[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EZCQMYWW2DTGD2S0DDFH70":3,"skill-same:01M7EZCQMYWW2DTGD2S0DDFH70":45},{"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":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7EZCQMYWW2DTGD2S0DDFH70","gui-automation",null,"Use when you need to visually interact with a GUI — test buttons, fill forms, verify visual layouts, fuzz web pages, automate user flows, take screenshots, or perform end-to-end QA on any application. Works on cloud VMs, Docker containers, local machines, and sandboxes. Install: pip install cua.","SenCha930511\u002Fomp-desktop","SenCha930511","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F69847839?v=4","01M7EZ7DZM6X416N39DB35SDDB","SenChaaa","01M7EZ7E0JQGT4PZ95XA7S77RZ",1,"MIT","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fgui-automation\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: gui-automation\ndescription: >-\n  Use when you need to visually interact with a GUI — test buttons, fill forms,\n  verify visual layouts, fuzz web pages, automate user flows, take screenshots,\n  or perform end-to-end QA on any application. Works on cloud VMs, Docker\n  containers, local machines, and sandboxes. Install: pip install cua.\n---\n\n# GUI Automation\n\nCUA gives you **eyes and hands on a real computer**: see the screen, move the\nmouse, click, type, drag, and manage windows — like a human at the keyboard.\n\nUse this skill for **visual interaction** that can't be done via shell or API.\n\n## Setup\n\n```bash\ncua --version          # check install; if missing: pip install cua\n\n# Connect to target (pick one)\ncua do switch cloud my-vm\ncua do switch docker my-container\ncua do-host-consent && cua do switch host   # local machine (one-time consent)\n```\n\n> `ANTHROPIC_API_KEY` is optional. With it, `cua do snapshot` returns an\n> AI-annotated screen with element coordinates. Without it, use `screenshot`\n> and read the image yourself.\n\n## Workflow\n\n**Look → Act → Verify** — repeat until done, then share:\n\n```bash\ncua do screenshot          # look\ncua do click 450 280       # act\ncua do screenshot          # verify\ncua trajectory share       # share replay link with user\n```\n\n> Re-screenshot after every UI change — coordinates go stale when the screen changes.\n\n## Scenarios\n\n### Click a button\n\n```bash\ncua do screenshot\ncua do click 450 280\ncua do screenshot\n```\n\n### Fill a form\n\n```bash\ncua do screenshot\ncua do click 400 200 && cua do type \"Jane Doe\"\ncua do key tab            && cua do type \"jane@example.com\"\ncua do key tab            && cua do type \"SecureP@ss123\"\ncua do click 400 500\ncua do screenshot\n```\n\n### File upload dialog\n\n```bash\ncua do click 350 400       # \"Choose File\"\ncua do type \"\u002Fhome\u002Fuser\u002Freport.pdf\"\ncua do key enter\ncua do screenshot\n```\n\n### Zoom in for precision clicks (host or small targets)\n\nWhen clicking small or dense UI elements — especially on the host machine —\nzoom into the target window first. Coordinates become **window-relative** and\nscreenshots show only that window, giving you higher effective resolution.\n\n```bash\ncua do zoom \"Google Chrome\"   # crop to Chrome window; coords are now window-relative\ncua do screenshot              # zoomed view — easier to locate small elements\ncua do click 112 44            # precise click on a small tab or button\ncua do screenshot              # verify\ncua do unzoom                  # restore full-screen coords when done\ncua do screenshot              # back to full desktop view\n```\n\n> Use `zoom` any time click accuracy is uncertain. `unzoom` before switching\n> windows or when you need to see the full desktop again.\n\n### Drag and drop\n\n```bash\ncua do window ls               # list open windows\ncua do drag 150 300 650 400    # source → destination\ncua do screenshot\n```\n\n### Fuzz a form\n\n```bash\ncua do screenshot\ncua do click 400 200\ncua do type \"\u003Cscript>alert(1)\u003C\u002Fscript>\"\ncua do key tab && cua do type \"'; DROP TABLE users; --\"\ncua do key tab && cua do type \"AAAAAAAAAAAAAAAAAAAAAAA\"\ncua do click 400 500\ncua do screenshot              # check for errors, crashes, unexpected behavior\n```\n\n## Trajectory\n\nEvery action is auto-recorded to `~\u002F.cua\u002Ftrajectories\u002F{machine}\u002F{session}\u002F`.\n\n```bash\ncua trajectory share           # upload and get shareable HTTPS link (always do this at end)\ncua trajectory ls              # list sessions\ncua trajectory export          # generate HTML report\ncua do --no-record click 100 200   # disable recording for a single action\n```\n\nTell the user: `\"Here is the trajectory of my session: {url}\"`\n\n## Quick Reference\n\n| Action              | Command                                      |\n| ------------------- | -------------------------------------------- |\n| Connect to target   | `cua do switch \u003Cprovider> [name]`            |\n| Screenshot          | `cua do screenshot`                          |\n| AI-annotated screen | `cua do snapshot [\"instructions\"]`           |\n| Click               | `cua do click \u003Cx> \u003Cy> [left|right|middle]`   |\n| Double-click        | `cua do dclick \u003Cx> \u003Cy>`                      |\n| Type text           | `cua do type \"text\"`                         |\n| Press key           | `cua do key \u003Ckey>`                            |\n| Hotkey              | `cua do hotkey \u003Ccombo>` (e.g. `ctrl+c`)      |\n| Scroll              | `cua do scroll \u003Cdirection> [amount]`         |\n| Drag               | `cua do drag \u003Cx1> \u003Cy1> \u003Cx2> \u003Cy2>`            |\n| Move cursor         | `cua do move \u003Cx> \u003Cy>`                        |\n| Shell command       | `cua do shell \"command\"`                     |\n| Open URL\u002Ffile       | `cua do open \u003Curl|path>`                     |\n| List windows        | `cua do window ls [app]`                     |\n| Focus window        | `cua do window focus \u003Cid>`                   |\n| Zoom to window      | `cua do zoom \"App Name\"`                     |\n| Unzoom              | `cua do unzoom`                              |\n| Share trajectory    | `cua trajectory share`                       |\n\n## Providers\n\n| Provider     | Example                             |\n|--------------|-------------------------------------|\n| `cloud`      | `cua do switch cloud my-vm`          |\n| `cloudv2`    | `cua do switch cloudv2 my-vm`        |\n| `docker`     | `cua do switch docker my-container` |\n| `lume`       | `cua do switch lume my-vm`           |\n| `lumier`     | `cua do switch lumier my-vm`         |\n| `winsandbox` | `cua do switch winsandbox`           |\n| `host`       | `cua do switch host`                 |\n\nSee [references\u002Fcommand-reference.md](references\u002Fcommand-reference.md) for full argument syntax.\n","# GUI Automation\n\nCUA gives you **eyes and hands on a real computer**: see the screen, move the\nmouse, click, type, drag, and manage windows — like a human at the keyboard.\n\nUse this skill for **visual interaction** that can't be done via shell or API.\n\n## Setup\n\n```bash\ncua --version          # check install; if missing: pip install cua\n\n# Connect to target (pick one)\ncua do switch cloud my-vm\ncua do switch docker my-container\ncua do-host-consent && cua do switch host   # local machine (one-time consent)\n```\n\n> `ANTHROPIC_API_KEY` is optional. With it, `cua do snapshot` returns an\n> AI-annotated screen with element coordinates. Without it, use `screenshot`\n> and read the image yourself.\n\n## Workflow\n\n**Look → Act → Verify** — repeat until done, then share:\n\n```bash\ncua do screenshot          # look\ncua do click 450 280       # act\ncua do screenshot          # verify\ncua trajectory share       # share replay link with user\n```\n\n> Re-screenshot after every UI change — coordinates go stale when the screen changes.\n\n## Scenarios\n\n### Click a button\n\n```bash\ncua do screenshot\ncua do click 450 280\ncua do screenshot\n```\n\n### Fill a form\n\n```bash\ncua do screenshot\ncua do click 400 200 && cua do type \"Jane Doe\"\ncua do key tab            && cua do type \"jane@example.com\"\ncua do key tab            && cua do type \"SecureP@ss123\"\ncua do click 400 500\ncua do screenshot\n```\n\n### File upload dialog\n\n```bash\ncua do click 350 400       # \"Choose File\"\ncua do type \"\u002Fhome\u002Fuser\u002Freport.pdf\"\ncua do key enter\ncua do screenshot\n```\n\n### Zoom in for precision clicks (host or small targets)\n\nWhen clicking small or dense UI elements — especially on the host machine —\nzoom into the target window first. Coordinates become **window-relative** and\nscreenshots show only that window, giving you higher effective resolution.\n\n```bash\ncua do zoom \"Google Chrome\"   # crop to Chrome window; coords are now window-relative\ncua do screenshot              # zoomed view — easier to locate small elements\ncua do click 112 44            # precise click on a small tab or button\ncua do screenshot              # verify\ncua do unzoom                  # restore full-screen coords when done\ncua do screenshot              # back to full desktop view\n```\n\n> Use `zoom` any time click accuracy is uncertain. `unzoom` before switching\n> windows or when you need to see the full desktop again.\n\n### Drag and drop\n\n```bash\ncua do window ls               # list open windows\ncua do drag 150 300 650 400    # source → destination\ncua do screenshot\n```\n\n### Fuzz a form\n\n```bash\ncua do screenshot\ncua do click 400 200\ncua do type \"\u003Cscript>alert(1)\u003C\u002Fscript>\"\ncua do key tab && cua do type \"'; DROP TABLE users; --\"\ncua do key tab && cua do type \"AAAAAAAAAAAAAAAAAAAAAAA\"\ncua do click 400 500\ncua do screenshot              # check for errors, crashes, unexpected behavior\n```\n\n## Trajectory\n\nEvery action is auto-recorded to `~\u002F.cua\u002Ftrajectories\u002F{machine}\u002F{session}\u002F`.\n\n```bash\ncua trajectory share           # upload and get shareable HTTPS link (always do this at end)\ncua trajectory ls              # list sessions\ncua trajectory export          # generate HTML report\ncua do --no-record click 100 200   # disable recording for a single action\n```\n\nTell the user: `\"Here is the trajectory of my session: {url}\"`\n\n## Quick Reference\n\n| Action              | Command                                      |\n| ------------------- | -------------------------------------------- |\n| Connect to target   | `cua do switch \u003Cprovider> [name]`            |\n| Screenshot          | `cua do screenshot`                          |\n| AI-annotated screen | `cua do snapshot [\"instructions\"]`           |\n| Click               | `cua do click \u003Cx> \u003Cy> [left|right|middle]`   |\n| Double-click        | `cua do dclick \u003Cx> \u003Cy>`                      |\n| Type text           | `cua do type \"text\"`                         |\n| Press key           | `cua do key \u003Ckey>`                            |\n| Hotkey              | `cua do hotkey \u003Ccombo>` (e.g. `ctrl+c`)      |\n| Scroll              | `cua do scroll \u003Cdirection> [amount]`         |\n| Drag               | `cua do drag \u003Cx1> \u003Cy1> \u003Cx2> \u003Cy2>`            |\n| Move cursor         | `cua do move \u003Cx> \u003Cy>`                        |\n| Shell command       | `cua do shell \"command\"`                     |\n| Open URL\u002Ffile       | `cua do open \u003Curl|path>`                     |\n| List windows        | `cua do window ls [app]`                     |\n| Focus window        | `cua do window focus \u003Cid>`                   |\n| Zoom to window      | `cua do zoom \"App Name\"`                     |\n| Unzoom              | `cua do unzoom`                              |\n| Share trajectory    | `cua trajectory share`                       |\n\n## Providers\n\n| Provider     | Example                             |\n|--------------|-------------------------------------|\n| `cloud`      | `cua do switch cloud my-vm`          |\n| `cloudv2`    | `cua do switch cloudv2 my-vm`        |\n| `docker`     | `cua do switch docker my-container` |\n| `lume`       | `cua do switch lume my-vm`           |\n| `lumier`     | `cua do switch lumier my-vm`         |\n| `winsandbox` | `cua do switch winsandbox`           |\n| `host`       | `cua do switch host`                 |\n\nSee [references\u002Fcommand-reference.md](references\u002Fcommand-reference.md) for full argument syntax.\n",{"name":5,"description":7},"main","32794f82cde37d7beb6bd5a3ec6b2627df6343e1","assets\u002Fskills\u002Fgui-automation",0,"https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop","https:\u002F\u002Fgithub.com\u002FSenCha930511","2026-10-29 14:13:50",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add SenCha930511\u002Fomp-desktop --skill gui-automation",{"tool":37,"command":38},"bunx","bunx skills add SenCha930511\u002Fomp-desktop --skill gui-automation",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SenCha930511\u002Fomp-desktop --skill gui-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fgui-automation\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7EZCNGTT0C0T7MT3AZ4S1H5","gooeypi-computer-use","Drive native applications on macOS, Windows, or Linux through the separately installed TryCUA driver CLI.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002Fassets\u002Fskills\u002Fgooeypi-computer-use\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7EZCGWBSA4YMNJWZNE1THZM","verify-omp-desktop","Launch and drive the OMP Desktop desktop (Electron) app to prove user-facing behavior — sidebar navigation, Settings, and Capabilities — capturing screenshots and ARIA snapshots. Reach for this when verifying a OMP Desktop UI change or confirming the app still works end to end.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.cursor\u002Fskills\u002Fverify-omp-desktop\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7EZCEEK5702GNYQQ74J8XAR","review-pr-viability","Review a pull request or issue for value, implementation quality, maintainability, regression risk, and reliance on upstream changes.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Freview-pr-viability\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7EZC8CEFJ14446XSEMV807Q","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpstack\u002Fwhy\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7EZC61F3RFAV186YZT6R9ZM","unslop","Cut AI tells from any writing. Must always apply.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpstack\u002Funslop\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7EZC45MYQZW97YD28P5X7J8","typescript-best-practices","TypeScript best practices. Use when reading or editing any .ts or .tsx file.","https:\u002F\u002Fgithub.com\u002FSenCha930511\u002Fomp-desktop\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fpstack\u002Ftypescript-best-practices\u002FSKILL.md",[],[]]