[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDZXTWBNA0VFGCC97YB6DK":3,"skill-same:01M7FDZXTWBNA0VFGCC97YB6DK":46},{"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":30,"updatedAt":31,"install":32,"resources":45},"01M7FDZXTWBNA0VFGCC97YB6DK","browser-automation",null,"Use the Browser Automation BB plugin to inspect and automate persistent browser pages in an explicit desktop or local headless session. Use for browser navigation, snapshots, clicking, forms, and verification screenshots.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fbrowser-automation\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: browser-automation\ndescription: Use the Browser Automation BB plugin to inspect and automate persistent browser pages in an explicit desktop or local headless session. Use for browser navigation, snapshots, clicking, forms, and verification screenshots.\n---\n\nUse `bb browser-automation`. Open one session, retain its session ID, then inspect,\nact, and verify in short scripts.\n\nChoose `--backend local --headless --machine \u003Chost-id>` for headless Chrome on\nan enrolled host. Choose `--backend desktop --machine \u003Chost-id> --desktop\n\u003Cinstance-id>` for a new dedicated desktop automation tab. Starting desktop\ncontrol opens and focuses the browser panel; new pages created through that\ncontroller are selected automatically. Headless sessions remain headless.\nResolve the explicit instance with `bb browser instances --host \u003Chost-id> --json`\nfirst. Never silently choose a different host, mode, or login profile.\nAdding `--tab \u003Ctab-id>` hands off an existing tab and its profile's logged-in\nauthority; do so only when the user asked to use that tab. The CLI uses the\ncurrent thread, or `--thread \u003Cid>` outside a thread. Each session belongs to\nthat thread.\n\nCLI opening:\n\n```sh\nbb browser-automation open --backend local --headless --machine \u003Chost-id> --json\nbb browser-automation open --backend desktop --machine \u003Chost-id> --desktop \u003Cinstance-id> --json\n```\n\nRun scripts:\n\n```sh\nbb browser-automation run \u003Csession-id> --script 'const p = await browser.getPage(\"main\"); await p.goto(\"https:\u002F\u002Fexample.com\"); await p.snapshot()' --json\nbb browser-automation run \u003Csession-id> --script 'const p = await browser.getPage(\"main\"); await p.click(\"ref\u002Fe6\"); await p.snapshot()' --json\nbb browser-automation screenshot \u003Csession-id> --page main --json\n```\n\nTake a fresh snapshot before using refs after navigation or document changes.\nUse refs from that session's DevBrowser snapshot. Do not mix agent-browser refs\nor invent selectors. Prefer a cheap URL\u002Ftext\u002Fsnapshot check after each action;\nrequest a screenshot when visual verification matters. Use\n`await p.shot({type:\"jpeg\",maxEdge:960,quality:70}); undefined` inside scripts to\nreturn a bounded JPEG file.\n\n`run` and `screenshot` return JSON with `hostId` and `images`, where each image\nhas `path`, `mimeType`, `width`, and `height`. The path is in the browser session's\ntemporary directory on that host. Use your image-reading tool on the path when\nyou are on the same machine. If the browser host differs, fetch the image to\nlocal temporary storage first (substitute the returned path and host ID):\n\n```sh\nbb file read '\u003Cimage-path>' --host '\u003Chost-id>' --json | node -e '\nconst fs = require(\"node:fs\"), os = require(\"node:os\"), path = require(\"node:path\");\nconst file = JSON.parse(fs.readFileSync(0, \"utf8\"));\nif (file.contentEncoding !== \"base64\") throw new Error(\"Expected binary image\");\nconst destination = path.join(fs.mkdtempSync(path.join(os.tmpdir(), \"browser-image-\")), \"capture.jpg\");\nfs.writeFileSync(destination, Buffer.from(file.content, \"base64\"), {mode: 0o600});\nconsole.log(destination);\n'\n```\n\nRead the printed local path with your image-reading tool. Do not print base64\nimage bytes into the conversation. Read or copy captures before closing the\nsession: cleanup removes its temporary directory. Remove local copies when\nfinished.\n\n`pages` lists persistent pages. Runs serialize within a session. Scripts are\ntrusted JavaScript with Puppeteer-style DevBrowser APIs, not a sandbox.\n`--script-file` requires `--script-host \u003Chost-id>` naming the source host explicitly. Browser file\noperations and `localhost` refer to the browser host. Transfer files explicitly.\n\nStop cancels running and queued work and releases desktop control. Cancellation\nand timeout stop the session too; open a new session to resume. Close disposes\nowned Chrome and plugin-created desktop tabs while preserving handed-off tabs.\nClose sessions after use. Five-minute idle and thirty-minute absolute expiry\napply. Timeouts default to 30 seconds, maximum 120 seconds.\n\nAn unavailable backend or a failed runtime install is an actionable setup\nerror, not permission to attach to a random browser. The first open on a host\ninstalls the pinned `dev-browser` npm release into plugin-owned host storage\nthere and verifies its provenance and digest; it needs npm, network access, and\nChrome on that host, and can take a minute. Later opens reuse the verified\ninstall offline. The exact pin and Chrome setup are documented in the plugin\nREADME. Cloud browsers and arbitrary CDP endpoints are unsupported.\n","Use `bb browser-automation`. Open one session, retain its session ID, then inspect,\nact, and verify in short scripts.\n\nChoose `--backend local --headless --machine \u003Chost-id>` for headless Chrome on\nan enrolled host. Choose `--backend desktop --machine \u003Chost-id> --desktop\n\u003Cinstance-id>` for a new dedicated desktop automation tab. Starting desktop\ncontrol opens and focuses the browser panel; new pages created through that\ncontroller are selected automatically. Headless sessions remain headless.\nResolve the explicit instance with `bb browser instances --host \u003Chost-id> --json`\nfirst. Never silently choose a different host, mode, or login profile.\nAdding `--tab \u003Ctab-id>` hands off an existing tab and its profile's logged-in\nauthority; do so only when the user asked to use that tab. The CLI uses the\ncurrent thread, or `--thread \u003Cid>` outside a thread. Each session belongs to\nthat thread.\n\nCLI opening:\n\n```sh\nbb browser-automation open --backend local --headless --machine \u003Chost-id> --json\nbb browser-automation open --backend desktop --machine \u003Chost-id> --desktop \u003Cinstance-id> --json\n```\n\nRun scripts:\n\n```sh\nbb browser-automation run \u003Csession-id> --script 'const p = await browser.getPage(\"main\"); await p.goto(\"https:\u002F\u002Fexample.com\"); await p.snapshot()' --json\nbb browser-automation run \u003Csession-id> --script 'const p = await browser.getPage(\"main\"); await p.click(\"ref\u002Fe6\"); await p.snapshot()' --json\nbb browser-automation screenshot \u003Csession-id> --page main --json\n```\n\nTake a fresh snapshot before using refs after navigation or document changes.\nUse refs from that session's DevBrowser snapshot. Do not mix agent-browser refs\nor invent selectors. Prefer a cheap URL\u002Ftext\u002Fsnapshot check after each action;\nrequest a screenshot when visual verification matters. Use\n`await p.shot({type:\"jpeg\",maxEdge:960,quality:70}); undefined` inside scripts to\nreturn a bounded JPEG file.\n\n`run` and `screenshot` return JSON with `hostId` and `images`, where each image\nhas `path`, `mimeType`, `width`, and `height`. The path is in the browser session's\ntemporary directory on that host. Use your image-reading tool on the path when\nyou are on the same machine. If the browser host differs, fetch the image to\nlocal temporary storage first (substitute the returned path and host ID):\n\n```sh\nbb file read '\u003Cimage-path>' --host '\u003Chost-id>' --json | node -e '\nconst fs = require(\"node:fs\"), os = require(\"node:os\"), path = require(\"node:path\");\nconst file = JSON.parse(fs.readFileSync(0, \"utf8\"));\nif (file.contentEncoding !== \"base64\") throw new Error(\"Expected binary image\");\nconst destination = path.join(fs.mkdtempSync(path.join(os.tmpdir(), \"browser-image-\")), \"capture.jpg\");\nfs.writeFileSync(destination, Buffer.from(file.content, \"base64\"), {mode: 0o600});\nconsole.log(destination);\n'\n```\n\nRead the printed local path with your image-reading tool. Do not print base64\nimage bytes into the conversation. Read or copy captures before closing the\nsession: cleanup removes its temporary directory. Remove local copies when\nfinished.\n\n`pages` lists persistent pages. Runs serialize within a session. Scripts are\ntrusted JavaScript with Puppeteer-style DevBrowser APIs, not a sandbox.\n`--script-file` requires `--script-host \u003Chost-id>` naming the source host explicitly. Browser file\noperations and `localhost` refer to the browser host. Transfer files explicitly.\n\nStop cancels running and queued work and releases desktop control. Cancellation\nand timeout stop the session too; open a new session to resume. Close disposes\nowned Chrome and plugin-created desktop tabs while preserving handed-off tabs.\nClose sessions after use. Five-minute idle and thirty-minute absolute expiry\napply. Timeouts default to 30 seconds, maximum 120 seconds.\n\nAn unavailable backend or a failed runtime install is an actionable setup\nerror, not permission to attach to a random browser. The first open on a host\ninstalls the pinned `dev-browser` npm release into plugin-owned host storage\nthere and verifies its provenance and digest; it needs npm, network access, and\nChrome on that host, and can take a minute. Later opens reuse the verified\ninstall offline. The exact pin and Chrome setup are documented in the plugin\nREADME. Cloud browsers and arbitrary CDP endpoints are unsupported.\n",{"name":5,"description":7},"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","07-后端与架构\u002Fbrowser-automation",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill browser-automation",{"tool":38,"command":39},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill browser-automation",{"tool":41,"command":42},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill browser-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fbrowser-automation\u002FSKILL.md",true,[],[47,54,59,66,73,80],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":55,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]