Cover Image Generator
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 title/subtitle text inside an already generated cover image. Regenerate from a corrected prompt, switch to a lower-text or no-title variant, 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.
Confirmation Policy
Default: confirm before generation.
- Explicit skill invocation, a file path, matched keywords/presets,
EXTEND.md defaults, and any documented auto-selection are recommendation inputs only — none authorizes skipping confirmation.
- Do not start Step 3 or Step 4 until the user confirms the dimensions / aspect / language / backend choices.
- Skip confirmation only when the current request explicitly says so:
--quick, "直接生成", "不用确认", "跳过确认", "按默认出图", or equivalent. quick_mode: true in EXTEND.md counts as a standing explicit opt-out — set it only when you want every run to skip Step 2.
- When skipped, state the assumed dimensions / aspect / language / backend in the next user-facing update before generating.
Options
| Option |
Description |
--type <name> |
hero, conceptual, typography, metaphor, scene, minimal |
--palette <name> |
warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone, macaron |
--rendering <name> |
flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print |
--style <name> |
Preset shorthand (see Style Presets) |
--text <level> |
none, title-only, title-subtitle, text-rich |
--mood <level> |
subtle, balanced, bold |
--font <name> |
clean, handwritten, serif, display |
--aspect <ratio> |
16:9 (default), 2.35:1, 4:3, 3:2, 1:1, 3:4 |
--lang <code> |
Title language (en, zh, ja, etc.) |
--no-title |
Alias for --text none |
--quick |
Skip confirmation (and first-time setup when no EXTEND.md), use auto-selection |
--ref <files...> |
Reference images for style/composition guidance |
Five Dimensions
| Dimension |
Default |
Details |
| Type |
auto |
types.md |
| Palette |
auto |
palettes/ |
| Rendering |
auto |
renderings/ |
| Text |
title-only |
dimensions/text.md |
| Mood |
balanced |
dimensions/mood.md |
| Font |
clean |
dimensions/font.md |
Values are listed in Options. Auto-selection: references/auto-selection.md. Compatibility matrices: references/compatibility.md. Icon vocabulary: references/visual-elements.md.
File Structure
Output directory per default_output_dir preference:
same-dir: {article-dir}/
imgs-subdir: {article-dir}/imgs/
independent (default): cover-image/{topic-slug}/
<output-dir>/
├── source-{slug}.{ext} # Source files
├── refs/ # Reference images (if provided)
│ ├── ref-01-{slug}.{ext}
│ └── ref-01-{slug}.md # Description file
├── prompts/cover.md # Generation prompt
└── cover.png # Output image
Slug: 2-4 words, kebab-case. Conflict: append -YYYYMMDD-HHMMSS
Workflow
Cover Image Progress:
- [ ] Step 0: Check preferences (EXTEND.md) ⛔ BLOCKING unless --quick
- [ ] Step 1: Analyze content + save refs + determine output dir
- [ ] Step 2: Confirm options (6 dimensions) ⚠️ unless --quick
- [ ] Step 3: Create prompt
- [ ] Step 4: Generate image
- [ ] Step 5: Completion report
Step 0: Load Preferences ⛔ BLOCKING
First match wins:
| Priority |
Path |
Scope |
| 1 |
.baoyu-skills/baoyu-cover-image/EXTEND.md |
Project |
| 2 |
${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-cover-image/EXTEND.md |
XDG |
| 3 |
$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md |
User home |
- Found → load, display summary.
- Not found → ⛔ run first-time-setup and save, BEFORE any other step or question.
- Not found + current request opts out of confirmation (
--quick or equivalent wording per the Confirmation Policy) → skip setup and use built-in defaults: no watermark, dimensions auto-selected, default_output_dir: independent, language from content. Do not prompt, do not create EXTEND.md. For a run with no one to answer (cron, CI), also pass --aspect so Step 2 asks nothing.
Step 1: Analyze Content
- Save reference images (if provided) → references/workflow/reference-images.md
- Save source content (if pasted, save to
source.md)
- Analyze content: topic, tone, keywords, visual metaphors
- Deep analyze references ⚠️: extract specific, concrete elements (see reference-images.md)
- Detect language: compare source, user input, EXTEND.md preference
- Determine output directory per File Structure
People in reference images who should appear in the cover:
- Model supports
--ref (default): copy image to refs/, pass via --ref at generation. No description file needed.
- Model does NOT support
--ref (Jimeng, Seedream 3.0): create refs/ref-NN-{slug}.md with per-character description (hair, glasses, skin tone, clothing); embed as MUST/REQUIRED instructions in prompt text.
Step 2: Confirm Options ⚠️
Hard gate per the Confirmation Policy (opt-out: --quick / quick_mode: true / equivalent wording in the current request).
MUST use AskUserQuestion (interactive selection, not plain-text tables): up to 4 questions in one call (Type, Palette, Rendering, Font + Settings), each with the recommended option first plus reason. --quick / quick_mode still asks aspect ratio unless --aspect is given; all 6 dimensions + --aspect specified skips everything. Full flow: references/workflow/confirm-options.md.
Step 3: Create Prompt
Save to prompts/cover.md per references/workflow/prompt-template.md.
- Frontmatter
references: only files saved to refs/ (verify test -f refs/ref-NN-{slug}.{ext}); verbally extracted style → omit references, describe in body.
- Reference elements in the body MUST be detailed, prefixed with "MUST"/"REQUIRED", with an integration approach.
Step 4: Generate Image
- Backup existing
cover.png if regenerating
- Select backend once per session via
## Image Generation Tools.
- Write the full final prompt to
prompts/01-cover-[slug].md (hard requirement) BEFORE invoking the backend.
- Process references from prompt frontmatter:
direct → pass via --ref (ref-capable backend); style/palette → extract traits, append to prompt.
- Generate with the prompt file, output path, aspect ratio. For
codex-imagegen, see references/codex-imagegen.md.
- On failure: auto-retry once
Step 5: Completion Report
Cover Generated!
Topic: [topic]
Type: [type] | Palette: [palette] | Rendering: [rendering]
Text: [text] | Mood: [mood] | Font: [font] | Aspect: [ratio]
Title: [title or "visual only"]
Language: [lang] | Watermark: [enabled/disabled]
References: [N images or "extracted style" or "none"]
Location: [directory path]
Files:
✓ source-{slug}.{ext}
✓ prompts/cover.md
✓ cover.png
Image Modification
| Action |
Steps |
| Regenerate |
Backup → Update prompt file FIRST → Regenerate |
| Change dimension |
Backup → Confirm new value → Update prompt → Regenerate |
Text correction: never patch a misspelled, garbled, or weak title/subtitle 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.
Composition Principles
- Whitespace: 40-60% breathing room
- Visual anchor: Main element centered or offset left
- Characters: Simplified silhouettes; NO realistic humans
- Title: Use exact title from user/source; never invent
Changing Preferences
EXTEND.md lives at the path from Step 0. Edit it directly (schema: references/config/preferences-schema.md; watermark: references/config/watermark-guide.md), or delete it / ask "reconfigure baoyu-cover-image 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)
watermark.enabled: true, preferred_type, preferred_palette, preferred_rendering, default_aspect, quick_mode: true, language — shift auto-selection defaults and the confirmation flow.
1---2name: baoyu-cover-image3description: Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 11 color palettes and 7 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".4version: 1.117.55metadata:6 source: https://skillmd.com/skills/tuyv/baoyu-cover-image7 openclaw:8 homepage: https://github.com/JimLiu/baoyu-skills#baoyu-cover-image9---1011# Cover Image Generator1213## User Input Tools1415When this skill prompts the user, follow this tool-selection rule (priority order):16171. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.182. **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.193. **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.2021Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.2223## Image Generation Tools2425Resolve the image backend in this order:26271. **User names a backend** in the current message → use it.282. **`preferred_image_backend`** in `EXTEND.md` names a backend available now → use it. `ask` means ask every run.293. **Auto-select** (preference `auto`, unset, or the pinned backend is unavailable), first match wins:30 - **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`.31 - **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.32 - **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`.33 - **Other runtime-native image tool** (e.g., Hermes `image_generate`) → use it the same way.34 - Exactly one non-native backend installed (e.g., `baoyu-image-gen`) → use it.35 - Several non-native backends → ask the user once, batched with other initial questions.364. **None available** → tell the user and ask how to proceed.3738**⛔ 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 4.3940**⛔ 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 title/subtitle text inside an already generated cover image. Regenerate from a corrected prompt, switch to a lower-text or no-title variant, or ask the user which imperfect candidate to keep.4142**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.4344Change the pinned backend via `## Changing Preferences` below. Tool names above are examples; use the local equivalent in other runtimes.4546## Confirmation Policy4748Default: **confirm before generation**.4950- Explicit skill invocation, a file path, matched keywords/presets, `EXTEND.md` defaults, and any documented auto-selection are recommendation inputs only — none authorizes skipping confirmation.51- Do not start Step 3 or Step 4 until the user confirms the dimensions / aspect / language / backend choices.52- Skip confirmation only when the current request explicitly says so: `--quick`, "直接生成", "不用确认", "跳过确认", "按默认出图", or equivalent. `quick_mode: true` in `EXTEND.md` counts as a standing explicit opt-out — set it only when you want every run to skip Step 2.53- When skipped, state the assumed dimensions / aspect / language / backend in the next user-facing update before generating.5455## Options5657| Option | Description |58|--------|-------------|59| `--type <name>` | hero, conceptual, typography, metaphor, scene, minimal |60| `--palette <name>` | warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone, macaron |61| `--rendering <name>` | flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print |62| `--style <name>` | Preset shorthand (see [Style Presets](references/style-presets.md)) |63| `--text <level>` | none, title-only, title-subtitle, text-rich |64| `--mood <level>` | subtle, balanced, bold |65| `--font <name>` | clean, handwritten, serif, display |66| `--aspect <ratio>` | 16:9 (default), 2.35:1, 4:3, 3:2, 1:1, 3:4 |67| `--lang <code>` | Title language (en, zh, ja, etc.) |68| `--no-title` | Alias for `--text none` |69| `--quick` | Skip confirmation (and first-time setup when no EXTEND.md), use auto-selection |70| `--ref <files...>` | Reference images for style/composition guidance |7172## Five Dimensions7374| Dimension | Default | Details |75|-----------|---------|---------|76| **Type** | auto | [types.md](references/types.md) |77| **Palette** | auto | [palettes/](references/palettes/) |78| **Rendering** | auto | [renderings/](references/renderings/) |79| **Text** | title-only | [dimensions/text.md](references/dimensions/text.md) |80| **Mood** | balanced | [dimensions/mood.md](references/dimensions/mood.md) |81| **Font** | clean | [dimensions/font.md](references/dimensions/font.md) |8283Values are listed in Options. Auto-selection: [references/auto-selection.md](references/auto-selection.md). Compatibility matrices: [references/compatibility.md](references/compatibility.md). Icon vocabulary: [references/visual-elements.md](references/visual-elements.md).8485## File Structure8687Output directory per `default_output_dir` preference:88- `same-dir`: `{article-dir}/`89- `imgs-subdir`: `{article-dir}/imgs/`90- `independent` (default): `cover-image/{topic-slug}/`9192```93<output-dir>/94├── source-{slug}.{ext} # Source files95├── refs/ # Reference images (if provided)96│ ├── ref-01-{slug}.{ext}97│ └── ref-01-{slug}.md # Description file98├── prompts/cover.md # Generation prompt99└── cover.png # Output image100```101102**Slug**: 2-4 words, kebab-case. Conflict: append `-YYYYMMDD-HHMMSS`103104## Workflow105106```107Cover Image Progress:108- [ ] Step 0: Check preferences (EXTEND.md) ⛔ BLOCKING unless --quick109- [ ] Step 1: Analyze content + save refs + determine output dir110- [ ] Step 2: Confirm options (6 dimensions) ⚠️ unless --quick111- [ ] Step 3: Create prompt112- [ ] Step 4: Generate image113- [ ] Step 5: Completion report114```115116### Step 0: Load Preferences ⛔ BLOCKING117118First match wins:119120| Priority | Path | Scope |121|----------|------|-------|122| 1 | `.baoyu-skills/baoyu-cover-image/EXTEND.md` | Project |123| 2 | `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-cover-image/EXTEND.md` | XDG |124| 3 | `$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md` | User home |125126- **Found** → load, display summary.127- **Not found** → ⛔ run [first-time-setup](references/config/first-time-setup.md) and save, BEFORE any other step or question.128- **Not found + current request opts out of confirmation** (`--quick` or equivalent wording per the [Confirmation Policy](#confirmation-policy)) → skip setup and use built-in defaults: no watermark, dimensions auto-selected, `default_output_dir: independent`, language from content. Do not prompt, do not create EXTEND.md. For a run with no one to answer (cron, CI), also pass `--aspect` so Step 2 asks nothing.129130### Step 1: Analyze Content1311321. **Save reference images** (if provided) → [references/workflow/reference-images.md](references/workflow/reference-images.md)1332. **Save source content** (if pasted, save to `source.md`)1343. **Analyze content**: topic, tone, keywords, visual metaphors1354. **Deep analyze references** ⚠️: extract specific, concrete elements (see reference-images.md)1365. **Detect language**: compare source, user input, EXTEND.md preference1376. **Determine output directory** per File Structure138139**People in reference images** who should appear in the cover:140- **Model supports `--ref`** (default): copy image to `refs/`, pass via `--ref` at generation. No description file needed.141- **Model does NOT support `--ref`** (Jimeng, Seedream 3.0): create `refs/ref-NN-{slug}.md` with per-character description (hair, glasses, skin tone, clothing); embed as MUST/REQUIRED instructions in prompt text.142143### Step 2: Confirm Options ⚠️144145**Hard gate** per the [Confirmation Policy](#confirmation-policy) (opt-out: `--quick` / `quick_mode: true` / equivalent wording in the current request).146147**MUST use `AskUserQuestion`** (interactive selection, not plain-text tables): up to 4 questions in one call (Type, Palette, Rendering, Font + Settings), each with the recommended option first plus reason. `--quick` / `quick_mode` still asks aspect ratio unless `--aspect` is given; all 6 dimensions + `--aspect` specified skips everything. Full flow: [references/workflow/confirm-options.md](references/workflow/confirm-options.md).148149### Step 3: Create Prompt150151Save to `prompts/cover.md` per [references/workflow/prompt-template.md](references/workflow/prompt-template.md).152153- Frontmatter `references`: only files saved to `refs/` (verify `test -f refs/ref-NN-{slug}.{ext}`); verbally extracted style → omit `references`, describe in body.154- Reference elements in the body MUST be detailed, prefixed with "MUST"/"REQUIRED", with an integration approach.155156### Step 4: Generate Image1571581. **Backup existing** `cover.png` if regenerating1592. **Select backend** once per session via `## Image Generation Tools`.1603. **Write the full final prompt** to `prompts/01-cover-[slug].md` (hard requirement) BEFORE invoking the backend.1614. **Process references** from prompt frontmatter: `direct` → pass via `--ref` (ref-capable backend); `style`/`palette` → extract traits, append to prompt.1625. **Generate** with the prompt file, output path, aspect ratio. For `codex-imagegen`, see [references/codex-imagegen.md](references/codex-imagegen.md).1636. On failure: auto-retry once164165### Step 5: Completion Report166167```168Cover Generated!169170Topic: [topic]171Type: [type] | Palette: [palette] | Rendering: [rendering]172Text: [text] | Mood: [mood] | Font: [font] | Aspect: [ratio]173Title: [title or "visual only"]174Language: [lang] | Watermark: [enabled/disabled]175References: [N images or "extracted style" or "none"]176Location: [directory path]177178Files:179✓ source-{slug}.{ext}180✓ prompts/cover.md181✓ cover.png182```183184## Image Modification185186| Action | Steps |187|--------|-------|188| **Regenerate** | Backup → Update prompt file FIRST → Regenerate |189| **Change dimension** | Backup → Confirm new value → Update prompt → Regenerate |190191Text correction: never patch a misspelled, garbled, or weak title/subtitle 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.192193## Composition Principles194195- **Whitespace**: 40-60% breathing room196- **Visual anchor**: Main element centered or offset left197- **Characters**: Simplified silhouettes; NO realistic humans198- **Title**: Use exact title from user/source; never invent199200## Changing Preferences201202EXTEND.md lives at the path from **Step 0**. Edit it directly (schema: [references/config/preferences-schema.md](references/config/preferences-schema.md); watermark: [references/config/watermark-guide.md](references/config/watermark-guide.md)), or delete it / ask "reconfigure baoyu-cover-image preferences" / "重新配置" to re-run first-time setup. Common edits:203204- `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)205- `watermark.enabled: true`, `preferred_type`, `preferred_palette`, `preferred_rendering`, `default_aspect`, `quick_mode: true`, `language` — shift auto-selection defaults and the confirmation flow.