Word Format
yeap531/word-format-skill
把一份参考 Word (.docx) 的排版样式（字体/字号/缩进/行距/对齐/页面设置/样式表/主题）复刻到新内容上。当用户要求「按某个 .docx 模板排版」「在已有文档基础上续写」「修复后半部分排版混乱」「统一字体字号缩进」等场景时使用。仅在 macOS 工作（依赖 Microsoft Word + 浏览器 + System Events 的 UI 自动化）。
Convert images between common formats on macOS, especially SVG/PNG/ICO/ICNS/JPEG/WebP/PDF, using installed local tools such as ImageMagick, rsvg-convert, sips, qlmanage, and iconutil.
Install Image Converter
$ npx skills add penwyp/ClaudePreference --skill image-converter -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install penwyp/ClaudePreference image-converter --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/penwyp/ClaudePreference.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/image-converter .claude/skills/image-converter && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "image-converter" agent skill from https://github.com/penwyp/ClaudePreference/tree/main/skills/image-converter into .claude/skills/image-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-converter", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/penwyp/ClaudePreference/tree/main/skills/image-converterType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add penwyp/ClaudePreference --skill image-converter -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install penwyp/ClaudePreference image-converter --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/penwyp/ClaudePreference.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/image-converter .agents/skills/image-converter && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "image-converter" agent skill from https://github.com/penwyp/ClaudePreference/tree/main/skills/image-converter into .agents/skills/image-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-converter", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add penwyp/ClaudePreference --skill image-converter -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install penwyp/ClaudePreference image-converter --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/penwyp/ClaudePreference.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/image-converter .cursor/skills/image-converter && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "image-converter" agent skill from https://github.com/penwyp/ClaudePreference/tree/main/skills/image-converter into .cursor/skills/image-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-converter", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/penwyp/ClaudePreference.git --path skills/image-converter--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add penwyp/ClaudePreference --skill image-converter -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install penwyp/ClaudePreference image-converter --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/penwyp/ClaudePreference.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/image-converter .gemini/skills/image-converter && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "image-converter" agent skill from https://github.com/penwyp/ClaudePreference/tree/main/skills/image-converter into .gemini/skills/image-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-converter", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install penwyp/ClaudePreference image-converterInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add penwyp/ClaudePreference --skill image-converter -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/penwyp/ClaudePreference.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/image-converter .github/skills/image-converter && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "image-converter" agent skill from https://github.com/penwyp/ClaudePreference/tree/main/skills/image-converter into .github/skills/image-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-converter", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add penwyp/ClaudePreference --skill image-converter -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install penwyp/ClaudePreference image-converter --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/penwyp/ClaudePreference.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/image-converter .opencode/skills/image-converter && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "image-converter" agent skill from https://github.com/penwyp/ClaudePreference/tree/main/skills/image-converter into .opencode/skills/image-converter/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "image-converter", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
image-converter- GitHub stars
- 136
- Token cost
- ~955 tokens
- SKILL.md length
- 285 words
- Files
- 3 (incl. scripts)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Convert images between common formats on macOS, especially SVG/PNG/ICO/ICNS/JPEG/WebP/PDF, using installed local tools such as ImageMagick, rsvg-convert, sips, qlmanage, and iconutil.
- Works in 5 steps: rsvg-convert for SVG to PNG when… → magick for most conversions and for… → sips for simple macOS-native… → …
- The user asks to convert image files
- SKILL.md covers Tool preference, Quick workflow, Format notes and Guardrails, plus 1 more section
- Runs Shell scripts from its folder; calls magick
What it does
Image Converter is an agent skill from penwyp/ClaudePreference. Convert images between common formats on macOS, especially SVG/PNG/ICO/ICNS/JPEG/WebP/PDF, using installed local tools such as ImageMagick, rsvg-convert, sips, qlmanage, and iconutil. Use when the user asks to convert image files, generate favicon/icon assets, rasterize SVGs, create Windows .ico files, create macOS .icns files, resize during conversion, or inspect available image conversion commands.
Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `agents/openai.yaml` and `scripts/convert-image.sh`).
It sits in Documents & Office. It works with macOS. The repository describes itself as: A comprehensive collection of development workflow commands for Claude Code. The licence is MIT.
When your agent uses it
- The user asks to convert image files
- Generate favicon/icon assets
- Create Windows .ico files
- Create macOS .icns files
Example prompts
- “/image-converter”
Requirements
- A Bash shell
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- rsvg-convert for SVG to PNG when available. It gives predictable SVG rasterization.
- magick for most conversions and for multi-size .ico.
- sips for simple macOS-native PNG/JPEG/TIFF conversions and resizing.
- iconutil for .iconset to .icns.
- qlmanage -t only as a fallback preview renderer when SVG/PDF conversion tools fail.
What it can do on your machine
Read from SKILL.md and the folder at commit a5eea54. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
magick
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Image Converter loads about 955 tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 285 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from penwyp/ClaudePreference at commit a5eea54, republished under its MIT licence (© penwyp). 285 words, ~955 tokens.
Download SKILL.mdSave it as
.claude/skills/image-converter/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- image-converter
- description
- Convert images between common formats on macOS, especially SVG/PNG/ICO/ICNS/JPEG/WebP/PDF, using installed local tools such as ImageMagick, rsvg-convert, sips, qlmanage, and iconutil. Use when the user asks to convert image files, generate favicon/icon assets, rasterize SVGs, create Windows .ico files, create macOS .icns files, resize during conversion, or inspect available image conversion commands.
Image Converter
Use this skill for local image format conversion on macOS.
Tool preference
Prefer tools in this order:
rsvg-convertfor SVG to PNG when available. It gives predictable SVG rasterization.magickfor most conversions and for multi-size.ico.sipsfor simple macOS-native PNG/JPEG/TIFF conversions and resizing.iconutilfor.iconsetto.icns.qlmanage -tonly as a fallback preview renderer when SVG/PDF conversion tools fail.
Common macOS tool locations include:
/opt/homebrew/bin/rsvg-convert/opt/homebrew/bin/magick/usr/bin/sips/usr/bin/iconutil/usr/bin/qlmanage
Use command -v at runtime instead of hardcoding paths unless a command lookup fails.
Quick workflow
Inspect the input:
bash file input.svg magick identify input.svgIf
magick identifycannot read the file, usefileonly and continue with format-specific tools.Convert with the bundled script when possible:
bash skills/image-converter/scripts/convert-image.sh input.svg output.png --size 800 skills/image-converter/scripts/convert-image.sh input.svg output.ico skills/image-converter/scripts/convert-image.sh input.png output.icnsVerify output:
bash file output.png output.ico magick identify output.png output.ico
Format notes
- SVG to PNG: preserve transparency with
rsvg-convertormagick -background none. - SVG/PNG to ICO: create a multi-resolution icon containing
256,128,64,48,32,16. - PNG to ICNS: create an
.iconsetwith 16, 32, 64, 128, 256, 512, and 1024 pixel variants, then runiconutil -c icns. - JPEG output has no alpha channel. If converting transparent input to JPEG, flatten onto white unless the user specifies a background.
- Do not overwrite source files unless the user explicitly asks. Same-stem outputs such as
icon.svg -> icon.pngare fine.
Guardrails
- Never overwrite source files unless the user explicitly asks.
- Never assume a tool is installed — check with
command -vat runtime before using it. - When all conversion tools are missing, report which tools are needed and stop; do not silently fall back to a different output format.
- For ICO/ICNS generation, always verify the output contains the expected sizes before reporting success.
Common commands
SVG to PNG:
rsvg-convert -w 800 -h 800 icon.svg -o icon.pngSVG/PNG to multi-size ICO:
magick icon.svg -background none -define icon:auto-resize=256,128,64,48,32,16 icon.icoPNG/JPEG resize:
sips -Z 1024 input.png --out output.pngPNG to ICNS:
mkdir -p AppIcon.iconset
sips -z 16 16 input.png --out AppIcon.iconset/icon_16x16.png
sips -z 32 32 input.png --out AppIcon.iconset/icon_16x16@2x.png
sips -z 32 32 input.png --out AppIcon.iconset/icon_32x32.png
sips -z 64 64 input.png --out AppIcon.iconset/icon_32x32@2x.png
sips -z 128 128 input.png --out AppIcon.iconset/icon_128x128.png
sips -z 256 256 input.png --out AppIcon.iconset/icon_128x128@2x.png
sips -z 256 256 input.png --out AppIcon.iconset/icon_256x256.png
sips -z 512 512 input.png --out AppIcon.iconset/icon_256x256@2x.png
sips -z 512 512 input.png --out AppIcon.iconset/icon_512x512.png
sips -z 1024 1024 input.png --out AppIcon.iconset/icon_512x512@2x.png
iconutil -c icns AppIcon.iconset -o AppIcon.icns© penwyp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (scripts) in skills/image-converter of penwyp/ClaudePreference.
- SKILL.md
- agents/openai.yaml
- scripts/convert-image.sh
Open the folder on GitHubat commit a5eea54
Compare with similar skills
Image Converter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Image Converter this skillpenwyp/ClaudePreference | 136 | — | ~955 | Automated safety check: Pass | MIT | |
| Word Formatyeap531/word-format-skill | 204 | — | ~1.5k | Automated safety check: Pass | Custom licence | |
| Huashu Md To PDFalchaincyf/huashu-skills | 1.7k | — | ~824 | Automated safety check: Pass | MIT | |
| DOCXguyi-a/pi-ling | 106 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Enrich Exceltinyfish-io/tinyfish-cookbook | 2.2k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Visa Doc Translateaffaan-m/ECC | 276k | 3 repos | ~508 | Automated safety check: Pass | MIT |
Similar skills
Huashu Md To PDF
alchaincyf/huashu-skills
将 Markdown 文档转换为专业的 PDF 白皮书，采用苹果设计风格. An agent skill from alchaincyf/huashu-skills.
DOCX
guyi-a/pi-ling
Word 文档（.docx）的日常处理：md → docx（生成简历/报告）、docx → PDF/图片（分享预览）、.doc → .docx（老格式升级）。触发场景：用户说"生成 Word 版" / "做份 Word 简历" / "把这份报告转 Word" / "这份 .doc 打不开" / "docx 转 PDF" 等。读 docx 内容走 agent 已有的…
Enrich Excel
tinyfish-io/tinyfish-cookbook
Enrich a live Excel spreadsheet by researching missing data with TinyFish and writing results directly into the running Excel app via AppleScript.
Visa Doc Translate
affaan-m/ECC
将签证申请文件（图片）翻译成英文，并创建包含原文和译文的双语PDF
Visa Doc Translate
affaan-m/ECC
ビザ申請書類（画像）を英語に翻訳し、原文と翻訳を含むバイリンガルPDFを作成する. An agent skill from affaan-m/ECC.
More from penwyp/ClaudePreference
Local Project Runtime
penwyp/ClaudePreference
Diagnose and stabilize local project setup after clone or checkout.
Explain
penwyp/ClaudePreference
Analyze a code snippet, file path, symbol name, or the current conversation context against the local repository and explain what it does in the project.
Refactor Design Report
penwyp/ClaudePreference
Produce a professional, code-grounded refactor or implementation design report from identified technical problems, product gaps, review findings, architecture concerns, or frontend-backend contract…
Doc Code Review Report
penwyp/ClaudePreference
Review text input or documents against the local codebase and produce a structured review report with findings and refactor suggestions.
Browser Flow Fallbacks
penwyp/ClaudePreference
Diagnose flaky browser automation flows (login, OAuth, signup, multi-step forms).
Develop Review Gate
penwyp/ClaudePreference
适用于这类请求：直接在当前 checkout 完成开发、固定做两轮自我 review/refactor、先把最终 review 结果给人类确认、确认后再继续改动、提交或进入下一步。用户可能会说："先开发再自审两轮"、"先 review 两次再给我确认"、"不要开 worktree，直接改"、"先输出 review 结论不要继续"、"做完先停在 gate"。
Related
Works with
Categories
Questions about Image Converter
What does Image Converter do?
Convert images between common formats on macOS, especially SVG/PNG/ICO/ICNS/JPEG/WebP/PDF, using installed local tools such as ImageMagick, rsvg-convert, sips, qlmanage, and iconutil. Image Converter is an agent skill from penwyp/ClaudePreference. Convert images between common formats on macOS, especially SVG/PNG/ICO/ICNS/JPEG/WebP/PDF, using installed local tools such as ImageMagick, rsvg-convert, sips, qlmanage, and iconutil.
When should I use Image Converter?
Image Converter fits situations like: the user asks to convert image files; generate favicon/icon assets; create Windows .ico files; create macOS .icns files.
How do I install Image Converter in Claude Code?
Run `npx skills add penwyp/ClaudePreference --skill image-converter -a claude-code`. Or copy the skill folder (skills/image-converter in penwyp/ClaudePreference) into .claude/skills/image-converter in your project. Claude Code loads it when a task matches its description.
How do I install Image Converter in Codex?
Run `npx skills add penwyp/ClaudePreference --skill image-converter -a codex`. Or copy the skill folder (skills/image-converter in penwyp/ClaudePreference) into .agents/skills/image-converter in your project. Codex loads it when a task matches its description.
Can I use Image Converter in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add penwyp/ClaudePreference --skill image-converter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/image-converter, .gemini/skills/image-converter, .github/skills/image-converter and .opencode/skills/image-converter in your project.
What does Image Converter need to run?
Going by SKILL.md and its folder, Image Converter needs a shell for the scripts in its folder and the command-line tools its instructions call (magick). Our summary lists: A Bash shell.
Does Image Converter access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Image Converter safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Image Converter use?
Image Converter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Image Converter use?
About 955 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Image Converter?
Skills that share tags, products or a category with Image Converter: Word Format (yeap531/word-format-skill, 204 stars), Huashu Md To PDF (alchaincyf/huashu-skills, 1.7k stars), DOCX (guyi-a/pi-ling, 106 stars) and Enrich Excel (tinyfish-io/tinyfish-cookbook, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Image Converter?
penwyp (a GitHub user) maintains it in penwyp/ClaudePreference, which has 136 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on May 27, 2026.
Source: penwyp/ClaudePreference on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.