
Imgcli
- 1 installs
- 12 repo stars
- Updated March 13, 2026
- geekjourneyx/imgcli
Run the imgcli tool for agent-native image processing: inspection, format conversion, fixed-layout card composition, platform variant export, watermarking, PDF packaging, and vertical stitching.
About
Guides an agent to execute imgcli for processing existing images with machine-readable JSON output, covering normalization, composition, padding to platform presets, and packaging. A developer uses it to inspect, transform, lay out, and export images inside an agent workflow, not to generate images.
- Does not generate images; handles inspection, layout, packaging, and export
- Defaults to JSON output and checks the binary is built before running
Imgcli by the numbers
- 1 all-time installs (skills.sh)
- Ranked #1,200 of 1,335 Generative Media skills by installs in the Skillselion catalog
- Data as of Jul 24, 2026 (Skillselion catalog sync)
npx skills add https://github.com/geekjourneyx/imgcli --skill imgcliAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1 |
|---|---|
| repo stars | ★ 12 |
| Last updated | March 13, 2026 |
| Repository | geekjourneyx/imgcli ↗ |
What it does
Run the imgcli tool for agent-native image processing: inspection, format conversion, fixed-layout card composition, platform variant export, watermarking, PDF packaging, and vertical stitching.
Files
imgcli
用于指导 Agent 直接执行 imgcli,而不是解释底层图像算法实现。
项目边界
imgcli不负责生成图片。- 图片生成应由外部工具完成,例如 Gemini、GPT Image 或其他 provider CLI/API。
imgcli负责对已经存在的图片做检查、加工、排版、打包和导出。
执行前检查
1. 先检查是否已构建:imgcli version 或 ./bin/imgcli version 2. 如果未安装但仓库存在,优先执行:
make build
./bin/imgcli version3. 默认使用 JSON 输出,不要关闭 --json 4. 输入路径必须存在;输出扩展名必须与目标格式匹配
常用工作流
Inspect
./bin/imgcli inspect \
--input input.jpg \
--hash \
--color-stats可选:
--input-dir ./images--limit 10
Compose
./bin/imgcli compose \
--input input.jpg \
--output poster.jpg \
--width 1080 \
--height 1440 \
--layout poster \
--title "Launch Day" \
--subtitle "A fixed-layout creator card"可选:
--logo brand.png--badge NEW--background-color '#f3efe7'--safe-area 64,64,64,64
Convert
./bin/imgcli convert \
--input alpha.png \
--output out.jpg \
--flatten-background "#ffffff" \
--max-width 1600 \
--quality 82 \
--strip-metadataRun
./bin/imgcli run \
--recipe recipe.json \
--dry-run
./bin/imgcli run \
--recipe recipe.json引用规则:
input:<name>引用顶层输入step:<id>引用前置 step 产出的文件
Variants
./bin/imgcli variants \
--input poster.jpg \
--output-dir dist \
--preset-set creator-basic可选:
--preset xiaohongshu --preset wechat_cover--background blur|solid--filename-template '{base}_{preset}{ext}'
SmartPad
./bin/imgcli smartpad \
--input input.jpg \
--output output.jpg \
--preset xiaohongshu可选:
--background blur|solid--blur-sigma 5--quality 85
Images to PDF
./bin/imgcli topdf \
--input page1.jpg \
--input page2.jpg \
--output bundle.pdf \
--watermark-text "internal" \
--watermark-position tile可选:
--input-dir ./images--watermark-opacity 0.25--watermark-size 42
Vertical Stitch
./bin/imgcli stitch \
--input a.jpg \
--input b.jpg \
--output stitched.jpg \
--width 1080可选:
--input-dir ./images--part-height-limit 65535--quality 85
真实烟测
如果本机已经配置 baoyu-image-gen,执行:
make real-smoke该流程会:
- 生成 3 张真实测试图
- 跑通
inspect - 跑通
compose - 跑通
convert - 跑通
variants - 跑通
run - 跑通
smartpad、topdf、stitch - 校验输出文件类型并打印产物目录
输出契约
成功:
{"ok":true,"command":"smartpad","data":{}}失败:
{"error":"reason","code":"INVALID_ARGUMENT","exit_code":2}失败时最小处理
PRESET_NOT_FOUND:检查--presetINVALID_ARGUMENT:检查必填 flag 与输入模式冲突CONFIG_ERROR:检查--recipe文件扩展名和 JSON/YAML 语法PLAN_INVALID:检查 step 引用、重复 step id、必填字段OUTPUT_CONFLICT:检查 recipe 是否把多个 step 写到同一路径,或覆盖顶层输入DECODE_FAILED:检查图片是否损坏或格式不支持PDF_WRITE_FAILED:检查输出路径是否可写CANVAS_TOO_LARGE:减小--width或调低分卷阈值