baoyu-infographic

Infographic Generator

Two dimensions: layout (information structure) × style (visual aesthetics); any layout combines with any style.

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 labels, headings, callouts, data values, or any other text inside an already generated infographic. Regenerate from a corrected prompt, switch to a layout with less 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-{type}-[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.

Reference Images

Accept via --ref <files...>, file paths, or pasted images (guide style, palette, composition, or subject):

• File path(s) → copy to refs/NN-ref-{slug}.{ext} alongside the output
• Pasted image with no path → ask for the path (per User Input Tools), or extract style traits verbally as a text fallback

Record refs in prompts/infographic.md frontmatter:

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

At generation: verify each referenced file exists; if usage: direct AND the backend accepts reference images (e.g., baoyu-image-gen via --ref), pass it via the backend's ref parameter; otherwise embed extracted style/palette traits in the prompt text.

Confirmation Policy

Default: confirm before generation.

• Explicit skill invocation, a file path, a matched keyword shortcut, EXTEND.md defaults, and the documented default combination are recommendation inputs only — none authorizes skipping confirmation.
• Do not start Step 5 or Step 6 until the user confirms the combination/aspect/language/backend choices.
• Skip confirmation only when the current request explicitly says so: --no-confirm, "直接生成", "不用确认", "跳过确认", "按默认出图", or equivalent. Then state the assumed combination/aspect/language/backend in the next user-facing update before generating.

Options

Layout Gallery (21)

Definitions: references/layouts/<layout>.md.

Style Gallery (22)

Definitions: references/styles/<style>.md.

Recommended Combinations

Default combination: bento-grid + craft-handmade (fallback recommendation only — never bypasses Step 4).

Keyword Shortcuts

When the user's input contains these keywords, use the mapped layout as the leading Step 3 recommendation, promote the listed styles to the top of the Step 3 list, skip content-based layout inference, and append any Prompt Notes to the Step 5 prompt.

Output Structure

infographic/{topic-slug}/
├── source-{slug}.{ext}
├── analysis.md
├── structured-content.md
├── prompts/infographic.md
└── infographic.png

Slug: 2-4 words kebab-case from topic. Conflict: append -YYYYMMDD-HHMMSS.

Core Principles

• Preserve source data faithfully—no summarization or rephrasing (but strip any credentials, API keys, tokens, or secrets before including in outputs)
• Define learning objectives before structuring content
• Structure for visual communication (headlines, labels, visual elements)

Workflow

Step 1: Setup & Analyze

1.1 Load Preferences (EXTEND.md) — first match wins:

Found → read, parse, display a one-line summary. Not found → ask the user with AskUserQuestion per references/config/first-time-setup.md. Supports preferred layout/style, default aspect, language, image backend, custom styles (schema: references/config/preferences-schema.md).

1.2 Analyze Content → analysis.md (format: references/analysis-framework.md)

1. Save source content (file path or paste → source.md). Backup rule: if source.md exists, rename to source-backup-YYYYMMDD-HHMMSS.md
2. Analyze: topic, data type, complexity, tone, audience
3. Detect source language and user language
4. Extract design instructions from user input
5. Save analysis. Backup rule: if analysis.md exists, rename to analysis-backup-YYYYMMDD-HHMMSS.md

Step 2: Generate Structured Content → structured-content.md

Format: references/structured-content-template.md. Title and learning objectives; sections with key concept, content (verbatim), visual element, text labels; data points (all statistics/quotes copied exactly); user design instructions.

Rules: Markdown only. No new information. Preserve data faithfully. Strip any credentials or secrets from output.

Step 3: Recommend Combinations

1. If user input matches a Keyword Shortcut, apply it (see above).
2. Otherwise recommend 3-5 layout×style combinations from data structure → layout, content tone → style, audience expectations, and user design instructions.

Step 4: Confirm Options

Hard gate per the Confirmation Policy (opt-out: --no-confirm / equivalent in the current request). Ask per User Input Tools:

Step 5: Generate Prompt → prompts/infographic.md

Backup rule: if prompts/infographic.md exists, rename to prompts/infographic-backup-YYYYMMDD-HHMMSS.md.

Combine: layout definition (references/layouts/<layout>.md), style definition (references/styles/<style>.md), base template (references/base-prompt.md), structured content from Step 2; all text in the confirmed language.

{{ASPECT_RATIO}}: landscape→16:9, portrait→9:16, square→1:1; custom W:H ratios as-is (e.g., 3:4, 4:3, 2.35:1).

Step 6: Generate Image

1. Resolve the backend per ## Image Generation Tools.
2. Ensure the full final prompt is persisted at prompts/infographic.md (Step 5) BEFORE invoking the backend.
3. If infographic.png exists, rename to infographic-backup-YYYYMMDD-HHMMSS.png.
4. Call the backend with the prompt file and output path. For codex-imagegen, see references/codex-imagegen.md.
5. On failure, auto-retry once.

Text correction: never patch misspelled, garbled, or weak rendered text (labels, headings, callouts, data values) in the bitmap with code. Write a new prompt file and a new output path so the flawed candidate is kept for comparison. Post-processing is limited to crop, resize, compression, or format conversion that doesn't alter text or composition.

Step 7: Output Summary

Report: topic, layout, style, aspect, language, image backend, output path, files created.

Changing Preferences

EXTEND.md lives at the first matching path in Step 1.1. Edit it directly (schema: references/config/preferences-schema.md), or delete it / ask "reconfigure baoyu-infographic preferences" / "重新配置" to re-run first-time setup. Common edits:

• preferred_image_backend: auto (default; runtime-native wins, else the only installed backend, ask if multiple non-native) | codex-imagegen | baoyu-image-gen | ask (confirm every run)
• preferred_layout: dense-modules, preferred_style: morandi-journal, preferred_aspect: portrait, language: zh — shift Step-3 recommendations and Step-4 defaults (never bypass Step 4).