[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KSBAQ9BXVEJQJB0ARMHVQ1":3,"skill-same:01M6KSBAQ9BXVEJQJB0ARMHVQ1":71},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":6,"updatedAt":56,"install":57,"resources":70},"01M6KSBAQ9BXVEJQJB0ARMHVQ1","playwright-bowser",null,"Headless browser automation using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, web scraping, or browser automation that can run in the background. Keywords - playwright, headless, browser, test, screenshot, scrape, parallel.","hollis-labs\u002Fnanite","hollis-labs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F209122427?v=4","01M6KSB2TDHAKZP6JEBD24X8ZQ","Hollis Labs","01M6KSB31JT4Q9NEY4X5ZYWBT1",1,"MIT","https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite\u002Fblob\u002Fmain\u002Finternal\u002Fassets\u002Fframework\u002Fdocs\u002Fref-playwright-bowser\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"playwright bowser","playwright","Bash","browsing","headless","can","you","use","scraping","web scraping","parallel","testing","scrape","browser","sessions","playwright cli","test","automation","browser automation","cli","2026-11-10 10:12:30",false,"---\nname: playwright-bowser\ndescription: Headless browser automation using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, web scraping, or browser automation that can run in the background. Keywords - playwright, headless, browser, test, screenshot, scrape, parallel.\nallowed-tools: Bash\n---\n\n# Playwright Bowser\n\n## Purpose\n\nAutomate browsers using `playwright-cli` — a token-efficient CLI for Playwright. Runs headless by default, supports parallel sessions via named sessions (`-s=`), and doesn't load tool schemas into context.\n\n## Key Details\n\n- **Headless by default** — pass `--headed` to `open` to see the browser\n- **Parallel sessions** — use `-s=\u003Cname>` to run multiple independent browser instances\n- **Persistent profiles** — cookies and storage state preserved between calls\n- **Token-efficient** — CLI-based, no accessibility trees or tool schemas in context\n- **Vision mode** (opt-in) — set `PLAYWRIGHT_MCP_CAPS=vision` to receive screenshots as image responses in context instead of just saving to disk\n\n## Sessions\n\n**Always use a named session.** Derive a short, descriptive kebab-case name from the user's prompt. This gives each task a persistent browser profile (cookies, localStorage, history) that accumulates across calls.\n\n```bash\n# Derive session name from prompt context:\n# \"test the volon dashboard\" → -s=volon-dashboard\n# \"UI test the tasks page\"  → -s=volon-tasks\n\nplaywright-cli -s=volon-dashboard open http:\u002F\u002Flocalhost:5173 --persistent\nplaywright-cli -s=volon-dashboard snapshot\nplaywright-cli -s=volon-dashboard click e12\n```\n\nManaging sessions:\n```bash\nplaywright-cli list                      # list all sessions\nplaywright-cli close-all                 # close all sessions\nplaywright-cli -s=\u003Cname> close           # close specific session\nplaywright-cli -s=\u003Cname> delete-data     # wipe session profile\n```\n\n## Quick Reference\n\n```\nCore:       open [url], goto \u003Curl>, click \u003Cref>, fill \u003Cref> \u003Ctext>, type \u003Ctext>, snapshot, screenshot [ref], close\nNavigate:   go-back, go-forward, reload\nKeyboard:   press \u003Ckey>, keydown \u003Ckey>, keyup \u003Ckey>\nMouse:      mousemove \u003Cx> \u003Cy>, mousedown, mouseup, mousewheel \u003Cdx> \u003Cdy>\nTabs:       tab-list, tab-new [url], tab-close [index], tab-select \u003Cindex>\nSave:       screenshot [ref], pdf, screenshot --filename=f\nStorage:    state-save, state-load, cookie-*, localstorage-*, sessionstorage-*\nNetwork:    route \u003Cpattern>, route-list, unroute, network\nDevTools:   console, run-code \u003Ccode>, tracing-start\u002Fstop, video-start\u002Fstop\nSessions:   -s=\u003Cname> \u003Ccmd>, list, close-all, kill-all\nConfig:     open --headed, open --browser=chrome, resize \u003Cw> \u003Ch>\n```\n\n## Workflow\n\n1. Derive a session name from the user's prompt and open with `--persistent` to preserve cookies\u002Fstate. Always set the viewport via env var at launch:\n```bash\nPLAYWRIGHT_MCP_VIEWPORT_SIZE=1440x900 playwright-cli -s=\u003Csession-name> open \u003Curl> --persistent\n# or headed:\nPLAYWRIGHT_MCP_VIEWPORT_SIZE=1440x900 playwright-cli -s=\u003Csession-name> open \u003Curl> --persistent --headed\n# or with vision (screenshots returned as image responses in context):\nPLAYWRIGHT_MCP_VIEWPORT_SIZE=1440x900 PLAYWRIGHT_MCP_CAPS=vision playwright-cli -s=\u003Csession-name> open \u003Curl> --persistent\n```\n\n2. Get element references via snapshot:\n```bash\nplaywright-cli snapshot\n```\n\n3. Interact using refs from snapshot:\n```bash\nplaywright-cli click \u003Cref>\nplaywright-cli fill \u003Cref> \"text\"\nplaywright-cli type \"text\"\nplaywright-cli press Enter\n```\n\n4. Capture results:\n```bash\nplaywright-cli screenshot\nplaywright-cli screenshot --filename=output.png\n```\n\n5. **Always close the session when done.**\n```bash\nplaywright-cli -s=\u003Csession-name> close\n```\n\n## Fragments Engine GUI Defaults\n\n- Volon GUI dev server: `http:\u002F\u002Flocalhost:1420`\n- Volon API server: `http:\u002F\u002Flocalhost:8085`\n- Mentat GUI dev server: check Cerberus for current port\n- Screenshots output: `.\u002Fscreenshots\u002Fbowser-qa\u002F`\n\n## Full Help\n\nRun `playwright-cli --help` or `playwright-cli --help \u003Ccommand>` for detailed command usage.\n","# Playwright Bowser\n\n## Purpose\n\nAutomate browsers using `playwright-cli` — a token-efficient CLI for Playwright. Runs headless by default, supports parallel sessions via named sessions (`-s=`), and doesn't load tool schemas into context.\n\n## Key Details\n\n- **Headless by default** — pass `--headed` to `open` to see the browser\n- **Parallel sessions** — use `-s=\u003Cname>` to run multiple independent browser instances\n- **Persistent profiles** — cookies and storage state preserved between calls\n- **Token-efficient** — CLI-based, no accessibility trees or tool schemas in context\n- **Vision mode** (opt-in) — set `PLAYWRIGHT_MCP_CAPS=vision` to receive screenshots as image responses in context instead of just saving to disk\n\n## Sessions\n\n**Always use a named session.** Derive a short, descriptive kebab-case name from the user's prompt. This gives each task a persistent browser profile (cookies, localStorage, history) that accumulates across calls.\n\n```bash\n# Derive session name from prompt context:\n# \"test the volon dashboard\" → -s=volon-dashboard\n# \"UI test the tasks page\"  → -s=volon-tasks\n\nplaywright-cli -s=volon-dashboard open http:\u002F\u002Flocalhost:5173 --persistent\nplaywright-cli -s=volon-dashboard snapshot\nplaywright-cli -s=volon-dashboard click e12\n```\n\nManaging sessions:\n```bash\nplaywright-cli list                      # list all sessions\nplaywright-cli close-all                 # close all sessions\nplaywright-cli -s=\u003Cname> close           # close specific session\nplaywright-cli -s=\u003Cname> delete-data     # wipe session profile\n```\n\n## Quick Reference\n\n```\nCore:       open [url], goto \u003Curl>, click \u003Cref>, fill \u003Cref> \u003Ctext>, type \u003Ctext>, snapshot, screenshot [ref], close\nNavigate:   go-back, go-forward, reload\nKeyboard:   press \u003Ckey>, keydown \u003Ckey>, keyup \u003Ckey>\nMouse:      mousemove \u003Cx> \u003Cy>, mousedown, mouseup, mousewheel \u003Cdx> \u003Cdy>\nTabs:       tab-list, tab-new [url], tab-close [index], tab-select \u003Cindex>\nSave:       screenshot [ref], pdf, screenshot --filename=f\nStorage:    state-save, state-load, cookie-*, localstorage-*, sessionstorage-*\nNetwork:    route \u003Cpattern>, route-list, unroute, network\nDevTools:   console, run-code \u003Ccode>, tracing-start\u002Fstop, video-start\u002Fstop\nSessions:   -s=\u003Cname> \u003Ccmd>, list, close-all, kill-all\nConfig:     open --headed, open --browser=chrome, resize \u003Cw> \u003Ch>\n```\n\n## Workflow\n\n1. Derive a session name from the user's prompt and open with `--persistent` to preserve cookies\u002Fstate. Always set the viewport via env var at launch:\n```bash\nPLAYWRIGHT_MCP_VIEWPORT_SIZE=1440x900 playwright-cli -s=\u003Csession-name> open \u003Curl> --persistent\n# or headed:\nPLAYWRIGHT_MCP_VIEWPORT_SIZE=1440x900 playwright-cli -s=\u003Csession-name> open \u003Curl> --persistent --headed\n# or with vision (screenshots returned as image responses in context):\nPLAYWRIGHT_MCP_VIEWPORT_SIZE=1440x900 PLAYWRIGHT_MCP_CAPS=vision playwright-cli -s=\u003Csession-name> open \u003Curl> --persistent\n```\n\n2. Get element references via snapshot:\n```bash\nplaywright-cli snapshot\n```\n\n3. Interact using refs from snapshot:\n```bash\nplaywright-cli click \u003Cref>\nplaywright-cli fill \u003Cref> \"text\"\nplaywright-cli type \"text\"\nplaywright-cli press Enter\n```\n\n4. Capture results:\n```bash\nplaywright-cli screenshot\nplaywright-cli screenshot --filename=output.png\n```\n\n5. **Always close the session when done.**\n```bash\nplaywright-cli -s=\u003Csession-name> close\n```\n\n## Fragments Engine GUI Defaults\n\n- Volon GUI dev server: `http:\u002F\u002Flocalhost:1420`\n- Volon API server: `http:\u002F\u002Flocalhost:8085`\n- Mentat GUI dev server: check Cerberus for current port\n- Screenshots output: `.\u002Fscreenshots\u002Fbowser-qa\u002F`\n\n## Full Help\n\nRun `playwright-cli --help` or `playwright-cli --help \u003Ccommand>` for detailed command usage.\n",{"name":5,"description":7,"allowed-tools":26},"main","8cba301ffd1b108fe3111f9e5017a338d9c2001f","internal\u002Fassets\u002Fframework\u002Fdocs\u002Fref-playwright-bowser",0,"https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite","https:\u002F\u002Fgithub.com\u002Fhollis-labs","https:\u002F\u002Fhollislabs.com","2026-10-31 10:37:21",{"source":8,"skillName":5,"commands":58,"prompt":68,"zipAvailable":69},[59,62,65],{"tool":60,"command":61},"npx","npx skills add hollis-labs\u002Fnanite --skill playwright-bowser",{"tool":63,"command":64},"bunx","bunx skills add hollis-labs\u002Fnanite --skill playwright-bowser",{"tool":66,"command":67},"pnpm","pnpm dlx skills add hollis-labs\u002Fnanite --skill playwright-bowser","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite\u002Fblob\u002Fmain\u002Finternal\u002Fassets\u002Fframework\u002Fdocs\u002Fref-playwright-bowser\u002FSKILL.md",true,[],[72,98,111,121,136,145],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":81,"publishedAt":44},"01M6KSD3MCFGZXJ4Y5XJR44R3G","Sample Skill","A sample skill fixture exercising scripts\u002F, references\u002F, assets\u002F, and declared parameters\u002Fdependencies.","https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite\u002Fblob\u002Fmain\u002Finternal\u002Fskillinstall\u002Ftestdata\u002Ffixtures\u002Fsample-skill\u002FSKILL.md",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[82,83,84,40,85,86,87,88,89,90,91,92,93,94,95,96,97],"sample skill","sample","assets","notes","run","logo","references","dependencies","fixture","false","scripts","output","operate","true","inline","skill fixture",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":44},"01M6KSD1NGHT9NRZER493Z1YSV","Malformed Skill","A malformed skill fixture whose scripts entry does not exist on disk.","https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite\u002Fblob\u002Fmain\u002Finternal\u002Fskillinstall\u002Ftestdata\u002Ffixtures\u002Fmalformed-missing-script\u002FSKILL.md",[104],{"categoryNo":79,"categoryName":80,"taxonomyType":21,"taxonomyTypeDesc":22},[106,107,92,108,90,109,96,97,110],"malformed","malformed skill","missing","script","disk",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":44},"01M6KSCY7011R35WR86HZMMJCK","malformed-frontmatter","Missing the required name field.","https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite\u002Fblob\u002Fmain\u002Finternal\u002Fskillinstall\u002Ftestdata\u002Ffixtures\u002Fmalformed-frontmatter\u002FSKILL.md",[],[106,118,119,120,108,96],"frontmatter","malformed frontmatter","name",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":44},"01M6KSCSP652QRJPQR3E8EQ07W","Resolver Parent","A skill declaring both a required, resolver-bound parameter and a nested dependency on resolver-child.","https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite\u002Fblob\u002Fmain\u002Finternal\u002Fskill\u002Ftestdata\u002Ffixtures\u002Fresolver-parent\u002FSKILL.md",[],[128,123,129,130,131,91,132,93,133,134,95,135],"resolver","nested","dependency","greeting","binding","note","with","child",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":44},"01M6KSCNPVT56RAJNPYQN0W82Q","Resolver Child","A minimal nested skill, installed independently so the resolver dependency-address test can resolve a real dependency against it.","https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite\u002Fblob\u002Fmain\u002Finternal\u002Fskill\u002Ftestdata\u002Ffixtures\u002Fresolver-child\u002FSKILL.md",[],[138,135,128,40,130,143,129,144,29],"minimal","it",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":44},"01M6KSCHFCQ1HA3Y4XNA6AQGJW","Compose Multilevel Root","Root skill for a 3-level composition chain crossing both inline and fork.","https:\u002F\u002Fgithub.com\u002Fhollis-labs\u002Fnanite\u002Fblob\u002Fmain\u002Finternal\u002Fskill\u002Ftestdata\u002Ffixtures\u002Fcompose-multilevel-root\u002FSKILL.md",[],[147,152,153,154,155,156,96,157,158],"root","compose","Composition","chain","for","fork","root skill"]