baoyu-cover-image

Name: baoyu-cover-image
Author: jimliu

byjimliu· 68 skills

Installs

29k

Stars

24k

Forks

2.7k

How to install baoyu-cover-image?

jimliu/baoyu-skills/baoyu-cover-image

$npx -y skills add jimliu/baoyu-skills --skill baoyu-cover-image

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/jimliu/baoyu-skills" --skill "jimliu/baoyu-skills/baoyu-cover-image"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/jimliu/baoyu-skills" that are relevant to the current task. Run `npx skills add "https://github.com/jimliu/baoyu-skills"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub

SKILL.md

1	# Cover Image Generator
2
3	Generate elegant cover images for articles with 5-dimensional customization.
4
5	## User Input Tools
6
7	When this skill prompts the user, follow this tool-selection rule (priority order):
8
9	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.
10	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.
11	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.
12
13	Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.
14
15	## Image Generation Tools
16
17	When this skill needs to render an image, resolve the backend in this order:
18
19	1. Current-request override — if the user names a specific backend in the current message, use it.
20	2. Saved preference — if `EXTEND.md` sets `preferred_image_backend` to a backend available right now, use it.
21	3. Auto-select (when the preference is `auto`, unset, or the pinned backend isn't available):
22	- Codex (`imagegen`) — first, inspect your available-skills / tool inventory. If a skill named `imagegen` is listed, you are running inside Codex and MUST use it: invoke via the `Skill` tool with `skill: "imagegen"`, passing the saved prompt file's content (plus output path and aspect ratio per Codex `imagegen`'s own args). Codex `imagegen` is the official raster backend in that runtime and outranks any non-native skill (e.g., `baoyu-image-gen`) unless the user has explicitly pinned a different `preferred_image_backend`.
23	- Codex via `codex exec` (`codex-imagegen`) — if the current runtime exposes no native `imagegen` skill but the `codex` CLI is on `PATH` with an active `codex login`, route through `baoyu-image-gen --provider codex-cli` (preferred), or — if baoyu-image-gen is unavailable — invoke the bundled wrapper directly. Details, parameters, and the runtime-discovery procedure live in [references/codex-imagegen.md](references/codex-imagegen.md) — load that file only when this branch is selected.
24	- Cursor (`GenerateImage`) — if the runtime exposes a native `GenerateImage` tool, you are running inside Cursor and it outranks any non-native skill the same way Codex `imagegen` does. Two hard caveats: (a) it has no aspect-ratio parameter — state the target aspect ratio / dimensions explicitly in the prompt text passed as `description`; (b) it does not accept an output directory — it saves to a tool-managed location, so after generation copy/move the file to the skill's expected output path (e.g., `outputs/.../NN-xxx.png`). Reference images go in `reference_image_paths`.
25	- Other runtime-native tools — if the runtime exposes a different native image tool (e.g., Hermes `image_generate`), use it the same way.
26	- Otherwise, if exactly one non-native backend is installed (e.g., `baoyu-image-gen`), use it.
27	- Otherwise (multiple non-native backends with no runtime-native tool), ask the user once — batch with any other initial questions.
28	4. If none are available, tell the user and ask how to proceed.
29
30	⛔ Never substitute SVG, HTML, canvas, or other code-based rendering for raster image generation. Codex `imagegen`'s own description says it should be used "when the output should be a bitmap asset rather than repo-native code or vector." If you cannot resolve a raster backend via step 3, fall through to step 4 and ask the user — do not silently emit SVG, write inline `<svg>` markup, or produce HTML/CSS art as a substitute. This applies even if the article/section seems "diagram-like": the consumer skill calling this rule has already decided that a raster image is what it needs.
31
32	⛔ Never repair rendered text by painting over a generated bitmap. Do not use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other programmatic overlay to cover, rewrite, erase, stroke, or replace title/subtitle text inside an already generated cover image. If text is wrong or unclear, regenerate from a corrected prompt, switch to a lower-text or no-title variant, or ask the user which imperfect candidate to keep.
33
34	Setting `preferred_image_backend: ask` forces the step-3 prompt every run regardless of available backends. Users change the pinned backend via the `## Changing Preferences` section below.
35
36	Prompt file requirement (hard): write each image's full, final prompt to a standalone file under `prompts/` (naming: `NN-{type}-[slug].md`) BEFORE invoking any backend. The backend receives the prompt file (or its content); the file is the reproducibility record and lets you switch backends without regenerating prompts.
37
38	Concrete tool names (`imagegen`, `GenerateImage`, `image_generate`, `baoyu-image-gen`) above are examples — substitute the local equivalents under the same rule.
39
40	## Confirmation Policy
41
42	Default behavior: confirm before generation.
43
44	- Treat explicit skill invocation, a file path, matched keywords/presets, `EXTEND.md` defaults, and any documented auto-selection as recommendation inputs only. None of them authorizes skipping confirmation.
45	- Do not start Step 3 or Step 4 until the user confirms the dimensions / aspect / language / backend choices.
46	- Skip confirmation only when the current request explicitly says to do so, for example: `--quick`, "直接生成", "不用确认", "跳过确认", "按默认出图", or equivalent wording. `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.
47	- If confirmation is skipped explicitly, state the assumed dimensions / aspect / language / backend in the next user-facing update before generating.
48
49	## Options
50
51	\| Option \| Description \|
52	\|--------\|-------------\|
53	\| `--type <name>` \| hero, conceptual, typography, metaphor, scene, minimal \|
54	\| `--palette <name>` \| warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone, macaron \|
55	\| `--rendering <name>` \| flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print \|
56	\| `--style <name>` \| Preset shorthand (see [Style Presets](references/style-presets.md)) \|
57	\| `--text <level>` \| none, title-only, title-subtitle, text-rich \|
58	\| `--mood <level>` \| subtle, balanced, bold \|
59	\| `--font <name>` \| clean, handwritten, serif, display \|
60	\| `--aspect <ratio>` \| 16:9 (default), 2.35:1, 4:3, 3:2, 1:1, 3:4 \|
61	\| `--lang <code>` \| Title language (en, zh, ja, etc.) \|
62	\| `--no-title` \| Alias for `--text none` \|
63	\| `--quick` \| Skip confirmation, use auto-selection \|
64	\| `--ref <files...>` \| Reference images for style/composition guidance \|
65
66	## Five Dimensions
67
68	\| Dimension \| Values \| Default \|
69	\|-----------\|--------\|---------\|
70	\| Type \| hero, conceptual, typography, metaphor, scene, minimal \| auto \|
71	\| Palette \| warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone, macaron \| auto \|
72	\| Rendering \| flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print \| auto \|
73	\| Text \| none, title-only, title-subtitle, text-rich \| title-only \|
74	\| Mood \| subtle, balanced, bold \| balanced \|
75	\| Font \| clean, handwritten, serif, display \| clean \|
76
77	Auto-selection rules: [references/auto-selection.md](references/auto-selection.md)
78
79	## Galleries
80
81	Types: hero, conceptual, typography, metaphor, scene, minimal
82	→ Details: [references/types.md](references/types.md)
83
84	Palettes: warm, elegant, cool, dark, earth, vivid, pastel, mono, retro, duotone, macaron
85	→ Details: [references/palettes/](references/palettes/)
86
87	Renderings: flat-vector, hand-drawn, painterly, digital, pixel, chalk, screen-print
88	→ Details: [references/renderings/](references/renderings/)
89
90	Text Levels: none (pure visual) \| title-only (default) \| title-subtitle \| text-rich (with tags)
91	→ Details: [references/dimensions/text.md](references/dimensions/text.md)
92
93	Mood Levels: subtle (low contrast) \| balanced (default) \| bold (high contrast)
94	→ Details: [references/dimensions/mood.md](references/dimensions/mood.md)
95
96	Fonts: clean (sans-serif) \| handwritten \| serif \| display (bold decorative)
97	→ Details: [references/dimensions/font.md](references/dimensions/font.md)
98
99	## File Structure
100
101	Output directory per `default_output_dir` preference:
102	- `same-dir`: `{article-dir}/`
103	- `imgs-subdir`: `{article-dir}/imgs/`
104	- `independent` (default): `cover-image/{topic-slug}/`
105
106	```
107	<output-dir>/
108	├── source-{slug}.{ext} # Source files
109	├── refs/ # Reference images (if provided)
110	│ ├── ref-01-{slug}.{ext}
111	│ └── ref-01-{slug}.md # Description file
112	├── prompts/cover.md # Generation prompt
113	└── cover.png # Output image
114	```
115
116	Slug: 2-4 words, kebab-case. Conflict: append `-YYYYMMDD-HHMMSS`
117
118	## Workflow
119
120	### Progress Checklist
121
122	```
123	Cover Image Progress:
124	- [ ] Step 0: Check preferences (EXTEND.md) ⛔ BLOCKING
125	- [ ] Step 1: Analyze content + save refs + determine output dir
126	- [ ] Step 2: Confirm options (6 dimensions) ⚠️ unless --quick
127	- [ ] Step 3: Create prompt
128	- [ ] Step 4: Generate image
129	- [ ] Step 5: Completion report
130	```
131
132	### Flow
133
134	```
135	Input → [Step 0: Preferences] ─┬─ Found → Continue
136	└─ Not found → First-Time Setup ⛔ BLOCKING → Save EXTEND.md → Continue
137	↓
138	Analyze + Save Refs → [Output Dir] → [Confirm: 6 Dimensions] → Prompt → Generate → Complete
139	↓
140	(skip if --quick or all specified)
141	```
142
143	### Step 0: Load Preferences ⛔ BLOCKING
144
145	Check EXTEND.md in priority order — the first one found wins:
146
147	\| Priority \| Path \| Scope \|
148	\|----------\|------\|-------\|
149	\| 1 \| `.baoyu-skills/baoyu-cover-image/EXTEND.md` \| Project \|
150	\| 2 \| `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-cover-image/EXTEND.md` \| XDG \|
151	\| 3 \| `$HOME/.baoyu-skills/baoyu-cover-image/EXTEND.md` \| User home \|
152
153	\| Result \| Action \|
154	\|--------\|--------\|
155	\| Found \| Load, display summary → Continue \|
156	\| Not found \| ⛔ Run first-time setup ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Save → Continue \|
157
158	CRITICAL: If not found, complete setup BEFORE any other steps or questions.
159
160	### Step 1: Analyze Content
161
162	1. Save reference images (if provided) → [references/workflow/reference-images.md](references/workflow/reference-images.md)
163	2. Save source content (if pasted, save to `source.md`)
164	3. Analyze content: topic, tone, keywords, visual metaphors
165	4. Deep analyze references ⚠️: Extract specific, concrete elements (see reference-images.md)
166	5. Detect language: Compare source, user input, EXTEND.md preference
167	6. Determine output directory: Per File Structure rules
168
169	⚠️ People in Reference Images:
170
171	If reference images contain people who should appear in the cover:
172
173	- Model supports `--ref` (default): Copy image to `refs/`, pass via `--ref` at generation. No description file needed — the model sees the face directly.
174	- 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.
175
176	See [reference-images.md](references/workflow/reference-images.md) for full decision table.
177
178	### Step 2: Confirm Options ⚠️
179
180	Hard gate: this step is mandatory per the [Confirmation Policy](#confirmation-policy) — Steps 3–4 cannot start until the user confirms here (or explicitly opts out with `--quick` / `quick_mode: true` / equivalent wording in the current request).
181
182	MUST use `AskUserQuestion` tool to present options as interactive selection — NOT plain text tables. Present up to 4 questions in a single `AskUserQuestion` call (Type, Palette, Rendering, Font + Settings). Each question shows the recommended option first with reason, followed by alternatives.
183
184	Full confirmation flow and question format: [references/workflow/confirm-options.md](references/workflow/confirm-options.md)
185
186	\| Condition \| Skipped \| Still Asked \|
187	\|-----------\|---------\|-------------\|
188	\| `--quick` or `quick_mode: true` \| 6 dimensions \| Aspect ratio (unless `--aspect`) \|
189	\| All 6 + `--aspect` specified \| All \| None \|
190
191	### Step 3: Create Prompt
192
193	Save to `prompts/cover.md`. Template: [references/workflow/prompt-template.md](references/workflow/prompt-template.md)
194
195	CRITICAL - References in Frontmatter:
196	- Files saved to `refs/` → Add to frontmatter `references` list
197	- Style extracted verbally (no file) → Omit `references`, describe in body
198	- Before writing → Verify: `test -f refs/ref-NN-{slug}.{ext}`
199
200	Reference elements in body MUST be detailed, prefixed with "MUST"/"REQUIRED", with integration approach.
201
202	### Step 4: Generate Image
203
204	1. Backup existing `cover.png` if regenerating
205	2. Select backend via the `## Image Generation Tools` rule at the top: use whatever is available; if multiple, ask the user once. Do this once per session before any generation.
206	3. Write the full final prompt to `prompts/01-cover-[slug].md` (hard requirement) BEFORE invoking the backend.
207	4. Process references from prompt frontmatter:
208	- `direct` usage → pass via `--ref` (use ref-capable backend)
209	- `style`/`palette` → extract traits, append to prompt
210	5. Generate: Call the chosen backend with the prompt file, output path, aspect ratio.
211	- `codex-imagegen`: see [references/codex-imagegen.md](references/codex-imagegen.md) for the invocation contract (preferred `baoyu-image-gen --provider codex-cli` path, runtime wrapper discovery, parameter notes, stdout schema, batch semantics).
212	- Codex `imagegen` (native) or other runtime-native tools / `baoyu-image-gen` skill: per the rule in `## Image Generation Tools` above.
213	6. On failure: auto-retry once
214
215	### Step 5: Completion Report
216
217	```
218	Cover Generated!
219
220	Topic: [topic]
221	Type: [type] \| Palette: [palette] \| Rendering: [rendering]
222	Text: [text] \| Mood: [mood] \| Font: [font] \| Aspect: [ratio]
223	Title: [title or "visual only"]
224	Language: [lang] \| Watermark: [enabled/disabled]
225	References: [N images or "extracted style" or "none"]
226	Location: [directory path]
227
228	Files:
229	✓ source-{slug}.{ext}
230	✓ prompts/cover.md
231	✓ cover.png
232	```
233
234	## Image Modification
235
236	\| Action \| Steps \|
237	\|--------\|-------\|
238	\| Regenerate \| Backup → Update prompt file FIRST → Regenerate \|
239	\| Change dimension \| Backup → Confirm new value → Update prompt → Regenerate \|
240
241	Text correction policy:
242
243	- If the title/subtitle is misspelled, garbled, hard to read, or visually weak, do not patch the bitmap with code.
244	- For text-correction regenerations, write a new prompt file and a new output path so the flawed candidate is preserved for comparison.
245	- Post-processing is limited to crop, resize, compression, or format conversion that does not alter text or the main composition.
246
247	## Composition Principles
248
249	- Whitespace: 40-60% breathing room
250	- Visual anchor: Main element centered or offset left
251	- Characters: Simplified silhouettes; NO realistic humans
252	- Title: Use exact title from user/source; never invent
253
254	## Changing Preferences
255
256	EXTEND.md lives at the path noted in Step 0. Three ways to change it:
257
258	- Edit directly — open EXTEND.md and change fields. Full schema: [references/config/preferences-schema.md](references/config/preferences-schema.md).
259	- Reconfigure interactively — delete EXTEND.md (or ask "reconfigure baoyu-cover-image preferences" / "重新配置"). The next run re-triggers first-time setup.
260	- Common one-line edits:
261	- `preferred_image_backend: auto` — default; runtime-native tool wins, falls back to the only installed backend, asks only if multiple non-native are present.
262	- `preferred_image_backend: codex-imagegen` — pin to Codex's built-in.
263	- `preferred_image_backend: baoyu-image-gen` — pin to the baoyu-image-gen skill.
264	- `preferred_image_backend: ask` — confirm backend every run.
265	- `watermark.enabled: true`, `preferred_type`, `preferred_palette`, `preferred_rendering`, `default_aspect`, `quick_mode: true`, `language` — shift the auto-selection defaults and confirmation flow.
266
267	## References
268
269	Dimensions: [text.md](references/dimensions/text.md) \| [mood.md](references/dimensions/mood.md) \| [font.md](references/dimensions/font.md)
270	Palettes: [references/palettes/](references/palettes/)
271	Renderings: [references/renderings/](references/renderings/)
272	Types: [references/types.md](references/types.md)
273	Auto-Selection: [references/auto-selection.md](references/auto-selection.md)
274	Style Presets: [references/style-presets.md](references/style-presets.md)
275	Compatibility: [references/compatibility.md](references/compatibility.md)
276	Visual Elements: [references/visual-elements.md](references/visual-elements.md)
277	Workflow: [confirm-options.md](references/workflow/confirm-options.md) \| [prompt-template.md](references/workflow/prompt-template.md) \| [reference-images.md](references/workflow/reference-images.md)
278	Config: [preferences-schema.md](references/config/preferences-schema.md) \| [first-time-setup.md](references/config/first-time-setup.md) \| [watermark-guide.md](references/config/watermark-guide.md)

6 picks

Type

Run `npx skills use "https://github.com/jimliu/baoyu-skills" --skill "jimliu/baoyu-skills/baoyu-cover-image"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the skills in "https://github.com/jimliu/baoyu-skills" that are relevant to the current task. Run `npx skills add "https://github.com/jimliu/baoyu-skills"` and select the relevant skills, then follow their instructions.

baoyu-cover-image

How to install baoyu-cover-image?

Related

baoyu-cover-image

How to install baoyu-cover-image?

Related