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):
- Prefer built-in user-input tools exposed by the current agent runtime — e.g.,
AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent.
- 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.
- 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:
- User names a backend in the current message → use it.
preferred_image_backend in EXTEND.md names a backend available now → use it. ask means ask every run.
- 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.
- 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
| Usage |
Effect |
direct |
Pass the file to the backend as a reference image |
style |
Extract style traits (line treatment, texture, mood) and append to the prompt body |
palette |
Extract hex colors from the image and append to the prompt body |
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
| Option |
Values |
--layout |
21 options (see Layout Gallery), default: bento-grid |
--style |
22 options (see Style Gallery), default: craft-handmade |
--aspect |
Named: landscape (16:9), portrait (9:16), square (1:1). Custom: any W:H ratio (e.g., 3:4, 4:3, 2.35:1) |
--lang |
en, zh, ja, etc. |
--no-confirm |
Skip Step 4 only when the user explicitly requests direct generation without confirmation |
--ref <files...> |
Reference images (file paths) for style / palette / composition / subject guidance |
Layout Gallery (21)
Definitions: references/layouts/<layout>.md.
| Layout |
Best For |
linear-progression |
Timelines, processes, tutorials |
binary-comparison |
A vs B, before-after, pros-cons |
comparison-matrix |
Multi-factor comparisons |
hierarchical-layers |
Pyramids, priority levels |
tree-branching |
Categories, taxonomies |
hub-spoke |
Central concept with related items |
structural-breakdown |
Exploded views, cross-sections |
bento-grid |
Multiple topics, overview (default) |
iceberg |
Surface vs hidden aspects |
bridge |
Problem-solution |
funnel |
Conversion, filtering |
isometric-map |
Spatial relationships |
dashboard |
Metrics, KPIs |
periodic-table |
Categorized collections |
comic-strip |
Narratives, sequences |
story-mountain |
Plot structure, tension arcs |
jigsaw |
Interconnected parts |
venn-diagram |
Overlapping concepts |
winding-roadmap |
Journey, milestones |
circular-flow |
Cycles, recurring processes |
dense-modules |
High-density modules, data-rich guides |
Style Gallery (22)
Definitions: references/styles/<style>.md.
| Style |
Description |
craft-handmade |
Hand-drawn, paper craft (default) |
claymation |
3D clay figures, stop-motion |
kawaii |
Japanese cute, pastels |
storybook-watercolor |
Soft painted, whimsical |
chalkboard |
Chalk on black board |
cyberpunk-neon |
Neon glow, futuristic |
bold-graphic |
Comic style, halftone |
aged-academia |
Vintage science, sepia |
corporate-memphis |
Flat vector, vibrant |
technical-schematic |
Blueprint, engineering |
origami |
Folded paper, geometric |
pixel-art |
Retro 8-bit |
ui-wireframe |
Grayscale interface mockup |
subway-map |
Transit diagram |
ikea-manual |
Minimal line art |
knolling |
Organized flat-lay |
lego-brick |
Toy brick construction |
pop-laboratory |
Blueprint grid, coordinate markers, lab precision |
morandi-journal |
Hand-drawn doodle, warm Morandi tones |
retro-pop-grid |
1970s retro pop art, Swiss grid, thick outlines |
hand-drawn-edu |
Macaron pastels, hand-drawn wobble, stick figures |
retro-popup-pop |
Retro popup collage, vintage UI, thick outlines, flat pop colors |
Recommended Combinations
| Content Type |
Layout + Style |
| Timeline/History |
linear-progression + craft-handmade |
| Step-by-step |
linear-progression + ikea-manual |
| A vs B |
binary-comparison + corporate-memphis |
| Hierarchy |
hierarchical-layers + craft-handmade |
| Overlap |
venn-diagram + craft-handmade |
| Conversion |
funnel + corporate-memphis |
| Cycles |
circular-flow + craft-handmade |
| Technical |
structural-breakdown + technical-schematic |
| Metrics |
dashboard + corporate-memphis |
| Educational |
bento-grid + chalkboard |
| Journey |
winding-roadmap + storybook-watercolor |
| Categories |
periodic-table + bold-graphic |
| Product Guide |
dense-modules + morandi-journal |
| Technical Guide |
dense-modules + pop-laboratory |
| Trendy Guide |
dense-modules + retro-pop-grid |
| Retro Pop Guide |
dense-modules + retro-popup-pop |
| Educational Diagram |
hub-spoke + hand-drawn-edu |
| Process Tutorial |
linear-progression + hand-drawn-edu |
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.
| User Keyword |
Layout |
Recommended Styles |
Default Aspect |
Prompt Notes |
| 高密度信息大图 / high-density-info |
dense-modules |
morandi-journal, pop-laboratory, retro-pop-grid, retro-popup-pop |
portrait |
— |
| 信息图 / infographic |
bento-grid |
craft-handmade |
landscape |
Minimalist: clean canvas, ample whitespace, no complex background textures. Simple cartoon elements and icons only. |
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:
| Priority |
Path |
Scope |
| 1 |
.baoyu-skills/baoyu-infographic/EXTEND.md |
Project |
| 2 |
${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-infographic/EXTEND.md |
XDG |
| 3 |
$HOME/.baoyu-skills/baoyu-infographic/EXTEND.md |
User home |
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)
- Save source content (file path or paste →
source.md). Backup rule: if source.md exists, rename to source-backup-YYYYMMDD-HHMMSS.md
- Analyze: topic, data type, complexity, tone, audience
- Detect source language and user language
- Extract design instructions from user input
- 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
- If user input matches a Keyword Shortcut, apply it (see above).
- 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:
| Priority |
Question |
When |
Options |
| 1 |
Combination |
Always |
3+ layout×style combos with rationale |
| 2 |
Aspect |
Always |
Named presets (landscape/portrait/square) or custom W:H ratio (e.g., 3:4, 4:3, 2.35:1) |
| 3 |
Language |
Only if source ≠ user language |
Language for text content |
| 4 |
Image Backend |
Only if step 3 of the ## Image Generation Tools rule needs to ask (no runtime-native tool AND multiple non-native backends, OR preferred_image_backend: ask) |
Available backends |
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
- Resolve the backend per
## Image Generation Tools.
- Ensure the full final prompt is persisted at
prompts/infographic.md (Step 5) BEFORE invoking the backend.
- If
infographic.png exists, rename to infographic-backup-YYYYMMDD-HHMMSS.png.
- Call the backend with the prompt file and output path. For
codex-imagegen, see references/codex-imagegen.md.
- 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).
1---2name: baoyu-infographic3description: Generate professional infographics with 21 layout types and 22 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".4version: 1.117.45metadata:6 source: https://skillmd.com/skills/tuyv/baoyu-infographic7 openclaw:8 homepage: https://github.com/JimLiu/baoyu-skills#baoyu-infographic9---1011# Infographic Generator1213Two dimensions: **layout** (information structure) × **style** (visual aesthetics); any layout combines with any style.1415## User Input Tools1617When this skill prompts the user, follow this tool-selection rule (priority order):18191. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.202. **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.213. **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.2223Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.2425## Image Generation Tools2627Resolve the image backend in this order:28291. **User names a backend** in the current message → use it.302. **`preferred_image_backend`** in `EXTEND.md` names a backend available now → use it. `ask` means ask every run.313. **Auto-select** (preference `auto`, unset, or the pinned backend is unavailable), first match wins:32 - **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`.33 - **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](references/codex-imagegen.md) only for this branch.34 - **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`.35 - **Other runtime-native image tool** (e.g., Hermes `image_generate`) → use it the same way.36 - Exactly one non-native backend installed (e.g., `baoyu-image-gen`) → use it.37 - Several non-native backends → ask the user once, batched with other initial questions.384. **None available** → tell the user and ask how to proceed.3940**⛔ 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 4.4142**⛔ 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.4344**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.4546Change the pinned backend via `## Changing Preferences` below. Tool names above are examples; use the local equivalent in other runtimes.4748## Reference Images4950Accept via `--ref <files...>`, file paths, or pasted images (guide style, palette, composition, or subject):51- File path(s) → copy to `refs/NN-ref-{slug}.{ext}` alongside the output52- Pasted image with no path → ask for the path (per User Input Tools), or extract style traits verbally as a text fallback5354| Usage | Effect |55|-------|--------|56| `direct` | Pass the file to the backend as a reference image |57| `style` | Extract style traits (line treatment, texture, mood) and append to the prompt body |58| `palette` | Extract hex colors from the image and append to the prompt body |5960Record refs in `prompts/infographic.md` frontmatter:6162```yaml63references:64 - ref_id: 0165 filename: 01-ref-brand.png66 usage: direct67```6869At 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.7071## Confirmation Policy7273Default: **confirm before generation**.7475- 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.76- Do not start Step 5 or Step 6 until the user confirms the combination/aspect/language/backend choices.77- 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.7879## Options8081| Option | Values |82|--------|--------|83| `--layout` | 21 options (see Layout Gallery), default: bento-grid |84| `--style` | 22 options (see Style Gallery), default: craft-handmade |85| `--aspect` | Named: landscape (16:9), portrait (9:16), square (1:1). Custom: any W:H ratio (e.g., 3:4, 4:3, 2.35:1) |86| `--lang` | en, zh, ja, etc. |87| `--no-confirm` | Skip Step 4 only when the user explicitly requests direct generation without confirmation |88| `--ref <files...>` | Reference images (file paths) for style / palette / composition / subject guidance |8990## Layout Gallery (21)9192Definitions: `references/layouts/<layout>.md`.9394| Layout | Best For |95|--------|----------|96| `linear-progression` | Timelines, processes, tutorials |97| `binary-comparison` | A vs B, before-after, pros-cons |98| `comparison-matrix` | Multi-factor comparisons |99| `hierarchical-layers` | Pyramids, priority levels |100| `tree-branching` | Categories, taxonomies |101| `hub-spoke` | Central concept with related items |102| `structural-breakdown` | Exploded views, cross-sections |103| `bento-grid` | Multiple topics, overview (default) |104| `iceberg` | Surface vs hidden aspects |105| `bridge` | Problem-solution |106| `funnel` | Conversion, filtering |107| `isometric-map` | Spatial relationships |108| `dashboard` | Metrics, KPIs |109| `periodic-table` | Categorized collections |110| `comic-strip` | Narratives, sequences |111| `story-mountain` | Plot structure, tension arcs |112| `jigsaw` | Interconnected parts |113| `venn-diagram` | Overlapping concepts |114| `winding-roadmap` | Journey, milestones |115| `circular-flow` | Cycles, recurring processes |116| `dense-modules` | High-density modules, data-rich guides |117118## Style Gallery (22)119120Definitions: `references/styles/<style>.md`.121122| Style | Description |123|-------|-------------|124| `craft-handmade` | Hand-drawn, paper craft (default) |125| `claymation` | 3D clay figures, stop-motion |126| `kawaii` | Japanese cute, pastels |127| `storybook-watercolor` | Soft painted, whimsical |128| `chalkboard` | Chalk on black board |129| `cyberpunk-neon` | Neon glow, futuristic |130| `bold-graphic` | Comic style, halftone |131| `aged-academia` | Vintage science, sepia |132| `corporate-memphis` | Flat vector, vibrant |133| `technical-schematic` | Blueprint, engineering |134| `origami` | Folded paper, geometric |135| `pixel-art` | Retro 8-bit |136| `ui-wireframe` | Grayscale interface mockup |137| `subway-map` | Transit diagram |138| `ikea-manual` | Minimal line art |139| `knolling` | Organized flat-lay |140| `lego-brick` | Toy brick construction |141| `pop-laboratory` | Blueprint grid, coordinate markers, lab precision |142| `morandi-journal` | Hand-drawn doodle, warm Morandi tones |143| `retro-pop-grid` | 1970s retro pop art, Swiss grid, thick outlines |144| `hand-drawn-edu` | Macaron pastels, hand-drawn wobble, stick figures |145| `retro-popup-pop` | Retro popup collage, vintage UI, thick outlines, flat pop colors |146147## Recommended Combinations148149| Content Type | Layout + Style |150|--------------|----------------|151| Timeline/History | `linear-progression` + `craft-handmade` |152| Step-by-step | `linear-progression` + `ikea-manual` |153| A vs B | `binary-comparison` + `corporate-memphis` |154| Hierarchy | `hierarchical-layers` + `craft-handmade` |155| Overlap | `venn-diagram` + `craft-handmade` |156| Conversion | `funnel` + `corporate-memphis` |157| Cycles | `circular-flow` + `craft-handmade` |158| Technical | `structural-breakdown` + `technical-schematic` |159| Metrics | `dashboard` + `corporate-memphis` |160| Educational | `bento-grid` + `chalkboard` |161| Journey | `winding-roadmap` + `storybook-watercolor` |162| Categories | `periodic-table` + `bold-graphic` |163| Product Guide | `dense-modules` + `morandi-journal` |164| Technical Guide | `dense-modules` + `pop-laboratory` |165| Trendy Guide | `dense-modules` + `retro-pop-grid` |166| Retro Pop Guide | `dense-modules` + `retro-popup-pop` |167| Educational Diagram | `hub-spoke` + `hand-drawn-edu` |168| Process Tutorial | `linear-progression` + `hand-drawn-edu` |169170Default combination: `bento-grid` + `craft-handmade` (fallback recommendation only — never bypasses Step 4).171172## Keyword Shortcuts173174When 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.175176| User Keyword | Layout | Recommended Styles | Default Aspect | Prompt Notes |177|--------------|--------|--------------------|----------------|--------------|178| 高密度信息大图 / high-density-info | `dense-modules` | `morandi-journal`, `pop-laboratory`, `retro-pop-grid`, `retro-popup-pop` | portrait | — |179| 信息图 / infographic | `bento-grid` | `craft-handmade` | landscape | Minimalist: clean canvas, ample whitespace, no complex background textures. Simple cartoon elements and icons only. |180181## Output Structure182183```184infographic/{topic-slug}/185├── source-{slug}.{ext}186├── analysis.md187├── structured-content.md188├── prompts/infographic.md189└── infographic.png190```191192Slug: 2-4 words kebab-case from topic. Conflict: append `-YYYYMMDD-HHMMSS`.193194## Core Principles195196- Preserve source data faithfully—no summarization or rephrasing (but **strip any credentials, API keys, tokens, or secrets** before including in outputs)197- Define learning objectives before structuring content198- Structure for visual communication (headlines, labels, visual elements)199200## Workflow201202### Step 1: Setup & Analyze203204**1.1 Load Preferences (EXTEND.md)** — first match wins:205206| Priority | Path | Scope |207|----------|------|-------|208| 1 | `.baoyu-skills/baoyu-infographic/EXTEND.md` | Project |209| 2 | `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-infographic/EXTEND.md` | XDG |210| 3 | `$HOME/.baoyu-skills/baoyu-infographic/EXTEND.md` | User home |211212Found → 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`).213214**1.2 Analyze Content → `analysis.md`** (format: `references/analysis-framework.md`)2152161. Save source content (file path or paste → `source.md`). **Backup rule**: if `source.md` exists, rename to `source-backup-YYYYMMDD-HHMMSS.md`2172. Analyze: topic, data type, complexity, tone, audience2183. Detect source language and user language2194. Extract design instructions from user input2205. Save analysis. **Backup rule**: if `analysis.md` exists, rename to `analysis-backup-YYYYMMDD-HHMMSS.md`221222### Step 2: Generate Structured Content → `structured-content.md`223224Format: `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.225226**Rules**: Markdown only. No new information. Preserve data faithfully. Strip any credentials or secrets from output.227228### Step 3: Recommend Combinations2292301. If user input matches a **Keyword Shortcut**, apply it (see above).2312. Otherwise recommend 3-5 layout×style combinations from data structure → layout, content tone → style, audience expectations, and user design instructions.232233### Step 4: Confirm Options234235**Hard gate** per the [Confirmation Policy](#confirmation-policy) (opt-out: `--no-confirm` / equivalent in the current request). Ask per [User Input Tools](#user-input-tools):236237| Priority | Question | When | Options |238|----------|----------|------|---------|239| 1 | **Combination** | Always | 3+ layout×style combos with rationale |240| 2 | **Aspect** | Always | Named presets (landscape/portrait/square) or custom W:H ratio (e.g., 3:4, 4:3, 2.35:1) |241| 3 | **Language** | Only if source ≠ user language | Language for text content |242| 4 | **Image Backend** | Only if step 3 of the `## Image Generation Tools` rule needs to ask (no runtime-native tool AND multiple non-native backends, OR `preferred_image_backend: ask`) | Available backends |243244### Step 5: Generate Prompt → `prompts/infographic.md`245246**Backup rule**: if `prompts/infographic.md` exists, rename to `prompts/infographic-backup-YYYYMMDD-HHMMSS.md`.247248Combine: 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.249250`{{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`).251252### Step 6: Generate Image2532541. Resolve the backend per `## Image Generation Tools`.2552. Ensure the full final prompt is persisted at `prompts/infographic.md` (Step 5) BEFORE invoking the backend.2563. If `infographic.png` exists, rename to `infographic-backup-YYYYMMDD-HHMMSS.png`.2574. Call the backend with the prompt file and output path. For `codex-imagegen`, see [references/codex-imagegen.md](references/codex-imagegen.md).2585. On failure, auto-retry once.259260Text 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.261262### Step 7: Output Summary263264Report: topic, layout, style, aspect, language, image backend, output path, files created.265266## Changing Preferences267268EXTEND.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:269270- `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)271- `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).