RGBColor(0xF0, 0xE8, 0xE8),   # blush\n        \"section_header\": RGBColor(0x8B, 0x00, 0x00),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0x2C, 0x3E, 0x50),   # slate\n        \"background\":   RGBColor(0xFA, 0xF9, 0xF9),\n    },\n    \"purple_modern\": {\n        \"header_bg\":    RGBColor(0x4A, 0x14, 0x8C),   # deep purple\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),\n        \"section_bg\":   RGBColor(0xED, 0xE7, 0xF6),   # lavender\n        \"section_header\": RGBColor(0x4A, 0x14, 0x8C),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0xF5, 0x7C, 0x00),   # orange\n        \"background\":   RGBColor(0xFA, 0xF8, 0xFF),\n    },\n    \"monochrome\": {\n        \"header_bg\":    RGBColor(0x21, 0x21, 0x21),\n        \"header_text\":  RGBColor(0xFF, 0xFF, 0xFF),\n        \"section_bg\":   RGBColor(0xEE, 0xEE, 0xEE),\n        \"section_header\": RGBColor(0x21, 0x21, 0x21),\n        \"body_text\":    RGBColor(0x1A, 0x1A, 0x1A),\n        \"accent\":       RGBColor(0x75, 0x75, 0x75),\n        \"background\":   RGBColor(0xFF, 0xFF, 0xFF),\n    },\n}\n\nDEFAULT_SCHEME = \"classic_blue\"\n```\n\n---\n\n## Helper Functions\n\n```python\n# ── Drawing helpers ────────────────────────────────────────────────────────────\n\nfrom pptx.oxml.ns import qn\nfrom lxml import etree\n\n\ndef set_background_color(slide, color: RGBColor):\n    \"\"\"Fill the slide background with a solid color.\"\"\"\n    background = slide.background\n    fill = background.fill\n    fill.solid()\n    fill.fore_color.rgb = color\n\n\ndef add_filled_rectangle(slide, left, top, width, height,\n                          fill_color: RGBColor, line_color=None, line_width_pt=0):\n    \"\"\"Add a solid filled rectangle shape (used for section boxes and header).\"\"\"\n    shape = slide.shapes.add_shape(\n        1,  # MSO_SHAPE_TYPE.RECTANGLE\n        left, top, width, height\n    )\n    shape.fill.solid()\n    shape.fill.fore_color.rgb = fill_color\n\n    if line_color:\n        shape.line.color.rgb = line_color\n        shape.line.width = Pt(line_width_pt)\n    else:\n        shape.line.fill.background()  # no border\n\n    return shape\n\n\ndef add_textbox(slide, left, top, width, height, text: str,\n                font_size: int, font_color: RGBColor,\n                bold=False, italic=False, alignment=PP_ALIGN.LEFT,\n                word_wrap=True, font_name=\"Calibri\"):\n    \"\"\"Add a text box with specified formatting.\"\"\"\n    txBox = slide.shapes.add_textbox(left, top, width, height)\n    tf = txBox.text_frame\n    tf.word_wrap = word_wrap\n\n    p = tf.paragraphs[0]\n    p.alignment = alignment\n    run = p.add_run()\n    run.text = text\n\n    font = run.font\n    font.name = font_name\n    font.size = Pt(font_size)\n    font.color.rgb = font_color\n    font.bold = bold\n    font.italic = italic\n\n    return txBox\n\n\ndef add_multiline_textbox(slide, left, top, width, height, lines: list,\n                           font_size: int, font_color: RGBColor,\n                           bold_first=False, font_name=\"Calibri\",\n                           bullet=False, line_spacing_pt=None):\n    \"\"\"\n    Add a text box with multiple paragraphs (one per item in `lines`).\n    If bullet=True, prepends '• ' to each line.\n    \"\"\"\n    txBox = slide.shapes.add_textbox(left, top, width, height)\n    tf = txBox.text_frame\n    tf.word_wrap = True\n\n    for i, line in enumerate(lines):\n        if i == 0:\n            p = tf.paragraphs[0]\n        else:\n            p = tf.add_paragraph()\n\n        p.alignment = PP_ALIGN.LEFT\n        run = p.add_run()\n        prefix = \"• \" if bullet else \"\"\n        run.text = prefix + line\n\n        font = run.font\n        font.name = font_name\n        font.size = Pt(font_size)\n        font.color.rgb = font_color\n        font.bold = (bold_first and i == 0)\n\n        if line_spacing_pt:\n            from pptx.util import Pt as pPt\n            from pptx.oxml.ns import qn\n            pPr = p._pPr\n            if pPr is None:\n                pPr = p._p.get_or_add_pPr()\n            lnSpc = etree.SubElement(pPr, qn(\"a:lnSpc\"))\n            spcPts = etree.SubElement(lnSpc, qn(\"a:spcPts\"))\n            spcPts.set(\"val\", str(int(line_spacing_pt * 100)))\n\n    return txBox\n\n\ndef add_image(slide, image_path: str, left, top, width, height=None):\n    \"\"\"\n    Insert an image at the specified position.\n    If height is None, python-pptx preserves the aspect ratio.\n    \"\"\"\n    if not os.path.exists(image_path):\n        print(f\"[WARNING] Image not found: {image_path} — skipping.\")\n        return None\n\n    if height is None:\n        pic = slide.shapes.add_picture(image_path, left, top, width=width)\n    else:\n        pic = slide.shapes.add_picture(image_path, left, top, width, height)\n\n    return pic\n\n\ndef add_section_header(slide, left, top, width, height,\n                        title: str, scheme: dict, font_size=24):\n    \"\"\"Draw a colored section header bar with white text.\"\"\"\n    add_filled_rectangle(slide, left, top, width, height,\n                         fill_color=scheme[\"section_header\"])\n    add_textbox(slide, left + Cm(0.3), top, width - Cm(0.3), height,\n                text=title,\n                font_size=font_size,\n                font_color=scheme[\"header_text\"],\n                bold=True,\n                alignment=PP_ALIGN.LEFT)\n```\n\n---\n\n## Poster Header Section\n\n```python\ndef build_header(slide, scheme: dict,\n                 title: str,\n                 authors: str,\n                 affiliations: str,\n                 logo_left_path: str = None,\n                 logo_right_path: str = None,\n                 poster_width_cm: float = POSTER_WIDTH_CM):\n    \"\"\"\n    Build the full-width header: logos on left\u002Fright, title\u002Fauthors\u002Faffiliations centre.\n    Header height = ~15% of poster height.\n    \"\"\"\n    HEADER_HEIGHT = cm(12)\n    LOGO_WIDTH    = cm(12)\n    PADDING       = cm(1)\n\n    # Background bar\n    add_filled_rectangle(slide,\n                         left=cm(0), top=cm(0),\n                         width=cm(poster_width_cm), height=HEADER_HEIGHT,\n                         fill_color=scheme[\"header_bg\"])\n\n    # Left logo\n    if logo_left_path and os.path.exists(logo_left_path):\n        add_image(slide, logo_left_path,\n                  left=PADDING, top=cm(1),\n                  width=LOGO_WIDTH, height=cm(10))\n\n    # Right logo\n    if logo_right_path and os.path.exists(logo_right_path):\n        add_image(slide, logo_right_path,\n                  left=cm(poster_width_cm) - LOGO_WIDTH - PADDING,\n                  top=cm(1),\n                  width=LOGO_WIDTH, height=cm(10))\n\n    # Title — centered\n    text_left  = LOGO_WIDTH + PADDING * 2\n    text_width = cm(poster_width_cm) - (LOGO_WIDTH + PADDING) * 2\n\n    add_textbox(slide,\n                left=text_left, top=cm(1),\n                width=text_width, height=cm(5),\n                text=title,\n                font_size=52,\n                font_color=scheme[\"header_text\"],\n                bold=True,\n                alignment=PP_ALIGN.CENTER)\n\n    add_textbox(slide,\n                left=text_left, top=cm(6),\n                width=text_width, height=cm(2.5),\n                text=authors,\n                font_size=28,\n                font_color=scheme[\"header_text\"],\n                bold=False,\n                alignment=PP_ALIGN.CENTER)\n\n    add_textbox(slide,\n                left=text_left, top=cm(8.5),\n                width=text_width, height=cm(2),\n                text=affiliations,\n                font_size=22,\n                font_color=scheme[\"header_text\"],\n                italic=True,\n                alignment=PP_ALIGN.CENTER)\n```\n\n---\n\n## Section Building Blocks\n\n```python\ndef build_text_section(slide, left, top, width, height,\n                        section_title: str,\n                        content_lines: list,\n                        scheme: dict,\n                        header_height_cm: float = 2.0,\n                        font_size: int = 20,\n                        bullet: bool = True):\n    \"\"\"\n    Draw a complete section box: colored header + white body with text lines.\n    \"\"\"\n    HDR = cm(header_height_cm)\n\n    # Section background\n    add_filled_rectangle(slide, left, top, width, height,\n                         fill_color=scheme[\"section_bg\"],\n                         line_color=scheme[\"section_header\"],\n                         line_width_pt=1.5)\n\n    # Section header bar\n    add_section_header(slide, left, top, width, HDR,\n                       title=section_title, scheme=scheme)\n\n    # Body text\n    add_multiline_textbox(slide,\n                          left=left + cm(0.5),\n                          top=top + HDR + cm(0.3),\n                          width=width - cm(1),\n                          height=height - HDR - cm(0.5),\n                          lines=content_lines,\n                          font_size=font_size,\n                          font_color=scheme[\"body_text\"],\n                          bullet=bullet)\n\n\ndef build_figure_section(slide, left, top, width, height,\n                          section_title: str,\n                          image_path: str,\n                          caption: str,\n                          scheme: dict,\n                          header_height_cm: float = 2.0,\n                          caption_height_cm: float = 2.5):\n    \"\"\"\n    Draw a section box containing a figure + caption below it.\n    \"\"\"\n    HDR     = cm(header_height_cm)\n    CAPTION = cm(caption_height_cm)\n    PAD     = cm(0.4)\n\n    # Background\n    add_filled_rectangle(slide, left, top, width, height,\n                         fill_color=scheme[\"section_bg\"],\n                         line_color=scheme[\"section_header\"],\n                         line_width_pt=1.5)\n\n    # Header\n    add_section_header(slide, left, top, width, HDR,\n                       title=section_title, scheme=scheme)\n\n    # Image area\n    img_top    = top + HDR + PAD\n    img_height = height - HDR - CAPTION - PAD * 2\n\n    if image_path:\n        add_image(slide, image_path,\n                  left=left + PAD,\n                  top=img_top,\n                  width=width - PAD * 2,\n                  height=img_height)\n    else:\n        # Placeholder grey box when no image provided\n        add_filled_rectangle(slide,\n                             left=left + PAD, top=img_top,\n                             width=width - PAD * 2, height=img_height,\n                             fill_color=RGBColor(0xCC, 0xCC, 0xCC))\n\n    # Caption\n    add_textbox(slide,\n                left=left + PAD,\n                top=top + HDR + PAD + img_height,\n                width=width - PAD * 2,\n                height=CAPTION,\n                text=caption,\n                font_size=18,\n                font_color=scheme[\"body_text\"],\n                italic=True,\n                alignment=PP_ALIGN.CENTER)\n```\n\n---\n\n## Full Poster Assembly — Three-Column A0 Landscape\n\n```python\ndef build_a0_landscape_poster(\n    title: str,\n    authors: str,\n    affiliations: str,\n    abstract_lines: list,\n    intro_lines: list,\n    methods_lines: list,\n    results_lines: list,\n    conclusions_lines: list,\n    acknowledgements: str,\n    references_lines: list,\n    figure1_path: str = None,\n    figure1_caption: str = \"Figure 1.\",\n    figure2_path: str = None,\n    figure2_caption: str = \"Figure 2.\",\n    methods_figure_path: str = None,\n    methods_figure_caption: str = \"Workflow.\",\n    logo_left: str = None,\n    logo_right: str = None,\n    color_scheme: str = \"classic_blue\",\n    output_path: str = \"poster.pptx\"\n):\n    \"\"\"\n    Build a complete three-column A0 landscape scientific poster.\n\n    Layout (all measurements in cm from top-left origin):\n      Header:  full width, 0–12 cm\n      Column 1 (left):   0–38 cm wide,  12–82 cm tall\n      Column 2 (middle): 40–78 cm wide, 12–82 cm tall\n      Column 3 (right):  80–118 cm wide, 12–82 cm tall\n      Footer:  full width, 82–84.1 cm\n    \"\"\"\n    scheme = SCHEMES.get(color_scheme, SCHEMES[DEFAULT_SCHEME])\n    prs, slide = create_poster(output_path)\n\n    # Poster background\n    set_background_color(slide, scheme[\"background\"])\n\n    # ── HEADER ──────────────────────────────────────────────────────────────\n    build_header(slide, scheme,\n                 title=title, authors=authors, affiliations=affiliations,\n                 logo_left_path=logo_left, logo_right_path=logo_right)\n\n    # ── LAYOUT CONSTANTS ────────────────────────────────────────────────────\n    COL_TOP    = cm(12.5)\n    COL_BOTTOM = cm(82)\n    COL_HEIGHT = COL_BOTTOM - COL_TOP\n    GAP        = cm(1.5)\n\n    C1_LEFT  = cm(1)\n    C1_WIDTH = cm(37)\n    C2_LEFT  = C1_LEFT + C1_WIDTH + GAP\n    C2_WIDTH = cm(37)\n    C3_LEFT  = C2_LEFT + C2_WIDTH + GAP\n    C3_WIDTH = cm(POSTER_WIDTH_CM) - C3_LEFT - cm(1)\n\n    # ── COLUMN 1: Abstract + Introduction ───────────────────────────────────\n    ABSTRACT_H = cm(22)\n    build_text_section(slide,\n                       left=C1_LEFT, top=COL_TOP,\n                       width=C1_WIDTH, height=ABSTRACT_H,\n                       section_title=\"Abstract\",\n                       content_lines=abstract_lines,\n                       scheme=scheme, bullet=False, font_size=19)\n\n    INTRO_H = COL_HEIGHT - ABSTRACT_H - GAP\n    build_text_section(slide,\n                       left=C1_LEFT, top=COL_TOP + ABSTRACT_H + GAP,\n                       width=C1_WIDTH, height=INTRO_H,\n                       section_title=\"Introduction & Background\",\n                       content_lines=intro_lines,\n                       scheme=scheme, bullet=True, font_size=20)\n\n    # ── COLUMN 2: Methods + Methods Figure ──────────────────────────────────\n    METHODS_TEXT_H  = cm(28)\n    METHODS_FIG_H   = COL_HEIGHT - METHODS_TEXT_H - GAP\n\n    build_text_section(slide,\n                       left=C2_LEFT, top=COL_TOP,\n                       width=C2_WIDTH, height=METHODS_TEXT_H,\n                       section_title=\"Methods\",\n                       content_lines=methods_lines,\n                       scheme=scheme, bullet=True, font_size=20)\n\n    build_figure_section(slide,\n                          left=C2_LEFT,\n                          top=COL_TOP + METHODS_TEXT_H + GAP,\n                          width=C2_WIDTH, height=METHODS_FIG_H,\n                          section_title=\"Workflow\",\n                          image_path=methods_figure_path,\n                          caption=methods_figure_caption,\n                          scheme=scheme)\n\n    # ── COLUMN 3: Results (2 figures) + Conclusions ─────────────────────────\n    FIG1_H        = cm(26)\n    FIG2_H        = cm(22)\n    CONCLUSIONS_H = COL_HEIGHT - FIG1_H - FIG2_H - GAP * 2\n\n    build_figure_section(slide,\n                          left=C3_LEFT, top=COL_TOP,\n                          width=C3_WIDTH, height=FIG1_H,\n                          section_title=\"Results\",\n                          image_path=figure1_path,\n                          caption=figure1_caption,\n                          scheme=scheme)\n\n    build_figure_section(slide,\n                          left=C3_LEFT, top=COL_TOP + FIG1_H + GAP,\n                          width=C3_WIDTH, height=FIG2_H,\n                          section_title=\"\",\n                          image_path=figure2_path,\n                          caption=figure2_caption,\n                          scheme=scheme)\n\n    build_text_section(slide,\n                       left=C3_LEFT,\n                       top=COL_TOP + FIG1_H + FIG2_H + GAP * 2,\n                       width=C3_WIDTH, height=CONCLUSIONS_H,\n                       section_title=\"Conclusions\",\n                       content_lines=conclusions_lines,\n                       scheme=scheme, bullet=True, font_size=20)\n\n    # ── FOOTER: Acknowledgements + References ───────────────────────────────\n    FOOTER_TOP = cm(82.5)\n    FOOTER_H   = cm(POSTER_HEIGHT_CM) - FOOTER_TOP\n    HALF_W     = (cm(POSTER_WIDTH_CM) - cm(2)) \u002F 2\n\n    build_text_section(slide,\n                       left=cm(1), top=FOOTER_TOP,\n                       width=HALF_W, height=FOOTER_H,\n                       section_title=\"Acknowledgements\",\n                       content_lines=[acknowledgements],\n                       scheme=scheme, bullet=False, font_size=16)\n\n    build_text_section(slide,\n                       left=cm(1) + HALF_W + GAP, top=FOOTER_TOP,\n                       width=HALF_W - GAP, height=FOOTER_H,\n                       section_title=\"References\",\n                       content_lines=references_lines,\n                       scheme=scheme, bullet=False, font_size=15)\n\n    # ── SAVE ────────────────────────────────────────────────────────────────\n    prs.save(output_path)\n    print(f\"[OK] Poster saved: {output_path}\")\n    return output_path\n```\n\n---\n\n## Example Usage\n\n```python\nif __name__ == \"__main__\":\n    build_a0_landscape_poster(\n        title=\"Deep Learning for Early Detection of Alzheimer's Disease\\nUsing Multimodal Neuroimaging\",\n        authors=\"J. Smith¹, A. Patel², R. Müller¹, L. Chen³\",\n        affiliations=\"¹Dept. of Neuroscience, University of Example | ²Brain Imaging Centre, City Hospital | ³ML Lab, Tech Institute\",\n\n        abstract_lines=[\n            \"Alzheimer's disease (AD) affects over 55 million people worldwide. \"\n            \"Early and accurate diagnosis remains a significant clinical challenge. \"\n            \"We present a multimodal deep learning framework integrating structural MRI, \"\n            \"FDG-PET, and cerebrospinal fluid biomarkers to improve early AD detection. \"\n            \"Our model achieves 94.2% accuracy on the ADNI dataset, outperforming \"\n            \"unimodal baselines by 8.3 percentage points. These results suggest \"\n            \"multimodal fusion substantially improves pre-clinical AD diagnosis.\"\n        ],\n\n        intro_lines=[\n            \"Alzheimer's disease is the leading cause of dementia, with costs exceeding $300B\u002Fyear in the US alone.\",\n            \"Current diagnostic methods rely on late-stage symptom presentation, missing the critical early treatment window.\",\n            \"Neuroimaging biomarkers (MRI atrophy, PET hypometabolism) show promise but are typically analysed in isolation.\",\n            \"Deep learning enables automated feature extraction from high-dimensional neuroimaging data.\",\n            \"We hypothesise that multimodal fusion will significantly outperform single-modality approaches for early AD classification.\",\n        ],\n\n        methods_lines=[\n            \"Dataset: 1,200 subjects from ADNI (400 CN, 400 MCI, 400 AD).\",\n            \"Modalities: T1-weighted MRI (3T), FDG-PET, CSF Aβ42\u002Ftau ratios.\",\n            \"Preprocessing: FreeSurfer cortical parcellation, SPM12 PET normalisation.\",\n            \"Architecture: Three-stream CNN encoders with cross-modal attention fusion.\",\n            \"Training: 5-fold cross-validation, AdamW optimiser, cosine LR schedule.\",\n            \"Evaluation: Accuracy, AUC-ROC, sensitivity\u002Fspecificity for CN vs. MCI vs. AD.\",\n        ],\n\n        results_lines=[\n            \"94.2% overall accuracy (vs. 86.1% MRI-only baseline).\",\n            \"AUC-ROC: 0.97 for AD vs. CN; 0.89 for MCI vs. CN.\",\n            \"Cross-modal attention identified hippocampus, entorhinal cortex, and precuneus as most predictive.\",\n            \"Model generalises across APOE-ε4 carrier subgroups (p > 0.05 for subgroup differences).\",\n        ],\n\n        conclusions_lines=[\n            \"Multimodal deep learning significantly improves early AD detection over single-modality approaches.\",\n            \"Cross-modal attention provides interpretable biomarker importance maps consistent with known AD pathology.\",\n            \"The framework is scanner-agnostic and generalises across genetic risk subgroups.\",\n            \"Future work: longitudinal modelling, external validation, prospective clinical study.\",\n        ],\n\n        acknowledgements=\"Funded by NIH R01-AG012345 and the Alzheimer's Association Research Grant #AARG-22-000123. \"\n                         \"Data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI). \"\n                         \"Computing resources from the National Center for Supercomputing Applications.\",\n\n        references_lines=[\n            \"[1] Jack et al. (2018). NIA-AA Research Framework. Alzheimer's & Dementia, 14, 535–562.\",\n            \"[2] Litjens et al. (2017). A survey on deep learning in medical image analysis. Med. Im. Analysis, 42, 60–88.\",\n            \"[3] Ngiam et al. (2011). Multimodal deep learning. ICML 2011.\",\n            \"[4] Zhang et al. (2022). Multimodal neuroimaging fusion for AD. NeuroImage, 249, 118907.\",\n            \"[5] Petersen et al. (2014). ADNI: 10 years. Arch Neurol, 71, 806–813.\",\n        ],\n\n        figure1_path=\"figures\u002Froc_curves.png\",\n        figure1_caption=\"Figure 1. ROC curves for AD vs. CN (AUC = 0.97), MCI vs. CN (AUC = 0.89), and AD vs. MCI (AUC = 0.91).\",\n        figure2_path=\"figures\u002Fattention_map.png\",\n        figure2_caption=\"Figure 2. Cross-modal attention heatmaps overlaid on MRI showing hippocampal and entorhinal activation.\",\n        methods_figure_path=\"figures\u002Farchitecture.png\",\n        methods_figure_caption=\"Figure 3. Three-stream CNN architecture with cross-modal attention fusion module.\",\n\n        logo_left=\"logos\u002Funiversity_logo.png\",\n        logo_right=\"logos\u002Ffunder_logo.png\",\n        color_scheme=\"classic_blue\",\n        output_path=\"poster_ad_multimodal.pptx\"\n    )\n```\n\n---\n\n## Portrait Poster (A0 \u002F A1)\n\nFor portrait orientation, adjust dimensions and use a two-column layout:\n\n```python\n# A0 Portrait: 84.1 cm × 118.9 cm\ndef create_portrait_poster(output_path=\"poster_portrait.pptx\"):\n    prs = Presentation()\n    prs.slide_width  = Cm(84.1)\n    prs.slide_height = Cm(118.9)\n    slide_layout = prs.slide_layouts[6]\n    slide = prs.slides.add_slide(slide_layout)\n    return prs, slide\n\n# A1 Landscape: 84.1 cm × 59.4 cm\ndef create_a1_landscape(output_path=\"poster_a1.pptx\"):\n    prs = Presentation()\n    prs.slide_width  = Cm(84.1)\n    prs.slide_height = Cm(59.4)\n    slide_layout = prs.slide_layouts[6]\n    slide = prs.slides.add_slide(slide_layout)\n    return prs, slide\n```\n\n---\n\n## PDF Export\n\n### Via LibreOffice (command line — cross-platform)\n\n```bash\n# Export .pptx to PDF using LibreOffice headless mode\nlibreoffice --headless --convert-to pdf poster_ad_multimodal.pptx --outdir .\u002F\n\n# Or specify output directory\nlibreoffice --headless --convert-to pdf:impress_pdf_Export poster.pptx --outdir output\u002F\n```\n\n### Via Python subprocess\n\n```python\nimport subprocess\nimport os\n\ndef export_to_pdf(pptx_path: str, output_dir: str = \".\") -> str:\n    \"\"\"Convert .pptx to PDF using LibreOffice.\"\"\"\n    os.makedirs(output_dir, exist_ok=True)\n    result = subprocess.run(\n        [\"libreoffice\", \"--headless\", \"--convert-to\", \"pdf\",\n         pptx_path, \"--outdir\", output_dir],\n        capture_output=True, text=True\n    )\n    if result.returncode != 0:\n        raise RuntimeError(f\"LibreOffice conversion failed:\\n{result.stderr}\")\n\n    pdf_name = os.path.splitext(os.path.basename(pptx_path))[0] + \".pdf\"\n    pdf_path = os.path.join(output_dir, pdf_name)\n    print(f\"[OK] PDF exported: {pdf_path}\")\n    return pdf_path\n```\n\n---\n\n## Verification Checklist\n\nBefore delivering the poster:\n\n- [ ] Title, authors, affiliations render correctly in header\n- [ ] All sections have content (no empty boxes)\n- [ ] All referenced image files exist and load without warnings\n- [ ] Text is not clipped or overflowing section boxes (check at 100% zoom)\n- [ ] Font sizes are legible at the target print size (≥18pt for body, ≥24pt for section headers)\n- [ ] Color scheme is consistent throughout\n- [ ] .pptx opens correctly in both PowerPoint and LibreOffice\n- [ ] PDF export renders without distortion\n\n---\n\n## Common Issues and Fixes\n\n| Problem | Likely cause | Fix |\n|---------|-------------|-----|\n| Text overflows section box | Font size too large \u002F too many lines | Reduce font size or split into two sections |\n| Image not inserted | File path wrong or file missing | Check `os.path.exists(path)` before calling `add_image` |\n| Wrong poster size | `slide_width`\u002F`slide_height` set in inches, not EMUs | Use `Cm()` or `Inches()` wrappers, not raw integers |\n| Logo appears stretched | Width and height both specified with wrong aspect ratio | Set only `width=` and let python-pptx auto-compute height |\n| PDF looks different from .pptx | Font not installed on LibreOffice machine | Embed fonts or use system fonts (Calibri → Liberation Sans) |\n| Columns misaligned | Arithmetic error in column left\u002Fwidth calculations | Print all `left`, `top`, `width`, `height` values and verify sum |\n\n---\n\n## Integration with Scientific Schematics\n\nFor high-quality figures to embed in the poster, use the `scientific-schematics` skill before generating the poster:\n\n```bash\n# Generate workflow diagram for Methods section\npython \u003Cpath-to-scientific-schematics-skill>\u002Fscripts\u002Fgenerate_schematic.py \\\n  \"Three-stream CNN architecture: MRI encoder, PET encoder, CSF encoder feeding into cross-modal attention fusion with final classification layer\" \\\n  -o figures\u002Farchitecture.png\n\n# Generate results figure\npython \u003Cpath-to-scientific-schematics-skill>\u002Fscripts\u002Fgenerate_schematic.py \\\n  \"ROC curves for three-class neuroimaging classification showing AD vs CN AUC 0.97, MCI vs CN AUC 0.89\" \\\n  -o figures\u002Froc_curves.png\n```\n\nThen pass the generated file paths as `figure1_path`, `figure2_path`, or `methods_figure_path` arguments to the poster builder.\n\n---\n\n## File Naming Conventions\n\n```\nposters\u002F\n└── YYYYMMDD_\u003Cshort_title>\u002F\n    ├── poster.pptx          # Primary deliverable\n    ├── poster.pdf           # PDF export\n    ├── generate_poster.py   # Generation script (reproducible)\n    └── figures\u002F             # Embedded images\n        ├── fig1_results.png\n        ├── fig2_attention.png\n        └── fig3_architecture.png\n```\n",{"name":5,"license":24,"version":25,"metadata":26,"description":7,"allowed-tools":28},"MIT license","1.0.0",{"skill-author":27},"K-Dense Inc.","Read Write Bash","master","63f17866001c5ca854bf2fa0b678ce277133de5b","skills\u002Fawesome-skills\u002Fposter-presentation",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill poster-presentation",{"tool":45,"command":46},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill poster-presentation",{"tool":48,"command":49},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill poster-presentation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Fposter-presentation\u002FSKILL.md",true,[],[54,62,69,76,83,90],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":61},"01M7DXW9N826PKXK174PVW3038","serpmaven","Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":61},"01M7DXVHSTWDV65475QEQ915M7","revnu-landing-page-audit","Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: \"audit my landing page\", \"why isn't this page converting\", \"review my homepage\", \"my ads get clicks but no signups\", \"people bounce from the pricing page\", \"CRO review\", \"improve conversion rate\", \"is my hero section clear\", \"roast my landing page\", \"rewrite my headline\", \"what's wrong with this page\", \"landing page feedback\", \"make the signup page convert better\". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\u002FSKILL.md",[],[],{"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":61},"01M7DXV8X2D7B3VTD4HHYYHTGR","revnu-growth-context","Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents\u002Frevnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says \"set up our marketing context\", \"who is our ideal customer\", \"write our ICP\", \"describe the product for marketing\", \"positioning doc\", \"what's our brand voice\", \"remember this about our customers\", \"log what we tried\", \"what have we learned from marketing\", \"we changed pricing, update the context\", \"update our growth notes\", \"summarize the business for the agent\", \"import my product-marketing.md\", \"start a growth doc\", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\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":61},"01M7DXV0DGJ1G0A60PAHC6J3C5","revnu-get-listed","Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: \"best X\" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says \"get us listed\", \"which directories should we submit to\", \"how do we get into best-of lists\", \"why does ChatGPT recommend competitors and not us\", \"get mentioned in AI answers\", \"submit to awesome lists\", \"get on G2\", \"where are our competitors listed\", \"pitch listicle authors\", \"find backlink opportunities\", \"launch directories\", \"get into roundups\", \"Product Hunt alternatives\", \"where should we be listed\", \"get cited by Perplexity\". Never submits, pays or posts without a yes. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\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":61},"01M7DXTSPMGT9D6DSS0HP9BSTA","revnu-ai-readiness-audit","Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks \"is my site ready for AI search\", \"audit my site for AI answers\", \"AEO audit\", \"GEO audit\", \"why doesn't ChatGPT quote our pricing\", \"make our pages citable by AI\", \"do I need llms.txt\", \"does schema help with ChatGPT\", \"check our structured data\", \"is our content visible without JavaScript\", \"AI SEO audit\", \"optimize our homepage for AI answers\", \"LLM SEO check\", \"why does AI get our product wrong\", \"fix our site for AI Overviews\". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\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":61},"01M7DXSZHCVTRS620GC3S97JZV","proxy-troubleshooting","Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]