原稿の主張と図の役割を頁ごとに整理し、選んだ書式を全頁へ引き継ぐ画像スライドと話者ノートを作る。
seaslides-html-slides-skill
AI-driven HTML presentation generation system. Converts source documents (PDF/DOCX/URL/Markdown) into browser-ready HTML slide decks and exports them to SVG, PNG, and native PPTX through multi-role collaboration. Use this skill when the user requests HTML slides, a web presentation, a browser-editable or WYSIWYG-friendly deck, horizontal swipe slides, or document-to-slides work that explicitly requires HTML output. Trigger phrases include "html slides", "html presentation", "web slides", "make html deck", "html ppt", "horizontal swipe deck", "浏览器幻灯片", "HTML 演示文稿", or mentions "seaslides-html-slides-skill".
日本語の概要は準備中です。原文の説明を表示しています。
実行スコア 未検証
インストール方法を見る含まれるファイル(143)
- SKILL.md14.6 KB
- references/ai-image-comparison/_index.md4.7 KB
- references/ai-image-comparison/README.md1.7 KB
- references/artifact-ownership.md3.1 KB
- references/checklist.md12.7 KB
- references/components.md19.5 KB
- references/design-guide.md18.6 KB
- references/executors/academic.md8.6 KB
- references/executors/base.md8.5 KB
- references/executors/canvas.md16.4 KB
- references/executors/consultant-top.md9.8 KB
- references/executors/consultant.md8.0 KB
- references/executors/general.md6.7 KB
- references/image-base.md5.0 KB
- references/image-generator.md14.8 KB
- references/image-layout-patterns.md28.2 KB
- references/image-renderings/_index.md4.4 KB
- references/image-renderings/3d-render.md3.0 KB
- references/image-renderings/abstract-geometric.md2.8 KB
- references/image-renderings/collage-editorial.md3.1 KB
- references/image-renderings/data-viz.md2.9 KB
- references/image-renderings/editorial-photo.md2.9 KB
- references/image-renderings/flat-vector.md2.7 KB
- references/image-renderings/ink-sketch.md2.8 KB
- references/image-renderings/watercolor.md3.1 KB
- references/image-searcher.md5.7 KB
- references/layouts.md14.4 KB
- references/scenarios/cv.md28.8 KB
- references/scenarios/poster.md24.7 KB
- references/scenarios/social-cover.md49.1 KB
- references/shared-standards-extended.md22.8 KB
- references/shared-standards.md16.8 KB
- references/strategist.md13.2 KB
- references/template-designer.md40.0 KB
- references/visual-review.md20.4 KB
- requirements.txt3.7 KB
- scripts/analyze_images.py15.8 KB
- scripts/assemble.py5.9 KB
- scripts/batch_validate.py6.7 KB
- scripts/config.py22.1 KB
- scripts/docs_html/browser_dom_export.md5.9 KB
- scripts/docs/conversion.md5.3 KB
- scripts/docs/image.md6.1 KB
- scripts/docs/project.md4.2 KB
- scripts/docs/troubleshooting.md10.9 KB
- scripts/html_compiler.py52.6 KB
- scripts/html_to_pptx.py9.5 KB
- scripts/html_to_svg/browser_dom_audit.mjs45.3 KB
- scripts/html_to_svg/browser_dom_to_svg.mjs57.2 KB
- scripts/html_to_svg/browser_html_to_png.mjs16.8 KB
- scripts/html_to_svg/browser_svg_to_pdf.mjs5.5 KB
- scripts/html_to_svg/browser_svg_to_png.mjs5.3 KB
- scripts/html_to_svg/chart_renderer.mjs18.2 KB
- scripts/html_to_svg/package-lock.json48.3 KB
- scripts/html_to_svg/package.json655 B
- scripts/html_to_svg/test-fixtures/dom-audit-decorative-media.html1.0 KB
- scripts/html_to_svg/test-fixtures/dom-audit-noise.html1.1 KB
- scripts/html_to_svg/test-fixtures/dom-audit-text-contracts.html1.0 KB
- scripts/html_to_svg/test-fixtures/runtime-contract-smoke.mjs3.1 KB
- scripts/image_backends/__init__.py57 B
- scripts/image_backends/backend_bfl.py5.6 KB
- scripts/image_backends/backend_common.py7.2 KB
- scripts/image_backends/backend_fal.py4.1 KB
- scripts/image_backends/backend_gemini.py8.6 KB
- scripts/image_backends/backend_ideogram.py4.8 KB
- scripts/image_backends/backend_minimax.py6.7 KB
- scripts/image_backends/backend_modelscope.py5.2 KB
- scripts/image_backends/backend_openai.py11.3 KB
- scripts/image_backends/backend_openrouter.py6.9 KB
- scripts/image_backends/backend_qwen.py6.2 KB
- scripts/image_backends/backend_replicate.py5.8 KB
- scripts/image_backends/backend_siliconflow.py5.6 KB
- scripts/image_backends/backend_stability.py4.8 KB
- scripts/image_backends/backend_volcengine.py5.9 KB
- scripts/image_backends/backend_zhipu.py5.8 KB
- scripts/image_gen.py25.6 KB
- scripts/image_search.py25.7 KB
- scripts/image_sources/__init__.py323 B
- scripts/image_sources/provider_common.py16.1 KB
- scripts/image_sources/provider_openverse.py3.8 KB
- scripts/image_sources/provider_pexels.py3.7 KB
- scripts/image_sources/provider_pixabay.py3.8 KB
- scripts/image_sources/provider_wikimedia.py6.2 KB
- scripts/project_manager.py30.6 KB
- scripts/project_utils.py15.5 KB
- scripts/README.md4.3 KB
- scripts/runtime_environment.py3.5 KB
- scripts/runtime/deck_runtime.js19.8 KB
- scripts/source_inventory.py6.4 KB
- scripts/source_to_md/conversion_receipt.py14.0 KB
- scripts/source_to_md/doc_to_md.py24.8 KB
- scripts/source_to_md/excel_to_md.py16.2 KB
- scripts/source_to_md/pdf_to_md.py55.9 KB
- scripts/source_to_md/ppt_to_md.py14.0 KB
- scripts/source_to_md/web_to_md.py32.3 KB
- scripts/svg_finalize/__init__.py471 B
- scripts/svg_finalize/align_embed_images.py14.1 KB
- scripts/svg_finalize/crop_images.py11.5 KB
- scripts/svg_finalize/embed_icons.py12.8 KB
- scripts/svg_finalize/embed_images.py9.5 KB
- scripts/svg_finalize/fix_image_aspect.py13.4 KB
- scripts/svg_finalize/flatten_tspan.py16.4 KB
- scripts/svg_finalize/svg_rect_to_path.py10.4 KB
- scripts/svg_to_pptx.py449 B
- scripts/svg_to_pptx/__init__.py465 B
- scripts/svg_to_pptx/animation_config.py8.2 KB
- scripts/svg_to_pptx/drawingml_context.py6.3 KB
- scripts/svg_to_pptx/drawingml_converter.py18.4 KB
- scripts/svg_to_pptx/drawingml_elements.py62.0 KB
- scripts/svg_to_pptx/drawingml_paths.py13.5 KB
- scripts/svg_to_pptx/drawingml_styles.py21.4 KB
- scripts/svg_to_pptx/drawingml_utils.py14.9 KB
- scripts/svg_to_pptx/pptx_builder.py37.1 KB
- scripts/svg_to_pptx/pptx_cli.py22.3 KB
- scripts/svg_to_pptx/pptx_dimensions.py4.1 KB
- scripts/svg_to_pptx/pptx_discovery.py3.6 KB
- scripts/svg_to_pptx/pptx_media.py4.4 KB
- scripts/svg_to_pptx/pptx_narration.py7.2 KB
- scripts/svg_to_pptx/pptx_notes.py4.6 KB
- scripts/svg_to_pptx/pptx_slide_xml.py4.6 KB
- scripts/svg_to_pptx/tspan_flattener.py4.2 KB
- scripts/svg_to_pptx/use_expander.py4.3 KB
- scripts/tests/test_html_browser_contracts.py5.1 KB
- scripts/tests/test_html_delivery_profiles.py29.4 KB
- scripts/tests/test_html_project_tools.py14.1 KB
- scripts/tests/test_html_project_utils.py5.3 KB
- scripts/tests/test_html_scripts.py31.5 KB
- scripts/tests/test_source_conversion_receipts.py28.7 KB
- scripts/tests/test_source_receipt_validation.py8.6 KB
- scripts/validate_project.py82.6 KB
- templates/content_design_spec_reference.md8.8 KB
- templates/editorial-magazine/demo.html19.9 KB
- templates/editorial-magazine/index-template.html21.1 KB
- templates/editorial-magazine/template.css33.7 KB
- templates/editorial-magazine/theme.md18.9 KB
- templates/index.json19.8 KB
- workflows/create-presentation.md5.8 KB
- workflows/create-template.md4.9 KB
- workflows/resume-execute.md4.8 KB
- workflows/select-theme.md2.9 KB
- workflows/topic-research.md7.9 KB
- workflows/verify-charts.md4.9 KB
- workflows/visual-review.md6.6 KB
SKILL.md(原文)
インストールする前に、エージェントに与えられる指示の中身を確認できます。
SeaSlides HTML Slides Skill
Convert source material into a browser-ready HTML deck with synchronized SVG, PNG, and PPTX outputs.
Pipeline: Source -> Project -> Theme -> Strategist -> [Images] -> Executor -> Assemble -> Review -> Export
Hard Contract for Standard Slides
- Run creation phases serially and complete each gate before continuing.
- Ask at blocking decisions. In unattended mode, decide them and continue.
- Convert document sources to Markdown before planning.
- Preserve Template-Content Separation (TCS): shell in
index-template.html, reusable styling intemplate.css, semantic slides incontent.html. - Keep
<style>,<script>,<link>, event handlers, and ad hoc visual styles out of standard-slidecontent.html. - Permit inline styles only for data values on the component/property allowlist defined in
${SKILL_DIR}/references/shared-standards.md; the validator enforces the same list. - Reassemble after every content, CSS, or template change. Treat root
index.html, SVGs, both PNG routes, overview, and compiler receipts as one synchronized generation. - Pass the source gate before building, then pass the current-build visual gate before delivery. Build PPTX in that same build when it is requested.
The canonical standard-slide TCS rules live in ${SKILL_DIR}/references/shared-standards.md and ${SKILL_DIR}/scripts/validate_project.py.
Scenario Routing
Route special outputs before applying the standard-slide contract:
| Intent | Read and follow |
|---|---|
| Academic or conference poster | ${SKILL_DIR}/references/scenarios/poster.md |
| CV or resume | ${SKILL_DIR}/references/scenarios/cv.md |
| Social cover, article header, or thumbnail | ${SKILL_DIR}/references/scenarios/social-cover.md |
| Standard HTML presentation | Continue below |
Each special scenario defines its own authoring and review contract. Do not apply the standard-slide TCS validator or standard slide-count/rhythm rules unless that scenario explicitly requests them.
Match the user's language. Keep the structural headings in content_design_spec.md stable while writing values in the user's language when appropriate.
For 25+ slide decks, use ${SKILL_DIR}/workflows/resume-execute.md to split planning and execution across sessions.
Standard-Slide Architecture
| File | Responsibility |
|---|---|
index-template.html | Browser shell, navigation, external libraries, {{CONTENT}} placeholder |
template.css | Canvas metadata, theme tokens, layout and component classes |
content.html | Semantic <section class="slide ..."> blocks and speaker notes |
html_compiler.py --all atomically assembles root index.html and produces output/svgs/, output/pngs/, output/browser_pngs/, output/overview.png, output/slides.pdf, output/dom-audit.json, output/render-fidelity.json, and output/compile-manifest.json. Add --include-pptx when PowerPoint is required; it produces output/slides.pptx in the same build and receipt.
Resource Map
Load references only when entering the relevant phase.
| Phase or need | Resource |
|---|---|
| Full creation workflow | ${SKILL_DIR}/workflows/create-presentation.md |
| Theme selection | ${SKILL_DIR}/workflows/select-theme.md |
| New theme creation | ${SKILL_DIR}/workflows/create-template.md |
| Topic-only research | ${SKILL_DIR}/workflows/topic-research.md |
| Chart calibration | ${SKILL_DIR}/workflows/verify-charts.md |
| Visual review | ${SKILL_DIR}/workflows/visual-review.md |
| Strategist role | ${SKILL_DIR}/references/strategist.md |
| Standard HTML/TCS contract | ${SKILL_DIR}/references/shared-standards.md |
| Executor fundamentals | ${SKILL_DIR}/references/executors/base.md |
| General / consulting / MBB / academic style | ${SKILL_DIR}/references/executors/<style>.md |
| Components and layouts | ${SKILL_DIR}/references/components.md, ${SKILL_DIR}/references/layouts.md |
| Design heuristics | ${SKILL_DIR}/references/design-guide.md |
| Image dispatch and layout | ${SKILL_DIR}/references/image-base.md, ${SKILL_DIR}/references/image-layout-patterns.md |
| Review rubric and issue severity | ${SKILL_DIR}/references/visual-review.md, ${SKILL_DIR}/references/checklist.md |
| Artifact and visual issue ownership | ${SKILL_DIR}/references/artifact-ownership.md |
| Theme creation internals | ${SKILL_DIR}/references/template-designer.md |
| Browser DOM export | ${SKILL_DIR}/scripts/docs_html/browser_dom_export.md |
| Content plan template | ${SKILL_DIR}/templates/content_design_spec_reference.md |
Use ${SKILL_DIR}/templates/index.json as the only theme catalog. Do not maintain a second theme list in this entry file.
Workflow
Step 1: Process Sources
Gate: Source material or a topic is available.
If only a topic is provided, follow ${SKILL_DIR}/workflows/topic-research.md or create a source brief before continuing.
| Input | Command |
|---|---|
python3 ${SKILL_DIR}/scripts/source_to_md/pdf_to_md.py <file> --images filtered | |
| DOCX / EPUB / HTML / LaTeX / RST | python3 ${SKILL_DIR}/scripts/source_to_md/doc_to_md.py <file> |
| PPTX / PPSX | python3 ${SKILL_DIR}/scripts/source_to_md/ppt_to_md.py <file> |
| Excel | python3 ${SKILL_DIR}/scripts/source_to_md/excel_to_md.py <file> |
| Web page | python3 ${SKILL_DIR}/scripts/source_to_md/web_to_md.py <url> |
| Markdown / text | Read directly |
Do not proceed with only an unread raw document when a converter is available.
Step 2: Initialize the Project
Gate: Readable source content exists.
python3 ${SKILL_DIR}/scripts/project_manager.py init <project_name>
python3 ${SKILL_DIR}/scripts/project_manager.py import-sources <project_path> <source_files...> --copy
Use --exact-name only when a deterministic, date-free directory name is needed (for example, a reproducible benchmark); normal projects retain the dated suffix.
Use --move only when explicitly requested. Copy extracted images into assets/ and import the converted Markdown.
Step 3: Select a Theme
Gate: Project directory exists.
Follow ${SKILL_DIR}/workflows/select-theme.md.
- Read
${SKILL_DIR}/templates/index.json. - Use a user-named theme directly; otherwise rank themes by metadata such as tags,
bestFor, style, audience, and content needs. - Present a concise recommendation and wait unless unattended mode is active.
- Do not use a fixed default theme merely because the request is ambiguous; choose the best-supported candidate from the catalog.
Copy the selected theme files:
cp ${SKILL_DIR}/templates/<theme>/index-template.html <project_path>/
cp ${SKILL_DIR}/templates/<theme>/template.css <project_path>/
Read the selected theme's theme.md and demo.html. Use their actual CSS vocabulary and composition patterns; do not copy irrelevant sample content or decorative details mechanically. A demo may contain theme-authoring geometry: never copy a non-data inline style into standard-slide content.html; translate reusable treatment into template.css classes.
Step 4: Produce the Content Design Spec
Gate: Theme is selected and understood.
Read the Strategist and shared standards. Present the nine decisions as one bundle and wait unless unattended mode is active:
- Page format
- Page-count range
- Target audience
- Style objective
- Color scheme
- Typography plan
- Image approach
- Slide rhythm plan
- Per-slide component/layout assignment
For standard slides, use canvas metadata in the first :root block of template.css:
:root {
--slide-width: 1280px;
--slide-height: 720px;
}
Use 960x720 for 4:3. Scenario documents own non-slide canvas formats.
If user images exist, run:
python3 ${SKILL_DIR}/scripts/analyze_images.py <project_path>/assets
Write content_design_spec.md from ${SKILL_DIR}/templates/content_design_spec_reference.md, including project settings, a catalog theme ID, narrative, per-slide content/layout decisions, image decisions, colors, and typography. Record intentionally excluded assets.
Step 5: Acquire Images When Needed
Gate: The design spec requests generated or searched images.
Read ${SKILL_DIR}/references/image-base.md, then the relevant image workflow. Generate/search assets, verify files, and match image shape to the intended slot. Skip this phase when no new images are needed.
Step 6: Author content.html
Gate: Design spec, selected theme, and required assets are ready.
Read executor base, exactly one style executor, shared standards, template.css, the selected theme.md, and demo.html.
Author standard slides with these constraints:
- Use
<section class="slide [mode] [modifier]" data-notes="...">for every slide. - Every slide must resolve to one valid mode: give it an explicit
light,dark,hero light, orhero darkclass; a selected theme's documented default mode intheme.mdis also valid. Do not rely on an undocumented CSS fallback. - Use only classes defined by the selected theme or required external libraries.
- Put reusable styling in
template.css; use only canonical data-value inline styles from shared standards. - Keep every slide visible in the settled export state without hover, timer, scroll, or active-carousel dependencies.
- Use action titles when they clarify the conclusion; allow short thematic titles for covers and dividers.
- Use relevant or user-required images and meaningful
alttext. Do not insert unrelated assets merely to exhaust the folder. - Keep TODOs, diagnostics, raw markup, component labels, and accidental source text out of rendered slides.
- Count all title, divider, hero, focus, and appendix slides within the requested range.
- Use
\(LaTeX\)for inline MathJax formulas and\[LaTeX\]for display formulas.
Treat layout variety, component variety, dark/light alternation, and hero cadence as design heuristics. Use them when they improve hierarchy and pacing; allow deliberate repetition for comparisons, timelines, tutorials, and other content that benefits from a stable visual grammar.
Step 7: Assemble, Review, Validate, and Export
Gate: content.html, template.css, and index-template.html exist.
7.1 Source Gate
Before building, validate the project source and TCS contract only:
python3 ${SKILL_DIR}/scripts/validate_project.py <project_path> --source-only --profile standard-project
Fix source/TCS errors before compiling. This is a project-directory gate; do not use the legacy single-file invocation for standard-slide delivery.
7.2 Assemble and Render
python3 ${SKILL_DIR}/scripts/html_compiler.py <project_path> --all
Require root index.html, matching slide counts in output/svgs/, output/pngs/, and output/browser_pngs/, plus output/overview.png, output/dom-audit.json, output/render-fidelity.json, and output/compile-manifest.json. Rerun after every source change. Diagnose compilation failures and retry up to five times.
dom-audit.json is the browser-layout truth: it records settled-DOM blockers
found before conversion plus theme-opted-in composition telemetry/review items.
Those composition measurements support rather than replace visual judgment.
render-fidelity.json records review-only differences between browser PNGs and
SVG-route PNGs. compile-manifest.json is the current-source receipt: it
fingerprints inputs, toolchain, assembled HTML, and published artifacts.
7.3 Perform Visual Review
Follow ${SKILL_DIR}/workflows/visual-review.md and ${SKILL_DIR}/references/visual-review.md.
- Inspect
output/overview.png, then every browser-rendered PNG at a projection-like scale; the overview routes attention but is not a substitute for page review. - Use matching
output/pngs/andrender-fidelity.jsononly to diagnose conversion-route differences. - For every page, identify its vertical mode (centered cluster, top-to-bottom, split anchors, image hero, or intentional breathing). Fix content pages stranded at the top even when a footer makes the raw content span look full.
- Fix blocking visual problems and pronounced composition/readability defects, re-run the source gate, rebuild with
--all, and repeat up to three visual iterations.
Evaluate rhythm and diversity in context. Do not change a clear repeated layout solely to satisfy a numeric quota, and do not add filler merely to consume whitespace.
7.4 Final Visual Gate
python3 ${SKILL_DIR}/scripts/validate_project.py <project_path> --require-build --artifact-profile visual
This gate requires a current compile-manifest.json, all visual artifacts, and zero browser DOM-audit blockers. Fix hard errors such as stale/missing artifacts, TCS violations, missing files, broken classes/references, invalid structure, and DOM blockers. Treat render-fidelity and diversity/density findings as review prompts, not automatic failures.
7.5 Export PPTX
python3 ${SKILL_DIR}/scripts/html_compiler.py <project_path> --all --include-pptx
python3 ${SKILL_DIR}/scripts/validate_project.py <project_path> --require-build --artifact-profile delivery
When PPTX is requested, use this same-build delivery sequence instead of a later standalone --format pptx export. Deliver root index.html, visual artifacts, receipts, and output/slides.pptx.
Editing an Existing Deck
- Read
content.html,template.css,index-template.html, theme documentation, and current rendered output. - Edit semantic content in
content.html; edit reusable presentation rules intemplate.css; preserve TCS. - Re-run the source gate, rebuild with
--all, visually review affected pages, and pass the final visual gate. When PPTX is requested, rebuild with--all --include-pptxand pass the delivery profile. - Re-run planning only when the request changes the narrative, theme, or deck structure.
Dependencies
pip install -r ${SKILL_DIR}/requirements.txt
cd ${SKILL_DIR}/scripts/html_to_svg
npm install
npx playwright install chromium
Open root index.html for local preview, but use the compiler's synchronized outputs for final review.
レビュー
まだレビューはありません。使ってみた感想をお寄せください。
コメント
ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。
まだコメントはありません。最初のコメントを書いてみませんか。
同じリポジトリのスキル
Convert literature reviews, paper folders, thesis drafts, journal-style reports, or research outlines into rigorous academic slide decks and review artifacts. Use when Codex must create, rebuild, or polish PPTX presentations from scholarly sources while preserving academic logic, citation-aware image/formula handling, editable layouts, figure explanations, template fidelity, and export-based visual QA.
日本語の概要は準備中です。原文の説明を表示しています。
既存PPTXの書式・配置を抽出し、planとnative編集操作からPowerPointを生成・検査する。
読者と目的から構成・版式を決め、確認を挟みながら、編集できる図形と文字のPPTXにする。
aham-ppt
無料全流程AI制作PPT演示文稿技能,克制专业、风格可选 A/B/C 三档(Aham UI v6.1 · Office 轨 · PPT)。 当用户说"帮我做PPT""做演示文稿""做一个汇报""根据这份资料做PPT" "做客户方案PPT""制作幻灯片"时立即触发。即使只有一句话需求也触发。 八阶段模块化流程:规范加载→材料解析→论点提炼→叙事骨架→大纲版式→样稿确认→逐页设计→质检交付。 内置能力自适应教练机制,无论用户专业水平高低,均引导至及格以上输出。 注意:本技能用于 PowerPoint / pptx 输出;SVG/HTML 版本见 ppt-svg 技能。
日本語の概要は準備中です。原文の説明を表示しています。
原典のReact scene kitを実scaffoldし、安定layoutIdの共通canvasでentityが移動・morphする日本語ブラウザ資料を作る。