Detailed Workflow Procedures

Step 1: Pre-check

1.0 Detect & Save Reference Images ⚠️ REQUIRED if images provided

Check if user provided reference images. Handle based on input type:

CRITICAL: Only add references to prompt frontmatter if files are ACTUALLY SAVED to references/ directory.

If user provides file path:

1. Copy to references/NN-ref-{slug}.png
2. Create description: references/NN-ref-{slug}.md
3. Verify files exist before proceeding

If user can't provide path (extracted verbally):

1. Analyze image visually, extract: colors, style, composition
2. Create references/extracted-style.md with extracted info
3. DO NOT add references to prompt frontmatter
4. Instead, append extracted style/colors directly to prompt text

Description File Format (only when file saved):

---
ref_id: NN
filename: NN-ref-{slug}.png
---
[User's description or auto-generated description]

Verification (only for saved files):

Reference Images Saved:
- 01-ref-{slug}.png ✓ (can use --ref)
- 02-ref-{slug}.png ✓ (can use --ref)

Or for extracted style:

Reference Style Extracted (no file):
- Colors: #E8756D coral, #7ECFC0 mint...
- Style: minimal flat vector, clean lines...
→ Will append to prompt text (not --ref)

1.1 Determine Input Type

Backup rule for pasted content: If source.md exists in target directory, rename to source-backup-YYYYMMDD-HHMMSS.md before saving.

1.2-1.4 Configuration (file path input only)

Check preferences and existing state, then ask ALL needed questions in ONE AskUserQuestion call (max 4 questions).

Questions to include (skip if preference exists or not applicable):

Preference Values (if configured, skip asking):

1.5 Load Preferences (EXTEND.md) ⛔ BLOCKING

CRITICAL: If EXTEND.md not found, MUST complete first-time setup before ANY other questions or steps. Do NOT proceed to reference images, do NOT ask about content, do NOT ask about type/style — ONLY complete the preferences setup first.

# macOS, Linux, WSL, Git Bash
test -f .baoyu-skills/baoyu-article-illustrator/EXTEND.md && echo "project"
test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-article-illustrator/EXTEND.md" && echo "xdg"
test -f "$HOME/.baoyu-skills/baoyu-article-illustrator/EXTEND.md" && echo "user"

# PowerShell (Windows)
if (Test-Path .baoyu-skills/baoyu-article-illustrator/EXTEND.md) { "project" }
$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
if (Test-Path "$xdg/baoyu-skills/baoyu-article-illustrator/EXTEND.md") { "xdg" }
if (Test-Path "$HOME/.baoyu-skills/baoyu-article-illustrator/EXTEND.md") { "user" }

Supports: Watermark | Preferred type/style | Custom styles | Language | Output directory

Step 2: Setup & Analyze

2.1 Analyze Content

2.2 Extract Core Arguments

• Main thesis
• Key concepts reader needs
• Comparisons/contrasts
• Framework/model proposed

CRITICAL: If article uses metaphors (e.g., "电锯切西瓜"), do NOT illustrate literally. Visualize the underlying concept.

2.3 Identify Positions

Illustrate:

• Core arguments (REQUIRED)
• Abstract concepts
• Data comparisons
• Processes, workflows

Do NOT Illustrate:

• Metaphors literally
• Decorative scenes
• Generic illustrations

2.4 Analyze Reference Images (if provided in Step 1.0)

For each reference image:

Step 3: Confirm Settings ⚠️

Do NOT skip. Use ONE AskUserQuestion call with max 4 questions. Q1, Q2, Q3 are ALL REQUIRED.

Q1: Preset or Type ⚠️ REQUIRED

Based on Step 2 content analysis, recommend a preset first (sets both type & style). Look up style-presets.md "Content Type → Preset Recommendations" table.

• [Recommended preset] — [brief: type + style + why] (Recommended)
• [Alternative preset] — [brief]
• Or choose type manually: infographic / scene / flowchart / comparison / framework / timeline / mixed

Default: if Step 2 found no strong content signal, the recommended preset MUST be hand-drawn-edu (infographic + sketch-notes + macaron — warm cream paper, black hand-drawn lines, soft pastel blocks). This is the universal fallback.

If user picks a preset → skip Q3 (type & style both resolved). If user picks a type → Q3 is REQUIRED.

Q2: Density ⚠️ REQUIRED - DO NOT SKIP

• minimal (1-2) - Core concepts only
• balanced (3-5) - Major sections
• per-section - At least 1 per section/chapter (Recommended)
• rich (6+) - Comprehensive coverage

Q3: Style ⚠️ REQUIRED (skip if preset chosen in Q1)

If EXTEND.md has preferred_style:

• [Custom style name + brief description] (Recommended)
• [Top compatible core style 1]
• [Top compatible core style 2]
• Other (see full Style Gallery)

If no preferred_style (present Core Styles first):

• [Best compatible core style] (Recommended)
• [Other compatible core style 1]
• [Other compatible core style 2]
• Other (see full Style Gallery)

Core Styles (simplified selection):

Default recommendation: when Step 2 surfaces no strong content signal, recommend hand-drawn-edu preset (→ infographic + sketch-notes + macaron) as the primary option in Q1. When the user picks a type manually without a preferred_style, recommend sketch-notes first in Q3.

Style selection based on Type × Style compatibility matrix (styles.md). In Step 5.1, read styles/<style>.md for visual elements and rendering rules.

Q4: Palette (optional)

If preset did not specify a palette, and the user may benefit from a palette override, offer available palettes:

• Default (use style's built-in colors) (Recommended)
• macaron — soft pastel blocks on warm cream
• warm — warm earth tones, no cool colors
• neon — vibrant neon on dark backgrounds

Skip if: preset already resolved palette, or preferred_palette set in EXTEND.md.

See Palette Gallery in styles.md and full specs in palettes/<palette>.md.

Q5: Image Text Language ⚠️ REQUIRED when article language ≠ EXTEND.md language

Detect article language from content. If different from EXTEND.md language setting, MUST ask:

• Article language (match article content) (Recommended)
• EXTEND.md language (user's general preference)

Skip only if: Article language matches EXTEND.md language, or EXTEND.md has no language setting.

Display Reference Usage (if references detected in Step 1.0)

When presenting outline preview to user, show reference assignments:

Reference Images:
| Ref | Filename | Recommended Usage |
|-----|----------|-------------------|
| 01 | 01-ref-diagram.png | direct → Illustration 1, 3 |
| 02 | 02-ref-chart.png | palette → Illustration 2 |

Step 4: Generate Outline

Save as {output-dir}/outline.md (all paths below are relative to the output directory determined in Step 1.1/1.2):

---
type: infographic
density: balanced
style: blueprint
image_count: 4
references:                    # Only if references provided
  - ref_id: 01
    filename: 01-ref-diagram.png
    description: "Technical diagram showing system architecture"
  - ref_id: 02
    filename: 02-ref-chart.png
    description: "Color chart with brand palette"
---

## Illustration 1

**Position**: [section] / [paragraph]
**Purpose**: [why this helps]
**Visual Content**: [what to show]
**Type Application**: [how type applies]
**References**: [01]                    # Optional: list ref_ids used
**Reference Usage**: direct             # direct | style | palette
**Filename**: 01-infographic-concept-name.png

## Illustration 2
...

Requirements:

• Each position justified by content needs
• Type applied consistently
• Style reflected in descriptions
• Count matches density
• References assigned based on Step 2.4 analysis

Step 5: Generate Images

5.1 Create Prompts ⛔ BLOCKING

Every illustration MUST have a saved prompt file before generation begins. DO NOT skip this step.

For each illustration in the outline:

1. Create prompt file: {output-dir}/prompts/NN-{type}-{slug}.md
2. Include YAML frontmatter:

   ---
   illustration_id: 01
   type: infographic
   style: custom-flat-vector
   ---

1. Load style specs: Read styles/<style>.md for visual elements, style rules, and rendering instructions
2. Load palette specs (if palette specified): Read palettes/<palette>.md for colors and background. Palette colors replace the style's default Color Palette. If no palette specified, use the style's built-in colors.
3. Follow type-specific template from prompt-construction.md, using rendering from style + colors from palette (or style default)
4. Prompt quality requirements (all REQUIRED):

• Layout: Describe overall composition (grid / radial / hierarchical / left-right / top-down)
• ZONES: Describe each visual area with specific content, not vague descriptions
• LABELS: Use actual numbers, terms, metrics, quotes from the article — NOT generic placeholders
• COLORS: Specify hex codes from palette (or style default) with semantic meaning
• STYLE: Describe line treatment, texture, mood, character rendering per style rules
• ASPECT: Specify ratio (e.g., 16:9)

1. Apply defaults: composition requirements, character rendering, text guidelines, watermark
2. Backup rule: If prompt file exists, rename to prompts/NN-{type}-{slug}-backup-YYYYMMDD-HHMMSS.md

Verification ⛔: Before proceeding to 5.2, confirm ALL prompt files exist:

Prompt Files:
- prompts/01-infographic-overview.md ✓
- prompts/02-infographic-distillation.md ✓
...

DO NOT pass ad-hoc inline text to --prompt without first saving prompt files. The generation command should either use --promptfiles prompts/NN-{type}-{slug}.md or read the saved file content for --prompt.

Execution choice:

• If multiple illustrations already have saved prompt files and the task is now plain generation, use batch generation by default.
• Prefer the chosen backend's native batch / multi-task interface when available.
• If the backend has no native batch interface but the runtime can issue parallel tool calls, dispatch up to generation_batch_size tasks at a time. Default: 4. The current user request overrides EXTEND.md.
• Generate sequentially only when neither backend batch nor runtime parallel calls are available.
• Use subagents only when each illustration still needs separate prompt rewriting, style exploration, or other per-image reasoning before generation. Do not use subagents just to parallelize rendering.

CRITICAL - References in Frontmatter:

• Only add references field if files ACTUALLY EXIST in references/ directory
• If style/palette was extracted verbally (no file), append info to prompt BODY instead
• Before writing frontmatter, verify: test -f references/NN-ref-{slug}.png

5.2 Select Generation Skill

Follow the ## Image Generation Tools rule at the top of SKILL.md. Concretely:

• If imagegen is in your available-skills list (Codex), use it — invoke via the Skill tool with skill: "imagegen".
• Else if the EXTEND.md pin is available, use it.
• Else if exactly one non-native backend is installed, use it.
• Else, ask the user.

Do not generate SVG, HTML, or any code-based vector as a substitute for the raster image. If no raster backend can be resolved, ask the user how to proceed.

5.3 Process References ⚠️ REQUIRED if references saved in Step 1.0

DO NOT SKIP if user provided reference images. For each illustration with references:

1. VERIFY files exist first:

   test -f references/NN-ref-{slug}.png && echo "exists" || echo "MISSING"

• If file MISSING but in frontmatter → ERROR, fix frontmatter or remove references field
• If file exists → proceed with processing

1. Read prompt frontmatter for reference info
2. Process based on usage type:

1. Check image generation skill capability:

Verification: Before generating, confirm reference processing:

Reference Processing:
- Illustration 1: using 01-ref-brand.png (direct) ✓
- Illustration 2: extracted palette from 02-ref-style.png ✓

5.4 Apply Watermark (if enabled)

Add: Include a subtle watermark "[content]" at [position].

5.5 Generate

1. Build a generation task list from saved prompt files:

• prompt_file: {output-dir}/prompts/NN-{type}-{slug}.md
• output_file: {output-dir}/NN-{type}-{slug}.png
• aspect_ratio: from prompt frontmatter or prompt body
• refs: only verified direct references from prompt frontmatter

1. Backup rule: Before dispatching a task, if its output image already exists, rename it to NN-{type}-{slug}-backup-YYYYMMDD-HHMMSS.{ext}.
2. Dispatch tasks in batches:

• Native batch backend: send all eligible tasks, or chunks of generation_batch_size if the backend has a practical limit.
• Runtime parallel calls: issue up to generation_batch_size image calls concurrently, then continue with the next chunk.
• Sequential fallback: process one task at a time.

1. After each completed task, record: "Generated X/N: filename".
2. On failure: retry the failed task once from the same saved prompt file. Keep successful outputs and continue.

Step 6: Finalize

6.1 Update Article

Insert after corresponding paragraph, using path relative to article file:

Alt text: concise description in article's language.

6.2 Output Summary

Article Illustration Complete!

Article: [path]
Type: [type] | Density: [level] | Style: [style]
Location: [directory]
Images: X/N generated

Positions:
- 01-xxx.png → After "[Section]"
- 02-yyy.png → After "[Section]"

[If failures]
Failed:
- NN-zzz.png: [reason]