Baoyu Slide Deck

Slide Deck Generator

Decks are designed for reading and sharing (self-explanatory slides, logical scroll flow, social-media-friendly), not live presentation — this drives every layout and density decision.

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

Resolve the image backend in this order:

1. User names a backend in the current message → use it.
2. preferred_image_backend in EXTEND.md names a backend available now → use it. ask means ask every run.
3. Auto-select (preference auto, unset, or the pinned backend is unavailable), first match wins:
   • Codex imagegen skill is in your available skills → you are in Codex and MUST use it: Skill with skill: "imagegen", passing the prompt file's content plus output path and aspect ratio. It outranks non-native skills such as baoyu-image-gen.
   • Codex via codex exec (codex-imagegen): no native imagegen, but the codex CLI is on PATH with an active codex login → baoyu-image-gen --provider codex-cli (preferred), or the bundled wrapper if baoyu-image-gen is unavailable. Load references/codex-imagegen.md only for this branch.
   • Cursor GenerateImage → use it (outranks non-native skills). It has no aspect-ratio parameter, so state the aspect ratio / dimensions in the description prompt; it saves to a tool-managed location, so copy the file to the expected output path (e.g., outputs/.../NN-xxx.png). Reference images go in reference_image_paths.
   • Other runtime-native image tool (e.g., Hermes image_generate) → use it the same way.
   • Exactly one non-native backend installed (e.g., baoyu-image-gen) → use it.
   • Several non-native backends → ask the user once, batched with other initial questions.
4. None available → tell the user and ask how to proceed.

⛔ Raster only: never substitute SVG, HTML/CSS, canvas, or other code-based rendering for a raster image, even for diagram-like content. If no raster backend resolves, go to step 4.

⛔ No bitmap text patching: never use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other overlay to cover, rewrite, erase, stroke, or replace slide titles, bullets, or any other text inside an already generated slide image. Regenerate from a corrected prompt, simplify the slide's on-image text, or ask the user which imperfect candidate to keep.

Prompt file (hard): before invoking any backend, write each image's full, final prompt to its own file under prompts/ (NN-slide-[slug].md) and pass that file (or its content) to the backend. It is the reproducibility record and lets you switch backends without rewriting prompts.

Change the pinned backend via ## Changing Preferences below. Tool names above are examples; use the local equivalent in other runtimes.

Batch Generation Policy

After every prompt file for the current generation group is saved and verified, generate slide images in batches by default:

1. Use the backend's native batch / multi-task interface if it exists. Each task keeps its own prompt file, output path, aspect ratio, session ID, and direct reference images.
2. Else, if the runtime can issue parallel tool calls, dispatch up to generation_batch_size slide images at a time (default 4). An explicit request in the current message (e.g. --batch-size 4, "并行4张一起生成") overrides EXTEND.md.
3. Else generate sequentially.

Rules:

• Never start the first batch until all selected slide prompt files exist on disk.
• Retry failed items once without regenerating successful items.
• Do not use subagents merely to parallelize image rendering; use them only for separate prompt iteration or creative exploration.
• Merge PPTX/PDF only after all selected slide images are generated.

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.

Script	Purpose
scripts/merge-to-pptx.ts	Merge slides into PowerPoint
scripts/merge-to-pdf.ts	Merge slides into PDF

Options

Option	Description
--style <name>	Preset (see Presets below), custom, or custom style name
--audience <type>	beginners / intermediate / experts / executives / general
--lang <code>	Output language (en, zh, ja, ...)
--slides <N>	Target slide count (8-25 recommended, max 30)
--ref <files...>	Reference images applied per slide (style / palette / composition / subject)
--batch-size <n>	Temporary slide image generation batch size for this run. Default: generation_batch_size from EXTEND.md, otherwise 4. Clamp to 1-8.
--outline-only	Stop after outline
--prompts-only	Stop after prompts (skip image generation)
--images-only	Skip to Step 7; requires existing prompts/
--regenerate <N>	Regenerate specific slide(s): 3 or 2,5,8

Style System

Each preset combines four dimensions (texture / mood / typography / density). If the user picks "Custom dimensions" in Round 1, Round 2 asks one question per dimension (copy in references/confirmation.md).

Presets (17)

Preset	Dimensions	Best For
blueprint (Default)	grid + cool + technical + balanced	Architecture, system design
chalkboard	organic + warm + handwritten + balanced	Education, tutorials
corporate	clean + professional + geometric + balanced	Investor decks, proposals
minimal	clean + neutral + geometric + minimal	Executive briefings
sketch-notes	organic + warm + handwritten + balanced	Educational, tutorials
hand-drawn-edu	organic + macaron + handwritten + balanced	Educational diagrams, process explainers
watercolor	organic + warm + humanist + minimal	Lifestyle, wellness
dark-atmospheric	clean + dark + editorial + balanced	Entertainment, gaming
notion	clean + neutral + geometric + dense	Product demos, SaaS
bold-editorial	clean + vibrant + editorial + balanced	Product launches, keynotes
editorial-infographic	clean + cool + editorial + dense	Tech explainers, research
fantasy-animation	organic + vibrant + handwritten + minimal	Educational storytelling
intuition-machine	clean + cool + technical + dense	Technical docs, academic
pixel-art	pixel + vibrant + technical + balanced	Gaming, developer talks
scientific	clean + cool + technical + dense	Biology, chemistry, medical
vector-illustration	clean + vibrant + humanist + balanced	Creative, children's content
vintage	paper + warm + editorial + balanced	Historical, heritage

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

Dimensions (when "Custom dimensions" picked)

Dimension	Options	Purpose
Texture	clean, grid, organic, pixel, paper	Background treatment
Mood	professional, warm, cool, vibrant, dark, neutral, macaron	Color temperature
Typography	geometric, humanist, handwritten, editorial, technical	Headline/body styling
Density	minimal, balanced, dense	Information per slide

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

Auto-Selection

Pick the first row whose signal keywords appear in the source; fall back to blueprint.

Signals in source	Preset
tutorial, learn, education, guide, beginner	sketch-notes
hand-drawn, infographic, diagram, process, onboarding	hand-drawn-edu
classroom, teaching, school, chalkboard	chalkboard
architecture, system, data, analysis, technical	blueprint
creative, children, kids, cute	vector-illustration
briefing, academic, research, bilingual	intuition-machine
executive, minimal, clean, simple	minimal
saas, product, dashboard, metrics	notion
investor, quarterly, business, corporate	corporate
launch, marketing, keynote, magazine	bold-editorial
entertainment, music, gaming, atmospheric	dark-atmospheric
explainer, journalism, science communication	editorial-infographic
story, fantasy, animation, magical	fantasy-animation
gaming, retro, pixel, developer	pixel-art
biology, chemistry, medical, scientific	scientific
history, heritage, vintage, expedition	vintage
lifestyle, wellness, travel, artistic	watercolor

Slide Count Heuristic

Source length	Recommended slides
< 1000 words	5-10
1000-3000 words	10-18
3000-5000 words	15-25
> 5000 words	20-30 (consider splitting)

Reference Images

User-supplied images guide style, palette, layout, or subject.

Intake via --ref <files...> or file paths / pasted 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):

Usage	Effect
direct	Pass the file to the backend as a reference image for each slide
style	Extract style traits (line treatment, texture, mood) and append to every slide's prompt body
palette	Extract hex colors and append to every slide's prompt body

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-image-gen --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 (all steps): if a file about to be written already exists, rename it to <name>-backup-YYYYMMDD-HHMMSS.<ext> first.

Workflow

- [ ] 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:

Path	Scope
.baoyu-skills/baoyu-slide-deck/EXTEND.md	Project
${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-slide-deck/EXTEND.md	XDG
$HOME/.baoyu-skills/baoyu-slide-deck/EXTEND.md	User home

If found, read, parse, and print a summary (style / audience / language / review / generation batch size). 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 per the Confirmation Policy: Steps 3+ wait for the user's answer here unless the current request explicitly opts out ("直接生成" or equivalent).

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

Show before the questions: content type + topic, detected language, recommended style (from signals), recommended slide count (from 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.
   • For codex-imagegen, follow references/codex-imagegen.md (n=1 per call, so slide batches dispatch one wrapper call per slide).
2. Confirm every prompts/NN-slide-{slug}.md exists (hard requirement).
3. Session ID: slides-{topic-slug}-{timestamp} — pass to the backend only if it supports sessions.
4. Build a task list for selected slides with each slide's prompt file, output PNG path, aspect ratio, session ID, and verified direct references.
5. Dispatch per ## Batch Generation Policy. Backup rule applies to PNG files before dispatch. Report progress as Generated X/N. Retry only failed items once 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

Action	How
Edit	Update prompts/NN-slide-{slug}.md first, then --regenerate N
Add	Create new prompt at position, generate image, renumber subsequent NN (slugs unchanged), update outline.md, re-merge
Delete	Remove PNG + prompt, renumber subsequent, update outline.md, re-merge

Always update the prompt file before regenerating the image (prompts are the source of truth). Only NN changes on renumber; slugs stay stable.

Text correction policy:

• If a slide's title, bullets, or any other rendered text is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
• For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
• Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.

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

Other References

• references/design-guidelines.md — audience, typography, color selection
• references/content-rules.md — content and style rules

Notes

• 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 in Step 1.1.

• Edit directly — 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-image-gen — pin to the baoyu-image-gen skill.
  • preferred_image_backend: ask — confirm backend every run.
  • generation_batch_size: 4 — default number of slide images to render concurrently when the backend/runtime supports batch or parallel generation.
  • preferred_style: blueprint, preferred_audience: experts, language: zh.