[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79JVRFK3WVCKRCVZ0S1K0X8":3,"skill-same:01M79JVRFK3WVCKRCVZ0S1K0X8":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M79JVRFK3WVCKRCVZ0S1K0X8","cua-driver-operation",null,"Operate PipiUI's pinned Cua Driver through snapshot, semantic locate, coherent action batch, and fresh verification.","Leehow\u002Fpipiui","Leehow","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F8022275?v=4","01M79JQKJ75AT6BQD6Q8BDZ6HX","01M79JQKK1HF42F74CMVWVS2ZJ",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui\u002Fblob\u002Fmain\u002FElectron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fcua-driver-operation\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cua-driver-operation\ndescription: Operate PipiUI's pinned Cua Driver through snapshot, semantic locate, coherent action batch, and fresh verification.\nmetadata:\n  cua-driver-version: \"0.20.0\"\n  upstream: https:\u002F\u002Fgithub.com\u002Ftrycua\u002Fcua\u002Ftree\u002Fmain\u002Flibs\u002Fcua-driver\u002Frust\u002FSkills\u002Fcua-driver\n---\n\n# Cua Driver Operation\n\nThis private adaptation is pinned to Cua Driver 0.20.0. Use the exact pinned application\u002Fwindow target. `desktop_open_application` success already pins the exact window and brings it to the front: immediately call a fresh `desktop_observe`. Never use Command-Tab, Command-Shift-Tab, or the app switcher to locate or refocus that application. Observe before acting, prefer AX\u002Fsemantic locators over pixels, batch coherent sequences, and obtain a fresh observation after consequential mutation. A timeout or driver error can mean unknown outcome: never repeat the mutation before observing.\n\nNative macOS application menus are application-level AX surfaces and may be absent from the pinned content-window observation. Use one exact `desktop_act` action `{type:\"invoke_menu\",path:[\u003Ctop-level menu>,\u003Cimmediate child>,...]}`. Every path segment must be a literal live menu label; the Host keeps the call bound to the already-proven pinned PID and the driver fails closed on missing, ambiguous, disabled, or structurally mismatched segments. Never guess an outside-window coordinate for a menu bar or menu item.\n\nEvery state mutation consumes the current observation. Before any later click, scroll, key, typing, or other mutation, call `desktop_observe` with `fresh:true` and re-evaluate the returned UI. A mutation batch may contain only one state mutation; only a bounded wait may follow it in that same batch. `fresh_observation_required_after_mutation` is recoverable by observing, not by trying a different blind mutation.\n\nTreat long-running target work as a temporal state, not as a failed Postcondition. A collapsible `thinking`, `internal notes`, `side note`, or similarly named disclosure label is not an error by itself. Never expand or open that disclosure to inspect raw chain-of-thought, and never count its presence as success. Only an explicit RPC, provider, runtime, or target error message is error evidence.\n\nWhen the target shows an in-progress cluster — for example, its input is disabled and a stop control or progress status is visible — compare fresh observations instead of judging from one frame. A step, elapsed-time, token, or status value that advances is progress. Use one bounded wait of at most 15 seconds followed by a fresh observe, and repeat only while progress advances and the current worker deadline still permits it. This wait-and-observe loop must not extend or re-arm the worker deadline. Completion requires terminal UI evidence: the input is enabled, the stop control disappears, and a new reply or the declared Postcondition is visible. If an explicit error appears, or the progress evidence stops changing until the existing no-progress\u002Fdeadline policy is exhausted, return the closed honest failure\u002Fblock result; do not invent completion and do not wait indefinitely.\n\nEvery wait used for pending progress creates a mandatory post-wait observation fence. The Operator must not return any terminal outcome — `completed`, `verified`, `blocked`, or `failed` — until `desktop_observe` with `fresh:true` succeeds after that exact wait. A failed or timed-out observe does not clear the fence, and a pre-wait screenshot cannot be reused after waiting. Only the successful post-wait observation may judge terminal UI, Postconditions, explicit error evidence, or no-progress. Do not issue a wait unless the current worker deadline leaves time for its required fresh observe; never extend or re-arm that deadline. If cancellation or the deadline ends the worker before the required observation succeeds, let the runtime cancellation\u002Fdeadline path close the worker instead of inferring a verdict from stale UI.\n\nWhen a fresh observation exposes an interactive `AXButton` and a same-name container or static text, call `desktop_locate` with the exact interactive role and name first, then click only the returned binding\u002Ftoken. A container, group, or static text is evidence, never an interactive substitute. When a blocking onboarding, modal, or interstitial exposes an explicit non-destructive continue button consistent with the goal, resolve and activate that button first, then fresh-observe before continuing. Never blind-scroll or send hotkeys around a blocking layer.\n\nWhen a fresh observation proves the pinned application is in the wrong target state **and the task explicitly forbids every safe action needed to restore it** (for example, clicking, closing, reopening, or recovery), return exactly `{\"outcome\":\"blocked\",\"summary\":\"Target state requires manual restoration before retry.\",\"recoveryDisposition\":\"manual_intervention\",\"blockedReason\":\"target_state_mismatch\",\"nextAction\":\"restore_target_state_manually\"}`. This is a closed manual-intervention signal, not ordinary failure prose. Do not use it for a failed locator, missing text with an allowed recovery path, a transient driver error, or an untried safe alternative.\n","# Cua Driver Operation\n\nThis private adaptation is pinned to Cua Driver 0.20.0. Use the exact pinned application\u002Fwindow target. `desktop_open_application` success already pins the exact window and brings it to the front: immediately call a fresh `desktop_observe`. Never use Command-Tab, Command-Shift-Tab, or the app switcher to locate or refocus that application. Observe before acting, prefer AX\u002Fsemantic locators over pixels, batch coherent sequences, and obtain a fresh observation after consequential mutation. A timeout or driver error can mean unknown outcome: never repeat the mutation before observing.\n\nNative macOS application menus are application-level AX surfaces and may be absent from the pinned content-window observation. Use one exact `desktop_act` action `{type:\"invoke_menu\",path:[\u003Ctop-level menu>,\u003Cimmediate child>,...]}`. Every path segment must be a literal live menu label; the Host keeps the call bound to the already-proven pinned PID and the driver fails closed on missing, ambiguous, disabled, or structurally mismatched segments. Never guess an outside-window coordinate for a menu bar or menu item.\n\nEvery state mutation consumes the current observation. Before any later click, scroll, key, typing, or other mutation, call `desktop_observe` with `fresh:true` and re-evaluate the returned UI. A mutation batch may contain only one state mutation; only a bounded wait may follow it in that same batch. `fresh_observation_required_after_mutation` is recoverable by observing, not by trying a different blind mutation.\n\nTreat long-running target work as a temporal state, not as a failed Postcondition. A collapsible `thinking`, `internal notes`, `side note`, or similarly named disclosure label is not an error by itself. Never expand or open that disclosure to inspect raw chain-of-thought, and never count its presence as success. Only an explicit RPC, provider, runtime, or target error message is error evidence.\n\nWhen the target shows an in-progress cluster — for example, its input is disabled and a stop control or progress status is visible — compare fresh observations instead of judging from one frame. A step, elapsed-time, token, or status value that advances is progress. Use one bounded wait of at most 15 seconds followed by a fresh observe, and repeat only while progress advances and the current worker deadline still permits it. This wait-and-observe loop must not extend or re-arm the worker deadline. Completion requires terminal UI evidence: the input is enabled, the stop control disappears, and a new reply or the declared Postcondition is visible. If an explicit error appears, or the progress evidence stops changing until the existing no-progress\u002Fdeadline policy is exhausted, return the closed honest failure\u002Fblock result; do not invent completion and do not wait indefinitely.\n\nEvery wait used for pending progress creates a mandatory post-wait observation fence. The Operator must not return any terminal outcome — `completed`, `verified`, `blocked`, or `failed` — until `desktop_observe` with `fresh:true` succeeds after that exact wait. A failed or timed-out observe does not clear the fence, and a pre-wait screenshot cannot be reused after waiting. Only the successful post-wait observation may judge terminal UI, Postconditions, explicit error evidence, or no-progress. Do not issue a wait unless the current worker deadline leaves time for its required fresh observe; never extend or re-arm that deadline. If cancellation or the deadline ends the worker before the required observation succeeds, let the runtime cancellation\u002Fdeadline path close the worker instead of inferring a verdict from stale UI.\n\nWhen a fresh observation exposes an interactive `AXButton` and a same-name container or static text, call `desktop_locate` with the exact interactive role and name first, then click only the returned binding\u002Ftoken. A container, group, or static text is evidence, never an interactive substitute. When a blocking onboarding, modal, or interstitial exposes an explicit non-destructive continue button consistent with the goal, resolve and activate that button first, then fresh-observe before continuing. Never blind-scroll or send hotkeys around a blocking layer.\n\nWhen a fresh observation proves the pinned application is in the wrong target state **and the task explicitly forbids every safe action needed to restore it** (for example, clicking, closing, reopening, or recovery), return exactly `{\"outcome\":\"blocked\",\"summary\":\"Target state requires manual restoration before retry.\",\"recoveryDisposition\":\"manual_intervention\",\"blockedReason\":\"target_state_mismatch\",\"nextAction\":\"restore_target_state_manually\"}`. This is a closed manual-intervention signal, not ordinary failure prose. Do not use it for a failed locator, missing text with an allowed recovery path, a transient driver error, or an untried safe alternative.\n",{"name":5,"metadata":23,"description":7},{"upstream":24,"cua-driver-version":25},"https:\u002F\u002Fgithub.com\u002Ftrycua\u002Fcua\u002Ftree\u002Fmain\u002Flibs\u002Fcua-driver\u002Frust\u002FSkills\u002Fcua-driver","0.20.0","main","0fc8c5f1d479ff1d7a0f392920d9479a67d4d884","Electron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fcua-driver-operation",0,"https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui","https:\u002F\u002Fpipi.aichattrpg.com\u002F","https:\u002F\u002Fgithub.com\u002FLeehow","2026-10-22 22:52:03",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Leehow\u002Fpipiui --skill cua-driver-operation",{"tool":40,"command":41},"bunx","bunx skills add Leehow\u002Fpipiui --skill cua-driver-operation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Leehow\u002Fpipiui --skill cua-driver-operation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui\u002Fblob\u002Fmain\u002FElectron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fcua-driver-operation\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M79JW5VYX2QR2404PD7WARKS","terminal-investigation","Bounded file discovery and terminal execution for a Computer Task Terminal Worker.","https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui\u002Fblob\u002Fmain\u002FElectron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fterminal-investigation\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M79JW2KXB8C795WKCMA3YQXH","procedure-learning","Compile verified Computer Task exploration into safe parameterized Procedure candidates.","https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui\u002Fblob\u002Fmain\u002FElectron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fprocedure-learning\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M79JVZ6B01YXQJNDRYQHMRY9","desktop-verification","Verify a Computer Task from a fresh observation without repairing or mutating the target.","https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui\u002Fblob\u002Fmain\u002FElectron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fdesktop-verification\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M79JVWSCCH7MKFKP9NJC4N4G","desktop-investigation","Locate desktop controls with semantic evidence and bounded visual fallback.","https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui\u002Fblob\u002Fmain\u002FElectron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fdesktop-investigation\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M79JVMQP7N4SR5HP5QYWMZD3","computer-task-recovery","Replan after target loss, ambiguous location, unknown mutation outcome, or failed verification.","https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui\u002Fblob\u002Fmain\u002FElectron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fcomputer-task-recovery\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M79JVJQ4BNFJFV1W4XXCB7WB","computer-task-planning","Turn one natural-language desktop goal into the shortest observable direct path or a small dependency plan.","https:\u002F\u002Fgithub.com\u002FLeehow\u002Fpipiui\u002Fblob\u002Fmain\u002FElectron\u002Fresources\u002Fruntime\u002Fpi-ext\u002Fpackages\u002Fcomputer-agent\u002Fskills\u002Fcomputer-task-planning\u002FSKILL.md",[],[]]