[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75FPRTHKXW2KCP7J2XXHHEQ":3,"skill-same:01M75FPRTHKXW2KCP7J2XXHHEQ":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M75FPRTHKXW2KCP7J2XXHHEQ","mac-control",null,"Control Mac via mouse\u002Fkeyboard automation using cliclick and AppleScript. Use for clicking UI elements, taking screenshots, getting window bounds, handling coordinate scaling on Retina displays, and automating UI interactions like clicking Chrome extension icons, dismissing dialogs, or toolbar buttons.","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\u002Feasonc13\u002Fmac-control\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: mac-control\ndescription: Control Mac via mouse\u002Fkeyboard automation using cliclick and AppleScript. Use for clicking UI elements, taking screenshots, getting window bounds, handling coordinate scaling on Retina displays, and automating UI interactions like clicking Chrome extension icons, dismissing dialogs, or toolbar buttons.\n---\n\n# Mac Control\n\nAutomate Mac UI interactions using cliclick (mouse\u002Fkeyboard) and system tools.\n\n## Tools\n\n- **cliclick**: `\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick` - mouse\u002Fkeyboard control\n- **screencapture**: Built-in screenshot tool\n- **magick**: ImageMagick for image analysis\n- **osascript**: AppleScript for window info\n\n## Coordinate System (Eason's Mac Mini)\n\n**Current setup**: 1920x1080 display, **1:1 scaling** (no conversion needed!)\n\n- Screenshot coords = cliclick coords\n- If screenshot shows element at (800, 500), click at (800, 500)\n\n### For Retina Displays (2x)\n\nIf screenshot is 2x the logical resolution:\n```bash\n# Convert: cliclick_coords = screenshot_coords \u002F 2\ncliclick c:$((screenshot_x \u002F 2)),$((screenshot_y \u002F 2))\n```\n\n### Calibration Script\n\nRun to verify your scale factor:\n```bash\n\u002FUsers\u002Feason\u002Fclawd\u002Fscripts\u002Fcalibrate-cursor.sh\n```\n\n## cliclick Commands\n\n```bash\n# Click at coordinates\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:500,300\n\n# Move mouse (no click) - Note: may not visually update cursor\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick m:500,300\n\n# Double-click\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick dc:500,300\n\n# Right-click\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick rc:500,300\n\n# Click and drag\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick dd:100,100 du:200,200\n\n# Type text\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick t:\"hello world\"\n\n# Press key (Return, Escape, Tab, etc.)\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick kp:return\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick kp:escape\n\n# Key with modifier (cmd+w to close window)\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick kd:cmd t:w ku:cmd\n\n# Get current mouse position\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick p\n\n# Wait before action (ms)\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick -w 100 c:500,300\n```\n\n## Screenshots\n\n```bash\n# Full screen (silent)\n\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fscreenshot.png\n\n# With cursor (may not work for custom cursor colors)\n\u002Fusr\u002Fsbin\u002Fscreencapture -C -x \u002Ftmp\u002Fscreenshot.png\n\n# Interactive region selection\nscreencapture -i region.png\n\n# Delayed capture\nscreencapture -T 3 -x delayed.png  # 3 second delay\n```\n\n## Workflow: Screenshot → Analyze → Click\n\n**Best practice for reliable clicking:**\n\n1. **Take screenshot**\n   ```bash\n   \u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fscreen.png\n   ```\n\n2. **View screenshot** (Read tool) to find target coordinates\n\n3. **Click at those coordinates** (1:1 on 1920x1080)\n   ```bash\n   \u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:X,Y\n   ```\n\n4. **Verify** by taking another screenshot\n\n### Example: Click a button\n\n```bash\n# 1. Screenshot\n\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fbefore.png\n\n# 2. View image, find button at (850, 450)\n# (Use Read tool on \u002Ftmp\u002Fbefore.png)\n\n# 3. Click\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:850,450\n\n# 4. Verify\n\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fafter.png\n```\n\n## Window Bounds\n\n```bash\n# Get Chrome window bounds\nosascript -e 'tell application \"Google Chrome\" to get bounds of front window'\n# Returns: 0, 38, 1920, 1080  (left, top, right, bottom)\n```\n\n## Common Patterns\n\n### Chrome Extension Icon (Browser Relay)\n\nUse AppleScript to find exact button position:\n\n```bash\n# Find Clawdbot extension button position\nosascript -e '\ntell application \"System Events\"\n    tell process \"Google Chrome\"\n        set toolbarGroup to group 2 of group 3 of toolbar 1 of group 1 of group 1 of group 1 of group 1 of group 1 of window 1\n        set allButtons to every pop up button of toolbarGroup\n        repeat with btn in allButtons\n            if description of btn contains \"Clawdbot\" then\n                return position of btn & size of btn\n            end if\n        end repeat\n    end tell\nend tell\n'\n# Output: 1755, 71, 34, 34 (x, y, width, height)\n\n# Click center of button\n# center_x = x + width\u002F2 = 1755 + 17 = 1772\n# center_y = y + height\u002F2 = 71 + 17 = 88\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:1772,88\n```\n\n### Clicking by Color Detection\n\nIf you need to find a specific colored element:\n\n```bash\n# Find red (#FF0000) pixels in screenshot\nmagick \u002Ftmp\u002Fscreen.png txt:- | grep \"#FF0000\" | head -5\n\n# Calculate center of colored region\nmagick \u002Ftmp\u002Fscreen.png txt:- | grep \"#FF0000\" | awk -F'[,:]' '\n  BEGIN{sx=0;sy=0;c=0}\n  {sx+=$1;sy+=$2;c++}\n  END{printf \"Center: (%d, %d)\\n\", sx\u002Fc, sy\u002Fc}'\n```\n\n### Dialog Button Click\n\n1. Screenshot the dialog\n2. Find button coordinates visually\n3. Click (no scaling on 1920x1080)\n\n```bash\n# Example: Click \"OK\" button at (960, 540)\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:960,540\n```\n\n### Type in Text Field\n\n```bash\n# Click to focus, then type\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:500,300\nsleep 0.2\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick t:\"Hello world\"\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick kp:return\n```\n\n## Helper Scripts\n\nLocated in `\u002FUsers\u002Feason\u002Fclawd\u002Fscripts\u002F`:\n\n- `calibrate-cursor.sh` - Calibrate coordinate scaling\n- `click-at-visual.sh` - Click at screenshot coordinates\n- `get-cursor-pos.sh` - Get current cursor position\n- `attach-browser-relay.sh` - Auto-click Browser Relay extension\n\n## Keyboard Navigation (When Clicks Fail)\n\n**Google OAuth and protected pages block synthetic mouse clicks!** Use keyboard navigation:\n\n```bash\n# Tab to navigate between elements\nosascript -e 'tell application \"System Events\" to keystroke tab'\n\n# Shift+Tab to go backwards\nosascript -e 'tell application \"System Events\" to key code 48 using shift down'\n\n# Enter to activate focused element\nosascript -e 'tell application \"System Events\" to keystroke return'\n\n# Full workflow: Tab 3 times then Enter\nosascript -e '\ntell application \"System Events\"\n    keystroke tab\n    delay 0.15\n    keystroke tab\n    delay 0.15\n    keystroke tab\n    delay 0.15\n    keystroke return\nend tell\n'\n```\n\n**When to use keyboard instead of mouse:**\n- Google OAuth \u002F login pages (anti-automation protection)\n- Popup dialogs with focus trapping\n- When mouse clicks consistently fail after verification\n\n## Chrome Browser Relay & Multiple Windows\n\n**Problem**: Browser Relay may list tabs from multiple Chrome windows, causing `snapshot` to fail on the desired tab.\n\n**Solution**:\n1. Close extra Chrome windows before automation\n2. Or ensure only the target window has relay attached\n\n**Check tabs visible to relay**:\n```bash\n# In agent code\nbrowser action=tabs profile=chrome\n```\n\nIf target tab missing from list → wrong window attached.\n\n**Verify single window**:\n```bash\nosascript -e 'tell application \"Google Chrome\" to return count of windows'\n```\n\n## Verify-Before-Click Workflow\n\n**Critical**: Always verify coordinates BEFORE clicking important buttons.\n\n```bash\n# 1. Take screenshot\nosascript -e 'do shell script \"\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fbefore.png\"'\n\n# 2. View screenshot (Read tool), note target position\n\n# 3. Move mouse to verify position (optional)\npython3 -c \"import pyautogui; pyautogui.moveTo(X, Y)\"\nosascript -e 'do shell script \"\u002Fusr\u002Fsbin\u002Fscreencapture -C -x \u002Ftmp\u002Fverify.png\"'\n\n# 4. Check cursor is on target, THEN click\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:X,Y\n\n# 5. Take screenshot to confirm action worked\nosascript -e 'do shell script \"\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fafter.png\"'\n```\n\n## Troubleshooting\n\n**Click lands wrong**: Verify scale factor with calibration script\n\n**cliclick m: doesn't move cursor visually**: Use `c:` (click) instead, or check with `cliclick p` to confirm position changed\n\n**Permission denied**: System Settings → Privacy & Security → Accessibility → Add `\u002Fopt\u002Fhomebrew\u002Fbin\u002Fnode`\n\n**Window not found**: Check exact app name:\n```bash\nosascript -e 'tell application \"System Events\" to get name of every process whose background only is false'\n```\n\n**Clicks ignored on OAuth\u002Fprotected pages**: These pages block synthetic events. Use keyboard navigation (Tab + Enter) instead.\n\n**pyautogui vs cliclick coordinates differ**: Stick with cliclick for consistency. pyautogui may have different coordinate mapping.\n\n**Quartz CGEvent clicks don't work**: Some pages (Google OAuth) block low-level mouse events too. Keyboard is the only reliable method.\n","# Mac Control\n\nAutomate Mac UI interactions using cliclick (mouse\u002Fkeyboard) and system tools.\n\n## Tools\n\n- **cliclick**: `\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick` - mouse\u002Fkeyboard control\n- **screencapture**: Built-in screenshot tool\n- **magick**: ImageMagick for image analysis\n- **osascript**: AppleScript for window info\n\n## Coordinate System (Eason's Mac Mini)\n\n**Current setup**: 1920x1080 display, **1:1 scaling** (no conversion needed!)\n\n- Screenshot coords = cliclick coords\n- If screenshot shows element at (800, 500), click at (800, 500)\n\n### For Retina Displays (2x)\n\nIf screenshot is 2x the logical resolution:\n```bash\n# Convert: cliclick_coords = screenshot_coords \u002F 2\ncliclick c:$((screenshot_x \u002F 2)),$((screenshot_y \u002F 2))\n```\n\n### Calibration Script\n\nRun to verify your scale factor:\n```bash\n\u002FUsers\u002Feason\u002Fclawd\u002Fscripts\u002Fcalibrate-cursor.sh\n```\n\n## cliclick Commands\n\n```bash\n# Click at coordinates\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:500,300\n\n# Move mouse (no click) - Note: may not visually update cursor\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick m:500,300\n\n# Double-click\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick dc:500,300\n\n# Right-click\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick rc:500,300\n\n# Click and drag\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick dd:100,100 du:200,200\n\n# Type text\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick t:\"hello world\"\n\n# Press key (Return, Escape, Tab, etc.)\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick kp:return\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick kp:escape\n\n# Key with modifier (cmd+w to close window)\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick kd:cmd t:w ku:cmd\n\n# Get current mouse position\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick p\n\n# Wait before action (ms)\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick -w 100 c:500,300\n```\n\n## Screenshots\n\n```bash\n# Full screen (silent)\n\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fscreenshot.png\n\n# With cursor (may not work for custom cursor colors)\n\u002Fusr\u002Fsbin\u002Fscreencapture -C -x \u002Ftmp\u002Fscreenshot.png\n\n# Interactive region selection\nscreencapture -i region.png\n\n# Delayed capture\nscreencapture -T 3 -x delayed.png  # 3 second delay\n```\n\n## Workflow: Screenshot → Analyze → Click\n\n**Best practice for reliable clicking:**\n\n1. **Take screenshot**\n   ```bash\n   \u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fscreen.png\n   ```\n\n2. **View screenshot** (Read tool) to find target coordinates\n\n3. **Click at those coordinates** (1:1 on 1920x1080)\n   ```bash\n   \u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:X,Y\n   ```\n\n4. **Verify** by taking another screenshot\n\n### Example: Click a button\n\n```bash\n# 1. Screenshot\n\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fbefore.png\n\n# 2. View image, find button at (850, 450)\n# (Use Read tool on \u002Ftmp\u002Fbefore.png)\n\n# 3. Click\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:850,450\n\n# 4. Verify\n\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fafter.png\n```\n\n## Window Bounds\n\n```bash\n# Get Chrome window bounds\nosascript -e 'tell application \"Google Chrome\" to get bounds of front window'\n# Returns: 0, 38, 1920, 1080  (left, top, right, bottom)\n```\n\n## Common Patterns\n\n### Chrome Extension Icon (Browser Relay)\n\nUse AppleScript to find exact button position:\n\n```bash\n# Find Clawdbot extension button position\nosascript -e '\ntell application \"System Events\"\n    tell process \"Google Chrome\"\n        set toolbarGroup to group 2 of group 3 of toolbar 1 of group 1 of group 1 of group 1 of group 1 of group 1 of window 1\n        set allButtons to every pop up button of toolbarGroup\n        repeat with btn in allButtons\n            if description of btn contains \"Clawdbot\" then\n                return position of btn & size of btn\n            end if\n        end repeat\n    end tell\nend tell\n'\n# Output: 1755, 71, 34, 34 (x, y, width, height)\n\n# Click center of button\n# center_x = x + width\u002F2 = 1755 + 17 = 1772\n# center_y = y + height\u002F2 = 71 + 17 = 88\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:1772,88\n```\n\n### Clicking by Color Detection\n\nIf you need to find a specific colored element:\n\n```bash\n# Find red (#FF0000) pixels in screenshot\nmagick \u002Ftmp\u002Fscreen.png txt:- | grep \"#FF0000\" | head -5\n\n# Calculate center of colored region\nmagick \u002Ftmp\u002Fscreen.png txt:- | grep \"#FF0000\" | awk -F'[,:]' '\n  BEGIN{sx=0;sy=0;c=0}\n  {sx+=$1;sy+=$2;c++}\n  END{printf \"Center: (%d, %d)\\n\", sx\u002Fc, sy\u002Fc}'\n```\n\n### Dialog Button Click\n\n1. Screenshot the dialog\n2. Find button coordinates visually\n3. Click (no scaling on 1920x1080)\n\n```bash\n# Example: Click \"OK\" button at (960, 540)\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:960,540\n```\n\n### Type in Text Field\n\n```bash\n# Click to focus, then type\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:500,300\nsleep 0.2\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick t:\"Hello world\"\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick kp:return\n```\n\n## Helper Scripts\n\nLocated in `\u002FUsers\u002Feason\u002Fclawd\u002Fscripts\u002F`:\n\n- `calibrate-cursor.sh` - Calibrate coordinate scaling\n- `click-at-visual.sh` - Click at screenshot coordinates\n- `get-cursor-pos.sh` - Get current cursor position\n- `attach-browser-relay.sh` - Auto-click Browser Relay extension\n\n## Keyboard Navigation (When Clicks Fail)\n\n**Google OAuth and protected pages block synthetic mouse clicks!** Use keyboard navigation:\n\n```bash\n# Tab to navigate between elements\nosascript -e 'tell application \"System Events\" to keystroke tab'\n\n# Shift+Tab to go backwards\nosascript -e 'tell application \"System Events\" to key code 48 using shift down'\n\n# Enter to activate focused element\nosascript -e 'tell application \"System Events\" to keystroke return'\n\n# Full workflow: Tab 3 times then Enter\nosascript -e '\ntell application \"System Events\"\n    keystroke tab\n    delay 0.15\n    keystroke tab\n    delay 0.15\n    keystroke tab\n    delay 0.15\n    keystroke return\nend tell\n'\n```\n\n**When to use keyboard instead of mouse:**\n- Google OAuth \u002F login pages (anti-automation protection)\n- Popup dialogs with focus trapping\n- When mouse clicks consistently fail after verification\n\n## Chrome Browser Relay & Multiple Windows\n\n**Problem**: Browser Relay may list tabs from multiple Chrome windows, causing `snapshot` to fail on the desired tab.\n\n**Solution**:\n1. Close extra Chrome windows before automation\n2. Or ensure only the target window has relay attached\n\n**Check tabs visible to relay**:\n```bash\n# In agent code\nbrowser action=tabs profile=chrome\n```\n\nIf target tab missing from list → wrong window attached.\n\n**Verify single window**:\n```bash\nosascript -e 'tell application \"Google Chrome\" to return count of windows'\n```\n\n## Verify-Before-Click Workflow\n\n**Critical**: Always verify coordinates BEFORE clicking important buttons.\n\n```bash\n# 1. Take screenshot\nosascript -e 'do shell script \"\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fbefore.png\"'\n\n# 2. View screenshot (Read tool), note target position\n\n# 3. Move mouse to verify position (optional)\npython3 -c \"import pyautogui; pyautogui.moveTo(X, Y)\"\nosascript -e 'do shell script \"\u002Fusr\u002Fsbin\u002Fscreencapture -C -x \u002Ftmp\u002Fverify.png\"'\n\n# 4. Check cursor is on target, THEN click\n\u002Fopt\u002Fhomebrew\u002Fbin\u002Fcliclick c:X,Y\n\n# 5. Take screenshot to confirm action worked\nosascript -e 'do shell script \"\u002Fusr\u002Fsbin\u002Fscreencapture -x \u002Ftmp\u002Fafter.png\"'\n```\n\n## Troubleshooting\n\n**Click lands wrong**: Verify scale factor with calibration script\n\n**cliclick m: doesn't move cursor visually**: Use `c:` (click) instead, or check with `cliclick p` to confirm position changed\n\n**Permission denied**: System Settings → Privacy & Security → Accessibility → Add `\u002Fopt\u002Fhomebrew\u002Fbin\u002Fnode`\n\n**Window not found**: Check exact app name:\n```bash\nosascript -e 'tell application \"System Events\" to get name of every process whose background only is false'\n```\n\n**Clicks ignored on OAuth\u002Fprotected pages**: These pages block synthetic events. Use keyboard navigation (Tab + Enter) instead.\n\n**pyautogui vs cliclick coordinates differ**: Stick with cliclick for consistency. pyautogui may have different coordinate mapping.\n\n**Quartz CGEvent clicks don't work**: Some pages (Google OAuth) block low-level mouse events too. Keyboard is the only reliable method.\n",{"name":5,"description":7},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Feasonc13\u002Fmac-control",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":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill mac-control",{"tool":39,"command":40},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill mac-control",{"tool":42,"command":43},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill mac-control","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Feasonc13\u002Fmac-control\u002FSKILL.md",true,[],[48,56,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":55},"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":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":55},"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":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":55},"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":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":55},"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":55},"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":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":55},"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",[],[]]