report-to-google-slides

작성자: openai

좁은 변환 스킬입니다. 사용자가 기존 HTML 분석 보고서를 네이티브 Google Slides 데크로 변환하도록 명시적으로 요청할 때만 호출하세요.

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.

openai의 다른 스킬

release
openai
커밋된 버전을 올리고, 이를 반영하고, 병합된 커밋에 태그를 단 후, Burrito 릴리스 워크플로우를 검증하여 Symphony 릴리스를 진행합니다. 다음과 같이 요청받았을 때 사용합니다…
signing-entitlements
openai
macOS 앱의 서명, 자격, 강화된 런타임 및 Gatekeeper 문제를 검사합니다. 코드 서명 실패, 누락된 자격 등을 진단하라는 요청을 받을 때 사용하세요.
building-ai-agent-on-cloudflare
openai
Cloudflare에서 Agents SDK를 사용하여 상태 관리, 실시간 WebSockets, 예약 작업, 도구 통합, 채팅을 통해 AI 에이전트를 구축합니다…
epigraphdb-skill
openai
온톨로지, 문헌, MR, 유전자-약물 및 지원 경로 증거에 대한 간결한 EpiGraphDB API 요청을 제출합니다. 사용자가 간결한 EpiGraphDB 요약을 원할 때 사용하세요.
runtime-behavior-probe
openai
런타임 동작 조사를 계획하고 실행하며, 임시 프로브 스크립트, 검증 매트릭스, 상태 제어, 결과 우선 보고서를 사용합니다. 다음 경우에만 사용하세요…
deep-security-scan
openai
사용자가 심층적이고, 철저하며, 다중 패스 또는 변동성을 줄이는 저장소 전체 또는 범위가 지정된 경로의 Codex Security 스캔을 요청할 때 사용합니다. 반복적으로 독립적인…
define-security-policy
openai
저장소 또는 구성 요소에 대한 SECURITY.md 지침을 정의, 검토 또는 업데이트합니다. 사용자가 Codex Security가 검토해야 할 대상과 범위를 벗어나는 항목을 명확히 하려 할 때 사용합니다…
validation
openai
Codex가 보안 스캔의 검증 단계에 이미 있거나 사용자가 하나 이상의 후보 보안 결과를 판별하도록 명시적으로 요청할 때 사용합니다…