一键导入
edit-image
Edit images using AI (Gemini). Fix text, change colors, remove elements, or make other modifications while preserving the original style.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Edit images using AI (Gemini). Fix text, change colors, remove elements, or make other modifications while preserving the original style.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Critique book prose in the author's voice using patterns learned from his own git edit history (not a hand-written rubric). Use when asked to "voice-check", "punch up", "make this sound like me / like Vonnegut / like Cunk", or to review whether a passage is too pompous / cute / self-aware. Catches what the regex scanner (voice-check.py, ~1.4% of real edits) misses.
Review and improve QMD chapter writing quality by replacing boring/consultant text with Wishonia's deadpan alien voice, consolidating redundancy, and reducing word count. Use when asked to fix voice, make content funnier, remove jargon, or enforce the book's writing style.
Spawns parallel agents to review all paperback QMD files. Reads variable-resolved previews, flags judgment-required issues with REVIEW comments.
Automated book maintenance. Runs health checks, prioritizes work, and systematically fixes issues. Use when you want Codex to autonomously improve the book.
Check GitHub Actions workflow status, diagnose failures, fetch logs, and fix common build issues. Use when builds fail, deploys break, or you need to investigate CI/CD problems.
Critically analyze a calculated parameter for academic rigor. Checks methodology, identifies weaknesses, suggests improvements for economist audiences.
| name | edit-image |
| description | Edit images using AI (Gemini). Fix text, change colors, remove elements, or make other modifications while preserving the original style. |
| allowed-tools | ["AskUserQuestion","Bash","Read","Glob"] |
Edit an existing image using Gemini AI while preserving its overall style.
/edit-image assets/images/chart.jpg "Change the title to 'Updated Chart'"
/edit-image assets/images/diagram.png "Make the background white"
/edit-image @assets/images/poster.jpg "Remove the watermark"
Priority order:
assets/images/chart.jpg)@assets/images/file.png)git diff --name-only HEAD~3 | grep -E "\.(jpg|jpeg|png|webp)$" | head -1If no image found, ask user to specify.
Verify image exists:
ls -la "<image-path>"
If not provided in the command, use AskUserQuestion to ask what changes to make:
Common edit types:
Show preview of what will happen:
Image: <image-path>
Edit: <instructions>
Backup: Yes (original saved as <image>.backup)
Use AskUserQuestion to confirm:
After user confirms:
npx tsx scripts/images/edit-image.ts '<image-path>' '<edit-instructions>'
Options:
--output <path> - Save to different location instead of overwriting--no-backup - Don't create backup of original--no-transcript - Skip transcript extraction after editExamples:
# Basic edit (overwrites original, creates .backup)
npx tsx scripts/images/edit-image.ts 'assets/images/chart.jpg' 'Change title to New Title'
# Save to new file
npx tsx scripts/images/edit-image.ts 'assets/images/old.png' 'Remove watermark' --output 'assets/images/new.png'
# No backup
npx tsx scripts/images/edit-image.ts 'assets/images/temp.jpg' 'Fix typo' --no-backup
IMPORTANT: Use single quotes around paths and instructions to prevent bash interpretation.
Report:
For fixing the same text across multiple images, use the fix-image-text script:
# Search for images with specific text
npx tsx scripts/images/fix-image-text.ts --search "oldtext"
# Edit all matching images
npx tsx scripts/images/fix-image-text.ts --search "oldtext" --replace "newtext" --edit
# Remove text from all matching images
npx tsx scripts/images/fix-image-text.ts --search "watermark" --remove --edit
Requires GOOGLE_GENERATIVE_AI_API_KEY environment variable.
Edit doesn't change what you wanted:
Image quality degrades:
"No edited image returned":