[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-roo-code-agent-browser":3,"mdc-70hgcc-key":34,"related-repo-roo-code-agent-browser":379,"related-org-roo-code-agent-browser":477},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"roo-code","Roo Code","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Froo-code.png","RooCodeInc",[13,17,20],{"name":14,"slug":15,"type":16},"CLI","cli","tag",{"name":18,"slug":19,"type":16},"Testing","testing",{"name":21,"slug":22,"type":16},"Browser Automation","browser-automation",5,"https:\u002F\u002Fgithub.com\u002FRooCodeInc\u002FRoomote","2026-07-16T06:02:26.045337",null,0,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"Your own cloud coding agent. Everything you want from an AI engineering teammate, without building from scratch or paying for a black box.","https:\u002F\u002Fgithub.com\u002FRooCodeInc\u002FRoomote\u002Ftree\u002FHEAD\u002Fpackages\u002Fcloud-agents\u002Fsrc\u002Fserver\u002Fworkflows\u002Fskills\u002Fstandard\u002Fagent-browser","---\nname: agent-browser\ndescription: Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.\nallowed-tools: Bash(agent-browser:*), Bash(npx agent-browser:*)\nhidden: true\n---\n\n# agent-browser\n\nFast browser automation CLI for AI agents. Chrome\u002FChromium via CDP with\naccessibility-tree snapshots and compact `@eN` element refs.\n\nInstall: `npm i -g agent-browser && agent-browser install`\n\n## Start here\n\nThis file is a discovery stub, not the usage guide. Before running any\n`agent-browser` command, load the actual workflow content from the CLI:\n\n```bash\nagent-browser skills get core             # start here — workflows, common patterns, troubleshooting\nagent-browser skills get core --full      # include full command reference and templates\n```\n\nThe CLI serves skill content that always matches the installed version,\nso instructions never go stale. The content in this stub cannot change\nbetween releases, which is why it just points at `skills get core`.\n\n## Specialized skills\n\nLoad a specialized skill when the task falls outside browser web pages:\n\n```bash\nagent-browser skills get electron          # Electron desktop apps (VS Code, Slack, Figma, ...)\nagent-browser skills get slack             # Slack workspace automation\nagent-browser skills get dogfood           # Exploratory testing \u002F QA \u002F bug hunts\nagent-browser skills get agentcore         # AWS Bedrock AgentCore cloud browsers\n```\n\nRun `agent-browser skills list` to see everything available on the\ninstalled version.\n\n## Why agent-browser\n\n- Fast native Rust CLI, not a Node.js wrapper\n- Works with any AI agent (Cursor, Claude Code, Continue, Windsurf, etc.)\n- Chrome\u002FChromium via CDP with no Playwright or Puppeteer dependency\n- Accessibility-tree snapshots with element refs for reliable interaction\n- Sessions, authentication vault, state persistence, video recording\n- Specialized skills for Electron apps, Slack, exploratory testing, cloud providers\n\n## Observability Dashboard\n\nThe dashboard runs independently of browser sessions on port 4848 and can also\nbe opened through a proxied or forwarded URL such as\n`https:\u002F\u002Fdashboard.agent-browser.localhost`. Agents should stay on the\ndashboard origin: session tabs, status, and stream traffic are proxied\ninternally, so session ports do not need to be exposed.\n",{"data":35,"body":38},{"name":4,"description":6,"allowed-tools":36,"hidden":37},"Bash(agent-browser:*), Bash(npx agent-browser:*)",true,{"type":39,"children":40},"root",[41,48,63,74,81,93,167,180,186,191,300,313,319,354,360,373],{"type":42,"tag":43,"props":44,"children":45},"element","h1",{"id":4},[46],{"type":47,"value":4},"text",{"type":42,"tag":49,"props":50,"children":51},"p",{},[52,54,61],{"type":47,"value":53},"Fast browser automation CLI for AI agents. Chrome\u002FChromium via CDP with\naccessibility-tree snapshots and compact ",{"type":42,"tag":55,"props":56,"children":58},"code",{"className":57},[],[59],{"type":47,"value":60},"@eN",{"type":47,"value":62}," element refs.",{"type":42,"tag":49,"props":64,"children":65},{},[66,68],{"type":47,"value":67},"Install: ",{"type":42,"tag":55,"props":69,"children":71},{"className":70},[],[72],{"type":47,"value":73},"npm i -g agent-browser && agent-browser install",{"type":42,"tag":75,"props":76,"children":78},"h2",{"id":77},"start-here",[79],{"type":47,"value":80},"Start here",{"type":42,"tag":49,"props":82,"children":83},{},[84,86,91],{"type":47,"value":85},"This file is a discovery stub, not the usage guide. Before running any\n",{"type":42,"tag":55,"props":87,"children":89},{"className":88},[],[90],{"type":47,"value":4},{"type":47,"value":92}," command, load the actual workflow content from the CLI:",{"type":42,"tag":94,"props":95,"children":100},"pre",{"className":96,"code":97,"language":98,"meta":99,"style":99},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","agent-browser skills get core             # start here — workflows, common patterns, troubleshooting\nagent-browser skills get core --full      # include full command reference and templates\n","bash","",[101],{"type":42,"tag":55,"props":102,"children":103},{"__ignoreMap":99},[104,137],{"type":42,"tag":105,"props":106,"children":109},"span",{"class":107,"line":108},"line",1,[110,115,121,126,131],{"type":42,"tag":105,"props":111,"children":113},{"style":112},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[114],{"type":47,"value":4},{"type":42,"tag":105,"props":116,"children":118},{"style":117},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[119],{"type":47,"value":120}," skills",{"type":42,"tag":105,"props":122,"children":123},{"style":117},[124],{"type":47,"value":125}," get",{"type":42,"tag":105,"props":127,"children":128},{"style":117},[129],{"type":47,"value":130}," core",{"type":42,"tag":105,"props":132,"children":134},{"style":133},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[135],{"type":47,"value":136},"             # start here — workflows, common patterns, troubleshooting\n",{"type":42,"tag":105,"props":138,"children":140},{"class":107,"line":139},2,[141,145,149,153,157,162],{"type":42,"tag":105,"props":142,"children":143},{"style":112},[144],{"type":47,"value":4},{"type":42,"tag":105,"props":146,"children":147},{"style":117},[148],{"type":47,"value":120},{"type":42,"tag":105,"props":150,"children":151},{"style":117},[152],{"type":47,"value":125},{"type":42,"tag":105,"props":154,"children":155},{"style":117},[156],{"type":47,"value":130},{"type":42,"tag":105,"props":158,"children":159},{"style":117},[160],{"type":47,"value":161}," --full",{"type":42,"tag":105,"props":163,"children":164},{"style":133},[165],{"type":47,"value":166},"      # include full command reference and templates\n",{"type":42,"tag":49,"props":168,"children":169},{},[170,172,178],{"type":47,"value":171},"The CLI serves skill content that always matches the installed version,\nso instructions never go stale. The content in this stub cannot change\nbetween releases, which is why it just points at ",{"type":42,"tag":55,"props":173,"children":175},{"className":174},[],[176],{"type":47,"value":177},"skills get core",{"type":47,"value":179},".",{"type":42,"tag":75,"props":181,"children":183},{"id":182},"specialized-skills",[184],{"type":47,"value":185},"Specialized skills",{"type":42,"tag":49,"props":187,"children":188},{},[189],{"type":47,"value":190},"Load a specialized skill when the task falls outside browser web pages:",{"type":42,"tag":94,"props":192,"children":194},{"className":96,"code":193,"language":98,"meta":99,"style":99},"agent-browser skills get electron          # Electron desktop apps (VS Code, Slack, Figma, ...)\nagent-browser skills get slack             # Slack workspace automation\nagent-browser skills get dogfood           # Exploratory testing \u002F QA \u002F bug hunts\nagent-browser skills get agentcore         # AWS Bedrock AgentCore cloud browsers\n",[195],{"type":42,"tag":55,"props":196,"children":197},{"__ignoreMap":99},[198,223,248,274],{"type":42,"tag":105,"props":199,"children":200},{"class":107,"line":108},[201,205,209,213,218],{"type":42,"tag":105,"props":202,"children":203},{"style":112},[204],{"type":47,"value":4},{"type":42,"tag":105,"props":206,"children":207},{"style":117},[208],{"type":47,"value":120},{"type":42,"tag":105,"props":210,"children":211},{"style":117},[212],{"type":47,"value":125},{"type":42,"tag":105,"props":214,"children":215},{"style":117},[216],{"type":47,"value":217}," electron",{"type":42,"tag":105,"props":219,"children":220},{"style":133},[221],{"type":47,"value":222},"          # Electron desktop apps (VS Code, Slack, Figma, ...)\n",{"type":42,"tag":105,"props":224,"children":225},{"class":107,"line":139},[226,230,234,238,243],{"type":42,"tag":105,"props":227,"children":228},{"style":112},[229],{"type":47,"value":4},{"type":42,"tag":105,"props":231,"children":232},{"style":117},[233],{"type":47,"value":120},{"type":42,"tag":105,"props":235,"children":236},{"style":117},[237],{"type":47,"value":125},{"type":42,"tag":105,"props":239,"children":240},{"style":117},[241],{"type":47,"value":242}," slack",{"type":42,"tag":105,"props":244,"children":245},{"style":133},[246],{"type":47,"value":247},"             # Slack workspace automation\n",{"type":42,"tag":105,"props":249,"children":251},{"class":107,"line":250},3,[252,256,260,264,269],{"type":42,"tag":105,"props":253,"children":254},{"style":112},[255],{"type":47,"value":4},{"type":42,"tag":105,"props":257,"children":258},{"style":117},[259],{"type":47,"value":120},{"type":42,"tag":105,"props":261,"children":262},{"style":117},[263],{"type":47,"value":125},{"type":42,"tag":105,"props":265,"children":266},{"style":117},[267],{"type":47,"value":268}," dogfood",{"type":42,"tag":105,"props":270,"children":271},{"style":133},[272],{"type":47,"value":273},"           # Exploratory testing \u002F QA \u002F bug hunts\n",{"type":42,"tag":105,"props":275,"children":277},{"class":107,"line":276},4,[278,282,286,290,295],{"type":42,"tag":105,"props":279,"children":280},{"style":112},[281],{"type":47,"value":4},{"type":42,"tag":105,"props":283,"children":284},{"style":117},[285],{"type":47,"value":120},{"type":42,"tag":105,"props":287,"children":288},{"style":117},[289],{"type":47,"value":125},{"type":42,"tag":105,"props":291,"children":292},{"style":117},[293],{"type":47,"value":294}," agentcore",{"type":42,"tag":105,"props":296,"children":297},{"style":133},[298],{"type":47,"value":299},"         # AWS Bedrock AgentCore cloud browsers\n",{"type":42,"tag":49,"props":301,"children":302},{},[303,305,311],{"type":47,"value":304},"Run ",{"type":42,"tag":55,"props":306,"children":308},{"className":307},[],[309],{"type":47,"value":310},"agent-browser skills list",{"type":47,"value":312}," to see everything available on the\ninstalled version.",{"type":42,"tag":75,"props":314,"children":316},{"id":315},"why-agent-browser",[317],{"type":47,"value":318},"Why agent-browser",{"type":42,"tag":320,"props":321,"children":322},"ul",{},[323,329,334,339,344,349],{"type":42,"tag":324,"props":325,"children":326},"li",{},[327],{"type":47,"value":328},"Fast native Rust CLI, not a Node.js wrapper",{"type":42,"tag":324,"props":330,"children":331},{},[332],{"type":47,"value":333},"Works with any AI agent (Cursor, Claude Code, Continue, Windsurf, etc.)",{"type":42,"tag":324,"props":335,"children":336},{},[337],{"type":47,"value":338},"Chrome\u002FChromium via CDP with no Playwright or Puppeteer dependency",{"type":42,"tag":324,"props":340,"children":341},{},[342],{"type":47,"value":343},"Accessibility-tree snapshots with element refs for reliable interaction",{"type":42,"tag":324,"props":345,"children":346},{},[347],{"type":47,"value":348},"Sessions, authentication vault, state persistence, video recording",{"type":42,"tag":324,"props":350,"children":351},{},[352],{"type":47,"value":353},"Specialized skills for Electron apps, Slack, exploratory testing, cloud providers",{"type":42,"tag":75,"props":355,"children":357},{"id":356},"observability-dashboard",[358],{"type":47,"value":359},"Observability Dashboard",{"type":42,"tag":49,"props":361,"children":362},{},[363,365,371],{"type":47,"value":364},"The dashboard runs independently of browser sessions on port 4848 and can also\nbe opened through a proxied or forwarded URL such as\n",{"type":42,"tag":55,"props":366,"children":368},{"className":367},[],[369],{"type":47,"value":370},"https:\u002F\u002Fdashboard.agent-browser.localhost",{"type":47,"value":372},". Agents should stay on the\ndashboard origin: session tabs, status, and stream traffic are proxied\ninternally, so session ports do not need to be exposed.",{"type":42,"tag":374,"props":375,"children":376},"style",{},[377],{"type":47,"value":378},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":380,"total":476},[381,397,403,417,433,447,466],{"slug":382,"name":382,"fn":383,"description":384,"org":385,"tags":386,"stars":23,"repoUrl":24,"updatedAt":396},"address-pr-feedback","address unresolved GitHub PR feedback","Focused GitHub PR-feedback workflow for addressing unresolved review threads on the current pull request.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[387,390,393],{"name":388,"slug":389,"type":16},"Code Review","code-review",{"name":391,"slug":392,"type":16},"GitHub","github",{"name":394,"slug":395,"type":16},"Pull Requests","pull-requests","2026-07-19T05:38:26.334008",{"slug":4,"name":4,"fn":5,"description":6,"org":398,"tags":399,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[400,401,402],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"slug":404,"name":404,"fn":405,"description":406,"org":407,"tags":408,"stars":23,"repoUrl":24,"updatedAt":416},"capture-visual-proof","capture visual proof of browser tasks","Visual-proof orchestrator that decides whether browser proof applies, classifies the proof package, and delegates capture to the hidden proof-runner subagent.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[409,412,413],{"name":410,"slug":411,"type":16},"Automation","automation",{"name":21,"slug":22,"type":16},{"name":414,"slug":415,"type":16},"Screenshots","screenshots","2026-08-01T05:44:47.369293",{"slug":418,"name":418,"fn":419,"description":420,"org":421,"tags":422,"stars":23,"repoUrl":24,"updatedAt":432},"ci-failure-triage","triage failed CI workflows","Investigate the latest default-branch CI failure in an environment-backed workspace and, when it is real and fixable, fix and open a PR in the same task.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[423,426,429],{"name":424,"slug":425,"type":16},"CI\u002FCD","ci-cd",{"name":427,"slug":428,"type":16},"Debugging","debugging",{"name":430,"slug":431,"type":16},"GitHub Actions","github-actions","2026-07-23T05:40:41.726992",{"slug":434,"name":434,"fn":435,"description":436,"org":437,"tags":438,"stars":23,"repoUrl":24,"updatedAt":446},"code-quality-auditor","audit code quality in merged pull requests","Automation skill: review recently merged pull requests for high-confidence code quality issues and submit `act` work items that auto-start follow-up execution tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[439,442,443],{"name":440,"slug":441,"type":16},"Code Analysis","code-analysis",{"name":388,"slug":389,"type":16},{"name":444,"slug":445,"type":16},"QA","qa","2026-07-26T05:47:47.339721",{"slug":448,"name":448,"fn":449,"description":450,"org":451,"tags":452,"stars":23,"repoUrl":24,"updatedAt":465},"codeql-triage","triage and remediate CodeQL security alerts","Review current open CodeQL \u002F GitHub code-scanning alerts with GitHub data, keep scheduled runs read-only, and submit a small set of environment-backed `act` work items that auto-start remediation execution tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[453,454,457,458,459,462],{"name":440,"slug":441,"type":16},{"name":455,"slug":456,"type":16},"CodeQL","codeql",{"name":427,"slug":428,"type":16},{"name":391,"slug":392,"type":16},{"name":460,"slug":461,"type":16},"Security","security",{"name":463,"slug":464,"type":16},"Triage","triage","2026-07-29T05:39:37.784486",{"slug":467,"name":467,"fn":468,"description":469,"org":470,"tags":471,"stars":23,"repoUrl":24,"updatedAt":475},"create-draft-pr","create draft pull requests","Draft pull-request creation workflow. Use when repositories have pending changes or unpushed commits and you want draft PRs created.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[472,473,474],{"name":410,"slug":411,"type":16},{"name":391,"slug":392,"type":16},{"name":394,"slug":395,"type":16},"2026-07-16T06:00:31.733527",33,{"items":478,"total":476},[479,485,491,497,503,509,518,524,533,545,556,569],{"slug":382,"name":382,"fn":383,"description":384,"org":480,"tags":481,"stars":23,"repoUrl":24,"updatedAt":396},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[482,483,484],{"name":388,"slug":389,"type":16},{"name":391,"slug":392,"type":16},{"name":394,"slug":395,"type":16},{"slug":4,"name":4,"fn":5,"description":6,"org":486,"tags":487,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[488,489,490],{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"name":18,"slug":19,"type":16},{"slug":404,"name":404,"fn":405,"description":406,"org":492,"tags":493,"stars":23,"repoUrl":24,"updatedAt":416},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[494,495,496],{"name":410,"slug":411,"type":16},{"name":21,"slug":22,"type":16},{"name":414,"slug":415,"type":16},{"slug":418,"name":418,"fn":419,"description":420,"org":498,"tags":499,"stars":23,"repoUrl":24,"updatedAt":432},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[500,501,502],{"name":424,"slug":425,"type":16},{"name":427,"slug":428,"type":16},{"name":430,"slug":431,"type":16},{"slug":434,"name":434,"fn":435,"description":436,"org":504,"tags":505,"stars":23,"repoUrl":24,"updatedAt":446},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[506,507,508],{"name":440,"slug":441,"type":16},{"name":388,"slug":389,"type":16},{"name":444,"slug":445,"type":16},{"slug":448,"name":448,"fn":449,"description":450,"org":510,"tags":511,"stars":23,"repoUrl":24,"updatedAt":465},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[512,513,514,515,516,517],{"name":440,"slug":441,"type":16},{"name":455,"slug":456,"type":16},{"name":427,"slug":428,"type":16},{"name":391,"slug":392,"type":16},{"name":460,"slug":461,"type":16},{"name":463,"slug":464,"type":16},{"slug":467,"name":467,"fn":468,"description":469,"org":519,"tags":520,"stars":23,"repoUrl":24,"updatedAt":475},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[521,522,523],{"name":410,"slug":411,"type":16},{"name":391,"slug":392,"type":16},{"name":394,"slug":395,"type":16},{"slug":525,"name":525,"fn":526,"description":527,"org":528,"tags":529,"stars":23,"repoUrl":24,"updatedAt":532},"create-pr","create pull requests for pending changes","Pull-request creation workflow. Use when repositories have pending changes or unpushed commits and you want ready-for-review PRs created.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[530,531],{"name":391,"slug":392,"type":16},{"name":394,"slug":395,"type":16},"2026-07-16T06:03:03.397562",{"slug":534,"name":534,"fn":535,"description":536,"org":537,"tags":538,"stars":23,"repoUrl":24,"updatedAt":544},"debug-reported-bug","reproduce and debug reported bugs","Reproduce-first bug diagnosis workflow. Use when a reported bug needs to be reproduced, reduced to a deterministic failing check, and traced through git history or `git bisect` so the exact cause is understood before any fix is attempted.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[539,540,543],{"name":427,"slug":428,"type":16},{"name":541,"slug":542,"type":16},"Git","git",{"name":18,"slug":19,"type":16},"2026-07-16T06:03:07.255013",{"slug":546,"name":546,"fn":547,"description":548,"org":549,"tags":550,"stars":23,"repoUrl":24,"updatedAt":555},"dependabot-triage","triage GitHub Dependabot alerts","Review current open Dependabot alerts with GitHub data, keep scheduled runs read-only, and submit a small set of environment-backed `act` work items that auto-start dependency-update execution tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[551,552,553,554],{"name":410,"slug":411,"type":16},{"name":391,"slug":392,"type":16},{"name":460,"slug":461,"type":16},{"name":463,"slug":464,"type":16},"2026-07-29T05:39:38.757423",{"slug":557,"name":557,"fn":558,"description":559,"org":560,"tags":561,"stars":23,"repoUrl":24,"updatedAt":568},"environment-setup","configure local development environments","Internal skill to configure environments. Never use unless the user explicitly initiates the skill. Focus on localhost-ready setup and validation.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[562,565],{"name":563,"slug":564,"type":16},"Configuration","configuration",{"name":566,"slug":567,"type":16},"Local Development","local-development","2026-08-01T05:44:46.333988",{"slug":570,"name":570,"fn":571,"description":572,"org":573,"tags":574,"stars":23,"repoUrl":24,"updatedAt":579},"explain-repo-code","explain repository code and architecture","Explanation-only repository workflow. Use when the user asks to understand behavior, architecture, or rationale from source context without modifying files.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[575,576],{"name":440,"slug":441,"type":16},{"name":577,"slug":578,"type":16},"Documentation","documentation","2026-07-16T06:00:34.090082"]