[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75KGSVAVBCCM0G3SY7W8EYH":3,"skill-same:01M75KGSVAVBCCM0G3SY7W8EYH":62},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M75KGSVAVBCCM0G3SY7W8EYH","mac-use",null,"Control macOS GUI apps visually — take screenshots, click, scroll, type. Use when the user asks to interact with any Mac desktop application's graphical interface.","javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fkekejun\u002Fmac-use\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: mac-use\ndescription: Control macOS GUI apps visually — take screenshots, click, scroll, type. Use when the user asks to interact with any Mac desktop application's graphical interface.\nmetadata: {\"openclaw\":{\"emoji\":\"🖥️\",\"requires\":{\"bins\":[\"python3\"]},\"os\":[\"darwin\"],\"install\":[{\"id\":\"python-brew\",\"kind\":\"brew\",\"formula\":\"python\",\"bins\":[\"python3\"],\"label\":\"Install Python 3 (brew)\"}]}}\n---\n\n# Mac Use\n\nControl any macOS GUI application through a **screenshot → pick element → click → verify** loop.\n\n## Setup\n\n**Platform**: macOS only (requires Apple Vision framework for OCR)\n\n**System binaries** (pre-installed on macOS):\n- `python3` — via Homebrew (`brew install python`)\n- `screencapture` — built-in macOS utility\n\n**Python packages** — install from the skill directory:\n```bash\npip3 install --break-system-packages -r {baseDir}\u002Frequirements.txt\n```\n\n## How It Works\n\nThe `screenshot` command captures a window, uses **Apple Vision OCR** to detect all text elements, draws numbered annotations on the image, and returns both:\n1. **Annotated image** at `\u002Ftmp\u002Fmac_use.png` — numbered green boxes around each detected text\n2. **Element list** in JSON — `[{num: 1, text: \"Submit\", at: [500, 200]}, {num: 2, text: \"Cancel\", at: [600, 200]}, ...]` where `at` is the center point `[x, y]` on the 1000x1000 canvas (origin at top-left)\n\nYou receive both by calling Bash (gets JSON with element list) and then Read on `\u002Ftmp\u002Fmac_use.png` (gets the visual). **Always do both** so you can cross-reference the numbers with what you see.\n\n## Quick Reference\n\n```bash\n# List all visible windows\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py list\n\n# Screenshot + annotate (returns image + numbered element list)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot \u003Capp> [--id N]\n\n# Click element by number (primary click method)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum \u003CN>\n\n# Click at canvas coordinates (fallback for unlabeled icons)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py click --app \u003Capp> [--id N] \u003Cx> \u003Cy>\n\n# Scroll inside a window\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py scroll --app \u003Capp> [--id N] \u003Cdirection> \u003Camount>\n\n# Type text (uses clipboard paste — supports all languages)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py type [--app \u003Capp>] \"text here\"\n\n# Press key or combo\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key [--app \u003Capp>] \u003Ccombo>\n```\n\n## Workflow\n\n1. **Open** the target app with `open -a \"App Name\"` (optionally with a URL or file path)\n2. **Wait** for it to load: `sleep 2`\n3. **Screenshot** the app:\n   ```bash\n   python3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot \u003Capp> [--id N]\n   ```\n   This returns JSON with `file` (image path) and `elements` (numbered text list).\n4. **Read** the annotated image at `\u002Ftmp\u002Fmac_use.png` to see the numbered elements visually\n5. **Decide** which element to interact with:\n   - **Prefer `clicknum N`** — pick the number of a detected text element\n   - **Fallback `click --app \u003Capp> x y`** — only for unlabeled icons (arrows, close buttons, cart icons) that have no text and therefore no number\n6. **Act** using `clicknum`, `type`, `key`, or `scroll`\n7. **Screenshot again** to verify the result\n8. Repeat from step 3\n\n## Commands\n\n### list\n\nShow all visible app windows.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py list\n```\n\nReturns JSON array: `[{\"app\":\"Google Chrome\",\"title\":\"Wikipedia\",\"id\":4527,\"x\":120,\"y\":80,\"w\":1200,\"h\":800}, ...]`\n\n### screenshot\n\nCapture a window, detect text elements via OCR, annotate with numbered markers, and return the element list. The target window is automatically raised to the top before capture, so overlapping windows are handled.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot chrome\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot chrome --id 4527\n```\n\n- `\u003Capp>`: fuzzy, case-insensitive match (e.g. \"chrome\" matches \"Google Chrome\")\n- `--id N`: target a specific window ID (required when multiple windows of the same app exist)\n- Returns JSON with:\n  - `file`: path to annotated screenshot (`\u002Ftmp\u002Fmac_use.png`)\n  - `id`, `app`, `title`, `scale`: window metadata\n  - `elements`: array of `{num, text, at}` — the numbered clickable text elements, where `at` is `[x, y]` center coordinates on the 1000x1000 canvas (origin at top-left)\n- If multiple windows match, returns a list of windows instead — pick one and retry with `--id`\n- The image is 1000x1000 pixels with green bounding boxes and blue number badges\n- Element map is saved to `\u002Ftmp\u002Fmac_use_elements.json` for `clicknum`\n\n### clicknum\n\nClick on a numbered element from the last screenshot. **This is the primary click method.**\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum 5\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum 12\n```\n\n- `N`: the element number from the last `screenshot` output\n- Reads the saved element map, activates the window, and clicks at the element's center\n- Returns JSON with `clicked_num`, `text`, canvas coords, and absolute screen coords\n\n### click\n\nClick at a position using canvas coordinates. **Fallback only — use for unlabeled icons.**\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py click --app chrome 500 300\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py click --app chrome --id 4527 500 300\n```\n\n- **Coordinates are canvas positions (0-1000)** from the screenshot image\n- x=0 is left, x=1000 is right; y=0 is top, y=1000 is bottom\n- Use this only when Vision OCR didn't detect the element (icon-only buttons, images, etc.)\n\n### scroll\n\nScroll inside an app window.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py scroll --app chrome down 5\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py scroll --app notes up 10\n```\n\n- Directions: `up`, `down`, `left`, `right`\n- Amount: number of scroll clicks (3-5 for moderate, 10+ for fast scrolling)\n- Mouse is moved to the center of the window before scrolling\n\n### type\n\nType text into the currently focused input field.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py type --app chrome \"hello world\"\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py type --app chrome \"你好世界\"\n```\n\n- `--app`: activates the app first to ensure keystrokes go to the right window\n- Uses clipboard paste (Cmd+V) for reliable Unicode\u002FCJK support\n- **Always click on the target input field first** before typing\n\n### key\n\nPress a single key or key combination.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key --app chrome return\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key --app chrome cmd+a\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key --app chrome cmd+shift+s\n```\n\n- `--app`: activates the app first\n- Common keys: `return`, `tab`, `escape`, `space`, `delete`, `backspace`, `up`, `down`, `left`, `right`\n- Modifiers: `cmd`, `ctrl`, `alt`\u002F`opt`, `shift`\n\n## Important Rules\n\n- **Always screenshot before your first interaction** with an app\n- **Always screenshot after an action** to verify the result\n- **Always Read the screenshot image** after running the screenshot command — you need both the element list AND the visual\n- **Prefer `clicknum`** over `click` — only use direct coordinates for unlabeled icons\n- **Click before typing** — ensure the correct input field has focus first\n- **Multiple windows**: if you get `multiple_windows` error, use `list` to see all windows, then pass `--id`\n- **Popup windows** (like WeChat mini-program panels) are separate windows with their own IDs — use `list` to find them and `--id` to target them\n- **Wait after opening apps**: use `sleep 2-3` after `open -a` before taking a screenshot\n- **Activate the app** before screenshot\u002Fclick: prepend `osascript -e 'tell application \"AppName\" to activate' && sleep 1` when the target app may be behind other windows\n- **Do not type passwords or secrets** via this tool\n\n## Coordinate System (for fallback `click` only)\n\nScreenshots are rendered onto a **1000x1000 canvas**:\n- **Origin (0, 0)** is at the **top-left** corner\n- **x** increases left to right (0 = left edge, 1000 = right edge)\n- **y** increases top to bottom (0 = top edge, 1000 = bottom edge)\n- The app window is scaled to fit (aspect ratio preserved), centered, with dark gray padding\n\n## Example: Order food on Meituan in WeChat\n\n```bash\n# 1. Open WeChat\nopen -a \"WeChat\"\nsleep 3\n\n# 2. Screenshot WeChat — find the mini program window\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py list\n# → find the mini program window ID\n\n# 3. Screenshot the mini program (annotated + element list)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot 微信 --id 41266\n# → returns: {\"file\": \"\u002Ftmp\u002Fmac_use.png\", \"elements\": [{num: 1, text: \"搜索\", at: [500, 200]}, ...]}\n# → Read \u002Ftmp\u002Fmac_use.png to see annotated image\n\n# 4. Click \"搜索\" (element #1)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum 1\n\n# 5. Type search query\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py type --app 微信 \"炸鸡\"\n\n# 6. Press Enter\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key --app 微信 return\nsleep 2\n\n# 7. Screenshot to see results\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot 微信 --id 41266\n# → Read \u002Ftmp\u002Fmac_use.png, pick a restaurant by number\n\n# 8. Click on a restaurant (e.g. element #5)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum 5\n```\n","# Mac Use\n\nControl any macOS GUI application through a **screenshot → pick element → click → verify** loop.\n\n## Setup\n\n**Platform**: macOS only (requires Apple Vision framework for OCR)\n\n**System binaries** (pre-installed on macOS):\n- `python3` — via Homebrew (`brew install python`)\n- `screencapture` — built-in macOS utility\n\n**Python packages** — install from the skill directory:\n```bash\npip3 install --break-system-packages -r {baseDir}\u002Frequirements.txt\n```\n\n## How It Works\n\nThe `screenshot` command captures a window, uses **Apple Vision OCR** to detect all text elements, draws numbered annotations on the image, and returns both:\n1. **Annotated image** at `\u002Ftmp\u002Fmac_use.png` — numbered green boxes around each detected text\n2. **Element list** in JSON — `[{num: 1, text: \"Submit\", at: [500, 200]}, {num: 2, text: \"Cancel\", at: [600, 200]}, ...]` where `at` is the center point `[x, y]` on the 1000x1000 canvas (origin at top-left)\n\nYou receive both by calling Bash (gets JSON with element list) and then Read on `\u002Ftmp\u002Fmac_use.png` (gets the visual). **Always do both** so you can cross-reference the numbers with what you see.\n\n## Quick Reference\n\n```bash\n# List all visible windows\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py list\n\n# Screenshot + annotate (returns image + numbered element list)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot \u003Capp> [--id N]\n\n# Click element by number (primary click method)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum \u003CN>\n\n# Click at canvas coordinates (fallback for unlabeled icons)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py click --app \u003Capp> [--id N] \u003Cx> \u003Cy>\n\n# Scroll inside a window\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py scroll --app \u003Capp> [--id N] \u003Cdirection> \u003Camount>\n\n# Type text (uses clipboard paste — supports all languages)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py type [--app \u003Capp>] \"text here\"\n\n# Press key or combo\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key [--app \u003Capp>] \u003Ccombo>\n```\n\n## Workflow\n\n1. **Open** the target app with `open -a \"App Name\"` (optionally with a URL or file path)\n2. **Wait** for it to load: `sleep 2`\n3. **Screenshot** the app:\n   ```bash\n   python3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot \u003Capp> [--id N]\n   ```\n   This returns JSON with `file` (image path) and `elements` (numbered text list).\n4. **Read** the annotated image at `\u002Ftmp\u002Fmac_use.png` to see the numbered elements visually\n5. **Decide** which element to interact with:\n   - **Prefer `clicknum N`** — pick the number of a detected text element\n   - **Fallback `click --app \u003Capp> x y`** — only for unlabeled icons (arrows, close buttons, cart icons) that have no text and therefore no number\n6. **Act** using `clicknum`, `type`, `key`, or `scroll`\n7. **Screenshot again** to verify the result\n8. Repeat from step 3\n\n## Commands\n\n### list\n\nShow all visible app windows.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py list\n```\n\nReturns JSON array: `[{\"app\":\"Google Chrome\",\"title\":\"Wikipedia\",\"id\":4527,\"x\":120,\"y\":80,\"w\":1200,\"h\":800}, ...]`\n\n### screenshot\n\nCapture a window, detect text elements via OCR, annotate with numbered markers, and return the element list. The target window is automatically raised to the top before capture, so overlapping windows are handled.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot chrome\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot chrome --id 4527\n```\n\n- `\u003Capp>`: fuzzy, case-insensitive match (e.g. \"chrome\" matches \"Google Chrome\")\n- `--id N`: target a specific window ID (required when multiple windows of the same app exist)\n- Returns JSON with:\n  - `file`: path to annotated screenshot (`\u002Ftmp\u002Fmac_use.png`)\n  - `id`, `app`, `title`, `scale`: window metadata\n  - `elements`: array of `{num, text, at}` — the numbered clickable text elements, where `at` is `[x, y]` center coordinates on the 1000x1000 canvas (origin at top-left)\n- If multiple windows match, returns a list of windows instead — pick one and retry with `--id`\n- The image is 1000x1000 pixels with green bounding boxes and blue number badges\n- Element map is saved to `\u002Ftmp\u002Fmac_use_elements.json` for `clicknum`\n\n### clicknum\n\nClick on a numbered element from the last screenshot. **This is the primary click method.**\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum 5\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum 12\n```\n\n- `N`: the element number from the last `screenshot` output\n- Reads the saved element map, activates the window, and clicks at the element's center\n- Returns JSON with `clicked_num`, `text`, canvas coords, and absolute screen coords\n\n### click\n\nClick at a position using canvas coordinates. **Fallback only — use for unlabeled icons.**\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py click --app chrome 500 300\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py click --app chrome --id 4527 500 300\n```\n\n- **Coordinates are canvas positions (0-1000)** from the screenshot image\n- x=0 is left, x=1000 is right; y=0 is top, y=1000 is bottom\n- Use this only when Vision OCR didn't detect the element (icon-only buttons, images, etc.)\n\n### scroll\n\nScroll inside an app window.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py scroll --app chrome down 5\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py scroll --app notes up 10\n```\n\n- Directions: `up`, `down`, `left`, `right`\n- Amount: number of scroll clicks (3-5 for moderate, 10+ for fast scrolling)\n- Mouse is moved to the center of the window before scrolling\n\n### type\n\nType text into the currently focused input field.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py type --app chrome \"hello world\"\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py type --app chrome \"你好世界\"\n```\n\n- `--app`: activates the app first to ensure keystrokes go to the right window\n- Uses clipboard paste (Cmd+V) for reliable Unicode\u002FCJK support\n- **Always click on the target input field first** before typing\n\n### key\n\nPress a single key or key combination.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key --app chrome return\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key --app chrome cmd+a\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key --app chrome cmd+shift+s\n```\n\n- `--app`: activates the app first\n- Common keys: `return`, `tab`, `escape`, `space`, `delete`, `backspace`, `up`, `down`, `left`, `right`\n- Modifiers: `cmd`, `ctrl`, `alt`\u002F`opt`, `shift`\n\n## Important Rules\n\n- **Always screenshot before your first interaction** with an app\n- **Always screenshot after an action** to verify the result\n- **Always Read the screenshot image** after running the screenshot command — you need both the element list AND the visual\n- **Prefer `clicknum`** over `click` — only use direct coordinates for unlabeled icons\n- **Click before typing** — ensure the correct input field has focus first\n- **Multiple windows**: if you get `multiple_windows` error, use `list` to see all windows, then pass `--id`\n- **Popup windows** (like WeChat mini-program panels) are separate windows with their own IDs — use `list` to find them and `--id` to target them\n- **Wait after opening apps**: use `sleep 2-3` after `open -a` before taking a screenshot\n- **Activate the app** before screenshot\u002Fclick: prepend `osascript -e 'tell application \"AppName\" to activate' && sleep 1` when the target app may be behind other windows\n- **Do not type passwords or secrets** via this tool\n\n## Coordinate System (for fallback `click` only)\n\nScreenshots are rendered onto a **1000x1000 canvas**:\n- **Origin (0, 0)** is at the **top-left** corner\n- **x** increases left to right (0 = left edge, 1000 = right edge)\n- **y** increases top to bottom (0 = top edge, 1000 = bottom edge)\n- The app window is scaled to fit (aspect ratio preserved), centered, with dark gray padding\n\n## Example: Order food on Meituan in WeChat\n\n```bash\n# 1. Open WeChat\nopen -a \"WeChat\"\nsleep 3\n\n# 2. Screenshot WeChat — find the mini program window\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py list\n# → find the mini program window ID\n\n# 3. Screenshot the mini program (annotated + element list)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot 微信 --id 41266\n# → returns: {\"file\": \"\u002Ftmp\u002Fmac_use.png\", \"elements\": [{num: 1, text: \"搜索\", at: [500, 200]}, ...]}\n# → Read \u002Ftmp\u002Fmac_use.png to see annotated image\n\n# 4. Click \"搜索\" (element #1)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum 1\n\n# 5. Type search query\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py type --app 微信 \"炸鸡\"\n\n# 6. Press Enter\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py key --app 微信 return\nsleep 2\n\n# 7. Screenshot to see results\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py screenshot 微信 --id 41266\n# → Read \u002Ftmp\u002Fmac_use.png, pick a restaurant by number\n\n# 8. Click on a restaurant (e.g. element #5)\npython3 {baseDir}\u002Fscripts\u002Fmac_use.py clicknum 5\n```\n",{"name":5,"metadata":24,"description":7},{"openclaw":25},{"os":26,"emoji":28,"install":29,"requires":37},[27],"darwin","🖥️",[30],{"id":31,"bins":32,"kind":34,"label":35,"formula":36},"python-brew",[33],"python3","brew","Install Python 3 (brew)","python",{"bins":38},[33],"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fkekejun\u002Fmac-use",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill mac-use",{"tool":54,"command":55},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill mac-use",{"tool":57,"command":58},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill mac-use","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fkekejun\u002Fmac-use\u002FSKILL.md",true,[],[63,71,78,85,92,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":70},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":70},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":70},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":70},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":70},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":70},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]