zhens
/
JimLiu-baoyu-skills
mirror of https://github.com/JimLiu/baoyu-skills.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

feat: Update image generation steps in article-illustrator, cover-image, and xhs-images skills for improved user guidance

This commit is contained in:
Jim Liu 宝玉 2026-01-15 10:58:20 -06:00
parent d4070b19d5
commit 3fddcc0e6a
4 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -139,3 +139,4 @@ vite.config.js.timestamp-*
vite.config.ts.timestamp-* vite.config.ts.timestamp-*
tests-data/ tests-data/
.DS_Store

19
skills/article-illustrator/SKILL.md
View File

@ -201,17 +201,16 @@ Style notes: [specific style characteristics]
### Step 5: Generate Images ### Step 5: Generate Images
For each illustration, call: **Image Generation Skill Selection**:
1. Check available image generation skills
2. If multiple skills available, ask user to choose
```bash **Generation Flow**:
/gemini-web --promptfiles [SKILL_ROOT]/skills/article-illustrator/prompts/system.md [ARTICLE_DIR]/imgs/prompts/illustration-[slug].md --image [ARTICLE_DIR]/imgs/illustration-[slug].png 1. Call selected image generation skill with prompt file and output path
``` 2. Generate images sequentially
3. After each image, output progress: "Generated X/N"
Generation flow: 4. On failure, auto-retry once
1. Generate images sequentially 5. If retry fails, log reason, continue to next
2. After each image, output progress: "Generated X/N"
3. On failure, auto-retry once
4. If retry fails, log reason, continue to next
### Step 6: Update Article ### Step 6: Update Article

9
skills/cover-image/SKILL.md
View File

@ -191,11 +191,12 @@ Note: No title text, pure visual illustration only.
### Step 5: Generate Image ### Step 5: Generate Image
Call gemini-web to generate the cover: **Image Generation Skill Selection**:
1. Check available image generation skills
2. If multiple skills available, ask user to choose
```bash **Generation**:
/gemini-web --promptfiles [SKILL_ROOT]/skills/cover-image/prompts/system.md [PROMPT_PATH] --image [OUTPUT_PATH] Call selected image generation skill with prompt file and output path.
```
### Step 6: Output Summary ### Step 6: Output Summary

17
skills/xhs-images/SKILL.md
View File

@ -328,16 +328,15 @@ Style notes: [style-specific characteristics]
| `comparison` | Two-column split, clear divider, mirrored structure left/right | | `comparison` | Two-column split, clear divider, mirrored structure left/right |
| `flow` | Horizontal or vertical flow with arrows, connected nodes/steps | | `flow` | Horizontal or vertical flow with arrows, connected nodes/steps |
Then generate using: **Image Generation Skill Selection**:
1. Check available image generation skills
2. If multiple skills available, ask user to choose
```bash **Generation Flow**:
/gemini-web --promptfiles [SKILL_ROOT]/skills/xhs-images/prompts/system.md [TARGET_DIR]/prompts/01-cover.md --image [TARGET_DIR]/01-cover.png 1. Call selected image generation skill with prompt file and output path
``` 2. Confirm generation success
3. Report progress: "Generated X/N"
After each image: 4. Continue to next
1. Confirm generation success
2. Report progress: "Generated X/N"
3. Continue to next
### Step 5: Completion Report ### Step 5: Completion Report