← 返回 Skills 市场
Baoyu Compress Image
作者
Jim Liu 宝玉
· GitHub ↗
· v1.117.2
· MIT-0
2111
总下载
0
收藏
49
当前安装
7
版本数
在 OpenClaw 中安装
/install baoyu-compress-image
功能描述
Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or red...
安全使用建议
Install only if you are comfortable with a compressor that changes files by default. Use --keep for important originals, test on a copy before recursive directory runs, and be careful when converting to the same format because the original file can be replaced.
能力评估
Purpose & Capability
The stated purpose is image compression/conversion, and the code only handles user-supplied image files or directories using expected image tooling. The default behavior can modify source filenames or replace same-format outputs, which is relevant but purpose-aligned.
Instruction Scope
The trigger phrases match image compression and conversion tasks. Documentation discloses file/directory use, the --keep option, and an example saying the default replaces the original, though the risk could be more prominent for directory and same-format processing.
Install Mechanism
No hidden installer, package-install script, persistence hook, or privilege escalation was found. The skill declares bun or npx as runtime requirements.
Credentials
Filesystem access is limited to the specified input path plus documented optional preference paths; there is no credential access, network exfiltration, broad local indexing, or unrelated data flow in the artifacts.
Persistence & Privilege
No background worker, durable agent behavior, privilege escalation, account access, or session/profile handling was found.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install baoyu-compress-image - 安装完成后,直接呼叫该 Skill 的名称或使用
/baoyu-compress-image触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.117.2
## 1.117.2 - 2026-05-17
### Documentation
- `baoyu-cover-image`: ban programmatic text repair on generated bitmaps — disallow ImageMagick / Pillow / Canvas / SVG / HTML overlays to cover, rewrite, or replace title/subtitle text; regenerate from a corrected prompt or switch to a lower-text or no-title variant instead
- `baoyu-article-illustrator`, `baoyu-comic`, `baoyu-image-cards`, `baoyu-xhs-images`, `baoyu-infographic`, `baoyu-slide-deck`: sync the same text-repair ban with skill-specific text categories (labels/captions, dialogue/sound effects, titles/body/tags, headings/data values, slide titles/bullets)
v1.115.4
### Documentation
- Image generation backend selection: emphasize Codex `imagegen` as the priority runtime-native tool (invoke via the `Skill` tool with `skill: "imagegen"`) and forbid SVG/HTML/canvas substitution when no raster backend can be resolved — fall through to asking the user instead of silently emitting code-based art. Updated in `docs/image-generation-tools.md` and inlined into `baoyu-article-illustrator`, `baoyu-comic`, `baoyu-cover-image`, `baoyu-image-cards`, `baoyu-infographic`, `baoyu-slide-deck`, and `baoyu-xhs-images`.
v1.103.2
- Clarified EXTEND.md preference lookup order for configuration: project, XDG config, then user home.
- Simplified and reformatted the preferences section for easier reference.
- Removed redundant shell and PowerShell code snippets; replaced with a streamlined table.
- No changes to functionality or options.
v1.103.1
## 1.103.1 - 2026-04-13
### Fixes
- `baoyu-markdown-to-html`: decode HTML entities and strip tags from article summary
- `baoyu-post-to-weibo`: decode HTML entities and strip tags from article summary
v1.103.0
## 1.103.0 - 2026-04-12
### Features
- baoyu-diagram: add multi-diagram mode for article-wide diagram generation
### Fixes
- baoyu-article-illustrator: prevent color names and hex codes from appearing as visible text in generated images
- baoyu-cover-image: prevent color names and hex codes from appearing as visible text in generated images
- baoyu-image-cards: prevent color names from appearing as visible text in generated images
- baoyu-post-to-wechat: decode HTML entities and strip tags from article summary
v1.60.0
## 1.60.0 - 2026-03-11
### Features
- `baoyu-url-to-markdown`: support reusing existing Chrome CDP instances and fix port detection order
### Fixes
- `baoyu-post-to-x`: add missing `fs` import in x-article
### Refactor
- Unify all CDP skills to use shared `baoyu-chrome-cdp` package with vendored copies
- Simplify CLAUDE.md, move detailed documentation to `docs/` directory
- Publish skills directly from synced vendor, removing separate artifact preparation step
v1.0.0
- Initial release of image compression skill.
- Compresses images to WebP (default), PNG, or JPEG, with automatic tool selection.
- Command-line interface supports input files or directories, output format, quality, and recursive processing.
- Preference and configuration support through EXTEND.md files at project or user level.
- Supports JSON output and option to keep original files.
元数据
常见问题
Baoyu Compress Image 是什么?
Compresses images to WebP (default) or PNG with automatic tool selection. Use when user asks to "compress image", "optimize image", "convert to webp", or red... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 2111 次。
如何安装 Baoyu Compress Image?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install baoyu-compress-image」即可一键安装,无需额外配置。
Baoyu Compress Image 是免费的吗?
是的,Baoyu Compress Image 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Baoyu Compress Image 支持哪些平台?
Baoyu Compress Image 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Baoyu Compress Image?
由 Jim Liu 宝玉(@jimliu)开发并维护,当前版本 v1.117.2。
推荐 Skills