본문으로 건너뛰기
cccskills
무료GitHub에 공개

document-authoring

Create and inspect charts, PDFs, editable Word documents, spreadsheets, and browser presentations from supplied material. The skill selects tools for each format, checks content and layout, and delivers files or opens presentations with animation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Create, inspect and deliver charts, PDFs, Word documents and spreadsheets, and open animated browser presentations.

연동 도구Word
설치 방법 보기

이럴 때 유용합니다

  • Create charts from source data
  • Prepare a PDF report with figures
  • Create an editable Word document
  • Open an animated browser presentation
  • Create and inspect a spreadsheet

포함된 파일(1)

  • SKILL.md6.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Document Authoring

  1. Establish the requested format, audience, content and acceptance criteria from the brief and supplied references. Reuse source material; for complex work, track criteria and verification evidence in plan details.
  2. Choose the creation tool based on the requested output:
    • Charts: use document.echarts.render with one named entry per requested chart and native ECharts JSON options. Ground the values in supplied/retrieved data, label units, and select only the requested image formats. Each chart becomes a separate SVG/PNG artifact. Use both formats when a vector document figure and raster preview are useful. Inspect a PNG preview and fix clipping or misleading axes before delivering it. Do not use image-generation models to invent or redraw quantitative charts.
    • Presentations: use document.slidev.create for an editable project, author slides.md and style.css with the file tool, and place selected chart/image assets in public/. Treat the scaffold as editable: owner choices for theme, layout, colors, typography, icons and animation override all defaults. Replace scaffold styles and components when needed; ensure additional themes have compatible installed dependencies. Use local Lucide icons and coherent cover/section/content layouts. Default to fully visible slides and a simple transition: fade between them. Animate mechanisms inside the slide automatically while it is active: moving evidence along a flow, state changes, process cycles or grounded chart evolution. Use CSS or v-motion with a static reduced-motion fallback. Avoid generic text/panel entrance and exit effects. Add click-triggered reveals (v-click or click motion variants) and elaborate slide transitions only when the owner explicitly requests them. Ground technical claims in retrieved context/source and label illustrative data. Batch independent grounding reads and author related files together. Use fenced code or HTML-escaped <pre v-pre><code> for literal examples; keep Vue markup balanced. Run inspect, then check; during repairs select affected options.slides. Targeted success has complete=false and cannot establish full-deck coverage. Run the default full check on the final source and require scope=full, complete=true and ok=true. Batch independent checks/previews and requested exports once source is stable; never edit files while those operations are reading them. Reuse current-run evidence and successful results while relevant source/assets are unchanged. Preview early/late motion frames and, only for requested staged reveals, initial/final click states; a passing check alone does not establish visual or animation quality. Finish with present to start/reuse a managed native Slidev server and open the deck in the host’s default browser. Return its audience and presenter links, Space/Right/Left navigation and f fullscreen control. Verify opening with the browser tool; if browserOpened=false, explain the reported issue and host-local URL scope. Use Satellite for device-side presentation when Leon runs remotely and ensure the project is on that device. Keep the session until the owner finishes, then stop its sessionId. Export web/PDF/PNG/PPTX downloads only when requested; opening a deck should not require extracting files or running commands. A web ZIP includes serve.mjs: extract and run node serve.mjs, then open its localhost URL; it can also be hosted as a static site. PDF/PNG and PowerPoint exports capture states rather than native browser motion. Normal PPTX contains slide images; editable PPTX may rasterize complex elements and needs fidelity review. Shared web decks omit notes by default; an optional source ZIP (includeSource=true) always contains them; omit that archive unless requested.
    • PDF: write a local .typ source with the file tool, then call document.typst.compile. Keep the source and selected assets together in a project directory. Use the smallest rootPath containing that project. Built-in/local assets require no generation-provider account or package download.
    • Editable Word: use document.document.create with format=docx. Typst does not export DOCX.
    • SVG/PNG: compile Typst with the requested format. Each selected page becomes an image artifact. For a standalone figure, set the page dimensions to fit the figure rather than exporting a full report page.
    • Plain text, CSV, Markdown and source files: use existing file writing.
    • Hosted generation or Office formats requiring a provider: inspect document.document.capabilities, then use generate with the configured defaults. Reserve generateWithModel for an explicitly owner-requested provider/model.

If hosted generation returns selection_required, ask the owner to select a provider or use local Typst/DOCX creation when it satisfies the request. Save a choice with configure only if asked to remember it.

  1. Use readable typography, consistent headings and generous spacing. Typst source supports tables, lists, equations, references and figures; use these instead of flattening everything into paragraphs. Generate chart assets with echarts.render or reuse supplied SVG/PNG assets. For PDFs, copy selected assets into the Typst project with the shell tool, embed them with image inside figure, and add a useful caption. For DOCX, pass each selected absolute artifact path in content.sections[].images with caption and altText; the writer preserves proportions and includes PNG fallbacks for SVG. Images follow the section's paragraphs, so use separate sections to position figures between text blocks. Keep chart values grounded in supplied or retrieved data. Use typst.listFonts before choosing multilingual fonts, and provide local fontPaths when needed. Inspect compiler diagnostics and fix unknown fonts or layout warnings; do not silently produce missing glyphs. Preview-package imports may download missing packages, so avoid them for offline work.
  2. Inspect final content against the sources and acceptance criteria. Render PDF pages with readPdf and compare layout with supplied references. For Word/Office files use an available renderer to inspect a PDF export; disclose when only structural/content checks were possible.
  3. Reconcile criteria with observed evidence and fix missing content or layout defects before delivery. Source or asset changes invalidate affected checks. A provider's success response alone is not a quality check; unresolved or unverified requirements remain incomplete.
  4. Generated files already have artifact references. For existing files use file_system.file.attach. Do not duplicate attachments, paste base64, or use server-local file markers as downloads.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

coding

무료

Investigate a codebase, reproduce bugs, implement requested changes, and verify the results using Leon’s file, search, and shell tools. Follow project instructions, preserve existing user changes, and report checks and unresolved issues.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Reproduce and fix a software bug
  • Implement a feature using existing project patterns
  • Check a UI against supplied references
leon-ai/leon1.8만2026년 10월 19일 업데이트

Create an MP4 tutorial from a workflow demonstrated in the actual application. Selected screenshots become annotated steps with captions, control highlights, and arrows, showing the actions performed and the verified result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Create a video explaining an app workflow
  • Show how to reach a specific setting
  • Add captions and arrows to demonstrated steps
leon-ai/leon1.8만2026년 10월 19일 업데이트

Generate images, edit photos and vector artwork, and assemble narration and supplied clips into videos. Inspect visual details, timing, motion, and audio, then deliver finished files for viewing or download.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Generate an image from a written brief
  • Edit photos and layered artwork
  • Create vector artwork
leon-ai/leon1.8만2026년 10월 19일 업데이트

leon-ai의 스킬 모두 보기

이 스킬의 문제 신고