Slide Deck Generator

Transform content into professional slide deck images. The deck is designed for reading and sharing (self-explanatory slides, logical scroll flow, social-media-friendly) rather than live presentation — that assumption drives every layout and density decision below.

User Input Tools

When this skill prompts the user, follow this tool-selection rule (priority order):

1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent.
2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
3. Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.

Concrete AskUserQuestion references below are examples — substitute the local equivalent in other runtimes.

Image Generation Tools

When this skill needs to render an image, resolve the backend in this order:

1. Current-request override — if the user names a specific backend in the current message, use it.
2. Saved preference — if EXTEND.md sets preferred_image_backend to a backend available right now, use it.
3. Auto-select (when the preference is auto, unset, or the pinned backend isn't available):
   • Codex (imagegen) — first, inspect your available-skills / tool inventory. If a skill named imagegen is listed, you are running inside Codex and MUST use it: invoke via the Skill tool with skill: "imagegen", passing the saved prompt file's content (plus output path and aspect ratio per Codex imagegen's own args). Codex imagegen is the official raster backend in that runtime and outranks any non-native skill (e.g., baoyu-imagine) unless the user has explicitly pinned a different preferred_image_backend.
   • Other runtime-native tools — if the runtime exposes a different native image tool (e.g., Hermes image_generate), use it the same way.
   • Otherwise, if exactly one non-native backend is installed (e.g., baoyu-imagine), use it.
   • Otherwise (multiple non-native backends with no runtime-native tool), ask the user once — batch with any other initial questions.
4. If none are available, tell the user and ask how to proceed.

⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation. Codex imagegen's own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do not silently emit SVG, write inline <svg> markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.

Setting preferred_image_backend: ask forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the ## Changing Preferences section below.

Prompt file requirement (hard): write each image's full, final prompt to a standalone file under prompts/ (naming: NN-slide-[slug].md) BEFORE invoking any backend. The file is the reproducibility record and lets you switch backends without regenerating prompts.

Concrete tool names (imagegen, image_generate, baoyu-imagine) above are examples — substitute the local equivalents under the same rule.

Confirmation Policy

Default behavior: confirm before generation.

• Treat explicit skill invocation, a file path, matched signals/presets, and EXTEND.md defaults as recommendation inputs only. None of them authorizes skipping confirmation.
• Do not start Step 3 or later until the user completes Step 2.
• Skip confirmation only when the current request explicitly says to do so, for example: "直接生成", "不用确认", "跳过确认", "按默认出幻灯片", or equivalent wording.
• If confirmation is skipped explicitly, state the assumed style / audience / slide-count / language / backend in the next user-facing update before generating.

Language

Respond in the user's language across questions, progress reports, error messages, and the completion summary. Keep technical tokens (style names, file paths, code) in English.

Script Directory

{baseDir} = this SKILL.md's directory. Resolve ${BUN_X}: prefer bun; else npx -y bun; else suggest brew install oven-sh/bun/bun.

Options

Style System

17 presets covering technical / educational / lifestyle / editorial use cases. Every preset is a combination of four dimensions (texture / mood / typography / density). If the user picks "Custom dimensions" in Round 1, Round 2 of the confirmation asks one question per dimension — options and verbatim copy live in references/confirmation.md.

Presets (17)

Per-preset specs: references/styles/<preset>.md. Preset → dimension mapping: references/dimensions/presets.md.

Dimensions (when "Custom dimensions" picked)

Full per-dimension specs: references/dimensions/*.md.

Auto-Selection

Match content signals to a preset. Pick the first row whose signal keywords appear in the source; fall back to blueprint if nothing matches.

Slide Count Heuristic

Reference Images

Users may supply reference images to guide style, palette, layout, or subject.

Intake: Accept via --ref <files...> or when the user provides file paths / pastes images in conversation.

• File path → copy to {slide-deck-dir}/refs/NN-ref-{slug}.{ext}
• Pasted image with no path → ask for the path, or extract style traits verbally as a text fallback

Usage modes (per reference):

Record refs in each slide's prompt frontmatter:

references:
  - ref_id: 01
    filename: 01-ref-brand.png
    usage: direct

At generation time, verify files exist. If usage: direct and the backend accepts refs (e.g., baoyu-imagine --ref), pass the file on every slide. Otherwise embed extracted style/palette traits in the prompt text.

File Layout

slide-deck/{topic-slug}/
├── source-{slug}.{ext}
├── outline.md
├── prompts/NN-slide-{slug}.md
├── NN-slide-{slug}.png
├── {topic-slug}.pptx
└── {topic-slug}.pdf

Slug: 2-4 words, kebab-case, extracted from topic. "Introduction to Machine Learning" → intro-machine-learning.

Backup rule (applies across steps): if a file about to be written already exists, rename it to <name>-backup-YYYYMMDD-HHMMSS.<ext> before writing the new one. This protects user edits and enables rollback.

Workflow

Copy this checklist and check off items as you complete them:

- [ ] Step 1: Setup & analyze
- [ ] Step 2: Confirmation ⚠️ REQUIRED (Round 1; Round 2 only if "Custom dimensions")
- [ ] Step 3: Generate outline
- [ ] Step 4: Review outline (conditional)
- [ ] Step 5: Generate prompts
- [ ] Step 6: Review prompts (conditional)
- [ ] Step 7: Generate images
- [ ] Step 8: Merge to PPTX/PDF
- [ ] Step 9: Output summary

Step 1: Setup & Analyze

1.1 Load EXTEND.md — check these paths in order; first hit wins:

If found, read, parse, and print a summary (style / audience / language / review). If not, proceed with defaults — first-time setup is not blocking for this skill. Schema: references/config/preferences-schema.md.

1.2 Analyze content — follow references/analysis-framework.md: classify content, detect language, note signals for style selection, estimate slide count from length (see the Slide Count Heuristic in Style System above), generate topic slug. Save source as source.md (honor backup rule if one exists).

1.3 Check existing output ⚠️ REQUIRED before Step 2. If slide-deck/{topic-slug}/ exists, ask how to proceed — four options (regenerate outline / regenerate images / backup and regenerate / exit), verbatim copy in references/confirmation.md.

Save findings to analysis.md: topic, audience, signals, recommended style and slide count, language detection.

Step 2: Confirmation ⚠️ REQUIRED

Hard gate: this step is mandatory per the Confirmation Policy — Steps 3+ cannot start until the user confirms here (or explicitly opts out with "直接生成" / equivalent wording in the current request).

Round 1 (always) — batch five questions in one AskUserQuestion call: style, audience, slide count, review-outline?, review-prompts?. Verbatim options in references/confirmation.md.

Summary displayed before the questions:

• Content type + topic
• Detected language
• Recommended style (based on signals)
• Recommended slide count (based on length)

Round 2 (only if "Custom dimensions" in Round 1) — batch four questions: texture, mood, typography, density. Verbatim options in references/confirmation.md. The four answers replace the preset.

After confirmation: update analysis.md with final choices and store skip_outline_review / skip_prompt_review flags from Q4/Q5.

Step 3: Generate Outline

Resolve style: preset → references/styles/{preset}.md; custom dimensions → combine files in references/dimensions/. Build STYLE_INSTRUCTIONS from the resolved style, apply confirmed audience + language + slide count, follow references/outline-template.md, and save as outline.md.

Stop here if --outline-only. Skip Step 4 if skip_outline_review.

Step 4: Review Outline (Conditional)

Display a slide-by-slide table (# | Title | Type | Layout) along with total count and resolved style. Ask: proceed / edit outline first / regenerate — verbatim in references/confirmation.md.

On "Edit outline first", tell the user to edit outline.md and ask again when ready. On "Regenerate outline", return to Step 3.

Step 5: Generate Prompts

For each slide in outline:

1. Read references/base-prompt.md
2. Extract STYLE_INSTRUCTIONS from the outline (don't re-read the style file)
3. Add the slide's content
4. If a Layout: is specified, include guidance from references/layouts.md
5. Save to prompts/NN-slide-{slug}.md (backup rule applies)

Stop here if --prompts-only. Skip Step 6 if skip_prompt_review.

Step 6: Review Prompts (Conditional)

Display the prompts index (# | Filename | Slide Title) and ask: proceed / edit prompts first / regenerate — verbatim in references/confirmation.md. Branches mirror Step 4.

Step 7: Generate Images

1. Resolve the image backend via the Image Generation Tools rule at the top — ask once if multiple are installed.
2. Confirm every prompts/NN-slide-{slug}.md exists (hard requirement; prompt files are the reproducibility record regardless of backend).
3. Session ID: slides-{topic-slug}-{timestamp} — pass to the backend only if it supports sessions.
4. For each slide: generate sequentially, reusing the session ID. Backup rule applies to PNG files. Report progress as Generated X/N. Auto-retry once on failure before reporting an error.

--regenerate N jumps to this step for the named slides only. --images-only starts here with existing prompts.

Step 8: Merge

${BUN_X} {baseDir}/scripts/merge-to-pptx.ts <slide-deck-dir>
${BUN_X} {baseDir}/scripts/merge-to-pdf.ts <slide-deck-dir>

Step 9: Summary

Slide Deck Complete!
Topic: [topic]
Style: [preset or "custom: texture+mood+typography+density"]
Location: [directory]
Slides: N

- 01-slide-cover.png
- ...
- NN-slide-back-cover.png

Outline: outline.md
PPTX: {topic-slug}.pptx
PDF: {topic-slug}.pdf

Slide Modification

Always update the prompt file before regenerating the image — this keeps the prompts directory as the source of truth and makes changes reproducible. Only NN changes on renumber; slugs stay stable so references remain valid.

See references/modification-guide.md for full details.

References

Notes

• Image generation takes ~10-30s per slide; report progress between them.
• For sensitive public figures, prefer stylized alternatives to avoid likeness issues.
• Maintain visual consistency via the session ID when the backend supports it.

Changing Preferences

EXTEND.md lives at the first matching path listed in Step 1.1. Two ways to change it:

• Edit directly — open EXTEND.md and change fields. Full schema: references/config/preferences-schema.md.
• Common one-line edits:
  • preferred_image_backend: auto — default; runtime-native tool wins, falls back to the only installed backend, asks only if multiple non-native are present.
  • preferred_image_backend: codex-imagegen — pin to Codex's built-in.
  • preferred_image_backend: baoyu-imagine — pin to the baoyu-imagine skill.
  • preferred_image_backend: ask — confirm backend every run.
  • preferred_style: blueprint, preferred_audience: experts, language: zh.