report-to-google-slides

作者: openai

狹義轉換技能。僅在使用者明確要求將現有HTML分析報告轉換為原生Google Slides簡報時調用。

npx skills add https://github.com/openai/role-specific-plugins --skill report-to-google-slides

Report To Google Slides

Use this skill only when the user explicitly has an existing HTML analytics report and wants a Google Slides deliverable. The output should be a deck, not a pasted report. A stakeholder skimming the slides should understand the answer, evidence, caveats, and recommended follow-up without opening the source report.

This skill consumes an HTML report. It does not convert a live MCP app report directly; if only an MCP app report exists, build an HTML report from the same source evidence as a separate report delivery mode first.

Workflow

  1. Resolve the local HTML report.

    Use an absolute file path. If the user provides a remote report, retrieve it outside this skill first. If the local file is a sign-in page, redirect page, or very small stub, stop and obtain the real report before continuing.

  2. Run the helper.

    python3 <REPORT_TO_GOOGLE_SLIDES_SKILL_DIR>/scripts/report_to_google_slides.py \
      <LOCAL_HTML_REPORT_PATH> \
      --out-dir /tmp/report_to_google_slides
    
  3. Inspect local outputs.

    Required outputs:

    • deck.pptx: editable local PowerPoint file
    • manifest.json: parsed source inventory and coverage counts
    • deck_plan.json: slide-by-slide plan with named elements
    • preflight_checks.json: local quality checks and pass/fail status
    • assets/: rendered chart images

    Do not import the PPTX until preflight_checks.json has status: "passed". Then run unzip -t <out-dir>/deck.pptx.

  4. Import and verify in Google Slides.

    Import deck.pptx with mcp__codex_apps__google_drive._import_presentation using upload_mode="native_google_slides". Verify the imported deck with _get_presentation_outline and _get_slide_thumbnail for every slide when possible. At minimum, inspect the cover, one chart slide, one table slide, and the caveats/sources slides.

  5. Repair before handoff.

    If thumbnails show clipped text, missing charts, low contrast, blank images, or awkward sizing, revise the helper output or source assumptions and regenerate before handing off the deck URL.

  6. Hand off the deck.

    Return the Google Slides URL and, when useful, the local PPTX path or source HTML path. Keep routine check, preflight, thumbnail-inspection, and import-check details in support artifacts. Do not list internal checks in the user-facing handoff unless a check failed, was unavailable, or produced a user-relevant caveat.

Standards

  • Preserve the report's decision-critical information: headline claim, executive summary, major findings, metric definitions, material charts, decision-critical tables, recommendations, implications, caveats, assumptions, freshness notes, and source/provenance notes.
  • Translate report prose into slide-native communication. Lead with the takeaway, use one main idea per slide, and put supporting detail in concise callouts, bullets, tables, chart annotations, or speaker notes.
  • Tighten copy before shrinking fonts.
  • Keep gross metric reads, net/incremental reads, causal claims, and caveats visibly separated when the source report distinguishes those lenses.
  • Use editable text and native PPTX tables wherever practical. Use native PPTX bullets; do not fake bullets with typed dashes.
  • Preserve source charts as evidence images. Do not screenshot the whole HTML report or paste whole report sections.
  • Support self-contained Recharts HTML reports whose chart evidence remains available as same-data inline SVG/table fallbacks or embedded images; the helper renders those into local chart evidence images before building the deck.
  • Use one chart per evidence slide unless the report has a stronger grouped comparison.
  • Keep table slides legible. If a full table is too dense, keep the main comparison in the deck and move extra detail to speaker notes or source slides.
  • Source notes should be visible but quiet.

Visual System

The helper derives colors and hierarchy from the HTML report CSS and chart palette, then applies a restrained analytics deck layout. It does not follow external deck files or company-specific branding.

來自 openai 的更多技能

user-context
openai
載入或管理資料分析插件的持久性來源路由偏好設定、入門邏輯、設定進度以及語義層註冊表。
official
notion-research-documentation
openai
研究Notion內容,並將其整合為結構化的簡報、報告或附有引用的比較分析。透過精準查詢搜尋並擷取Notion頁面,然後按主題組織發現,並附上內文來源引用及參考文獻章節。根據範圍與使用者目標,從四種輸出格式(快速簡報、研究摘要、比較分析、綜合報告)中選擇。使用內建範本建立與更新Notion頁面;直接連結來源,並在新資訊到來時追蹤變更。
official
rcsb-pdb-skill
openai
提交精簡的RCSB PDB請求以獲取核心元數據、Search API查詢及FASTA下載。當用戶需要簡潔的RCSB摘要時使用;保存原始JSON或…
official
pdf
openai
PDF 讀取、建立與驗證,支援視覺化渲染與程式化生成。使用 Poppler(pdftoppm)將 PDF 頁面渲染為 PNG,以便在交付前檢查版面、間距與排版。透過 reportlab 程式化生成 PDF,確保格式可靠;使用 pdfplumber 或 pypdf 提取文字與元資料。執行品質標準:無文字裁切、元素重疊、表格破損或渲染瑕疵;僅使用 ASCII 連字號,引用格式需具可讀性。使用...
official
test-coverage-improver
openai
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose…
official
playwright
openai
終端驅動的瀏覽器自動化,具備元素快照與互動式UI工作流程。透過playwright-cli包裝腳本運作(需npx),支援無頭模式與有頭模式以進行視覺化除錯。核心流程:開啟頁面、擷取快照以取得穩定元素參照、使用參照進行互動、在導航或DOM變更後重新擷取快照。包含表單填寫、點擊、輸入、多分頁管理、螢幕截圖/PDF擷取,以及流程除錯的軌跡記錄。元素參照(例如e3、e15)...
official
ukb-topmed-phewas-skill
openai
接受rsID、GRCh37或GRCh38輸入,解析為所需的GRCh38查詢,以獲取單一變異的簡潔UKB-TOPMed PheWAS摘要。當需要…時使用。
official
code-review-context
openai
模型可見上下文
official