[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77J2284WNKB18VTRTWSSDKW":3,"skill-same:01M77J2284WNKB18VTRTWSSDKW":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M77J2284WNKB18VTRTWSSDKW","run",null,"Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).","raaOS\u002Fsystem_prompts_leaks","raaOS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F214067397?v=4","01M77HV6K4ZTA4BZAGX00GTW6J","01M77HV6KX55HVRY679V25JXF8",0,"CC0-1.0","https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Frun\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: run\ndescription: Launch and drive this project's app to see a change working. Use when asked to run, start, or screenshot the app, or to confirm a change works in the real app (not just tests). First looks for a project skill that already covers launching the app; otherwise falls back to built-in patterns per project type (CLI, server, TUI, Electron, browser-driven, library).\n---\n\n**Running means launching the actual app and interacting with it** -\nnot the test suite, not an `import` of an internal function and a\n`console.log`. The app as a user (human or programmatic) would meet\nit: the CLI at its command, the server at its socket, the GUI at its\nwindow.\n\n## First: does a project skill already cover this?\n\nA project skill that launches this app is the repo's verified path -\nits author already cold-started from a Linux container and committed\nwhat worked: the exact `apt-get` line, the env vars, the patches, the\ndriver. Use it instead of rediscovering.\n\n```bash\nd=$PWD; while :; do\n  grep -Hm1 '^description:' \"$d\"\u002F.claude\u002Fskills\u002F*\u002FSKILL.md 2>\u002Fdev\u002Fnull\n  [ -e \"$d\u002F.git\" ] || [ \"$d\" = \u002F ] && break\n  d=$(dirname \"$d\")\ndone\n```\n\n- **One describes launching\u002Fdriving this app** -> read that SKILL.md\n  and follow it verbatim. Don't paraphrase; don't skip the patches.\n- **Mega-repo, several plausible, no clear match** -> ask the user\n  which unit to run.\n- **Stale** (fails on mechanics unrelated to your task) -> tell the\n  user; offer to refresh it via `\u002Frun-skill-generator`.\n- **Nothing about running** -> fall back to the patterns below.\n\n## Otherwise: match the shape, use the pattern\n\nPick the row closest to your project. Each example walks through\nlaunch + first interaction; ignore any trailing \"write the skill\"\nsection - you're using the recipe, not authoring one.\n\n| Project type | Handle | Example |\n|---|---|---|\n| CLI tool | direct invocation, exit code, stdin\u002Fstdout | [examples\u002Fcli.md](examples\u002Fcli.md) |\n| Web server \u002F API | background launch + `curl` smoke | [examples\u002Fserver.md](examples\u002Fserver.md) |\n| TUI \u002F interactive terminal | tmux `send-keys` \u002F `capture-pane` | [examples\u002Ftui.md](examples\u002Ftui.md) |\n| Electron \u002F desktop GUI | Playwright `_electron` REPL under xvfb | [examples\u002Felectron.md](examples\u002Felectron.md) |\n| Browser-driven | dev server + `chromium-cli` script | [examples\u002Fplaywright.md](examples\u002Fplaywright.md) |\n| Library \u002F SDK | import-and-call smoke script at the package boundary | [examples\u002Flibrary.md](examples\u002Flibrary.md) |\n\nIf nothing fits, start from the closest match and adapt. For a web\napp, [examples\u002Fplaywright.md](examples\u002Fplaywright.md) - drive it with\n`chromium-cli`, no custom driver needed. For a desktop app,\n[examples\u002Felectron.md](examples\u002Felectron.md) - it has the `_electron`\nREPL driver skeleton and the tmux wrapping.\n\n## Drive it, don't just launch it\n\nLaunching with no interaction proves the entrypoint resolves. That's\nnot running the app - it's typechecking with extra steps. Drive it to\na point where a user would see something:\n\n- CLI -> type a representative command, check the exit code and output.\n- Server -> hit the route the diff touches with `curl`, read the body.\n- TUI -> `send-keys` a navigation, `capture-pane` the result.\n- GUI -> click the button, screenshot the window. **Look at the\n  screenshot.** A blank frame is a failure to launch.\n\nIf the fallback pattern didn't work out of the box - you had to\ninstall packages, set env vars, patch config, or write a driver -\nrecommend `\u002Frun-skill-generator` in your report so that work gets\ncaptured as a project skill. If it just worked, don't.\n","**Running means launching the actual app and interacting with it** -\nnot the test suite, not an `import` of an internal function and a\n`console.log`. The app as a user (human or programmatic) would meet\nit: the CLI at its command, the server at its socket, the GUI at its\nwindow.\n\n## First: does a project skill already cover this?\n\nA project skill that launches this app is the repo's verified path -\nits author already cold-started from a Linux container and committed\nwhat worked: the exact `apt-get` line, the env vars, the patches, the\ndriver. Use it instead of rediscovering.\n\n```bash\nd=$PWD; while :; do\n  grep -Hm1 '^description:' \"$d\"\u002F.claude\u002Fskills\u002F*\u002FSKILL.md 2>\u002Fdev\u002Fnull\n  [ -e \"$d\u002F.git\" ] || [ \"$d\" = \u002F ] && break\n  d=$(dirname \"$d\")\ndone\n```\n\n- **One describes launching\u002Fdriving this app** -> read that SKILL.md\n  and follow it verbatim. Don't paraphrase; don't skip the patches.\n- **Mega-repo, several plausible, no clear match** -> ask the user\n  which unit to run.\n- **Stale** (fails on mechanics unrelated to your task) -> tell the\n  user; offer to refresh it via `\u002Frun-skill-generator`.\n- **Nothing about running** -> fall back to the patterns below.\n\n## Otherwise: match the shape, use the pattern\n\nPick the row closest to your project. Each example walks through\nlaunch + first interaction; ignore any trailing \"write the skill\"\nsection - you're using the recipe, not authoring one.\n\n| Project type | Handle | Example |\n|---|---|---|\n| CLI tool | direct invocation, exit code, stdin\u002Fstdout | [examples\u002Fcli.md](examples\u002Fcli.md) |\n| Web server \u002F API | background launch + `curl` smoke | [examples\u002Fserver.md](examples\u002Fserver.md) |\n| TUI \u002F interactive terminal | tmux `send-keys` \u002F `capture-pane` | [examples\u002Ftui.md](examples\u002Ftui.md) |\n| Electron \u002F desktop GUI | Playwright `_electron` REPL under xvfb | [examples\u002Felectron.md](examples\u002Felectron.md) |\n| Browser-driven | dev server + `chromium-cli` script | [examples\u002Fplaywright.md](examples\u002Fplaywright.md) |\n| Library \u002F SDK | import-and-call smoke script at the package boundary | [examples\u002Flibrary.md](examples\u002Flibrary.md) |\n\nIf nothing fits, start from the closest match and adapt. For a web\napp, [examples\u002Fplaywright.md](examples\u002Fplaywright.md) - drive it with\n`chromium-cli`, no custom driver needed. For a desktop app,\n[examples\u002Felectron.md](examples\u002Felectron.md) - it has the `_electron`\nREPL driver skeleton and the tmux wrapping.\n\n## Drive it, don't just launch it\n\nLaunching with no interaction proves the entrypoint resolves. That's\nnot running the app - it's typechecking with extra steps. Drive it to\na point where a user would see something:\n\n- CLI -> type a representative command, check the exit code and output.\n- Server -> hit the route the diff touches with `curl`, read the body.\n- TUI -> `send-keys` a navigation, `capture-pane` the result.\n- GUI -> click the button, screenshot the window. **Look at the\n  screenshot.** A blank frame is a failure to launch.\n\nIf the fallback pattern didn't work out of the box - you had to\ninstall packages, set env vars, patch config, or write a driver -\nrecommend `\u002Frun-skill-generator` in your report so that work gets\ncaptured as a project skill. If it just worked, don't.\n",{"name":5,"description":7},"main","2975a5ac469614541ae22929d43b6da2635e1ee9","Anthropic\u002Fclaude-code\u002Fskills\u002Frun","https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks","https:\u002F\u002Fgithub.com\u002FraaOS","2026-11-14 21:19:17",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add raaOS\u002Fsystem_prompts_leaks --skill run",{"tool":35,"command":36},"bunx","bunx skills add raaOS\u002Fsystem_prompts_leaks --skill run",{"tool":38,"command":39},"pnpm","pnpm dlx skills add raaOS\u002Fsystem_prompts_leaks --skill run","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Frun\u002FSKILL.md",true,[43,49,53,57,61,65],{"path":44,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":47,"sourceHtmlUrl":48},"examples\u002Fcli.md","REFERENCE","参考文档",1542,"https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Frun\u002Fexamples\u002Fcli.md",{"path":50,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":51,"sourceHtmlUrl":52},"examples\u002Felectron.md",14357,"https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Frun\u002Fexamples\u002Felectron.md",{"path":54,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":55,"sourceHtmlUrl":56},"examples\u002Flibrary.md",2032,"https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Frun\u002Fexamples\u002Flibrary.md",{"path":58,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":59,"sourceHtmlUrl":60},"examples\u002Fplaywright.md",3534,"https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Frun\u002Fexamples\u002Fplaywright.md",{"path":62,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":63,"sourceHtmlUrl":64},"examples\u002Fserver.md",3316,"https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Frun\u002Fexamples\u002Fserver.md",{"path":66,"resourceType":45,"resourceTypeDesc":46,"sizeBytes":67,"sourceHtmlUrl":68},"examples\u002Ftui.md",3021,"https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Frun\u002Fexamples\u002Ftui.md",[70,76,83,90,97,104],{"skillNo":71,"name":72,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M77JV1M0ZZTZZREM9Q96TKZZ","model-council","https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FPerplexity\u002Fskills\u002Fmodel-council\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M77JTYND3ETS9EGCX3B9CW6E","writing-style","Draft or edit writing in the user's voice for the person who will read it and where it will appear. Use for messages, emails, documents or slides written on their behalf, not for your own replies.","https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FOpenAI\u002Fdots\u002Fskills\u002Fwriting-style\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M77JTVWEHY80JC2H1JG1JMQB","write-page","Create or edit requested Page\u002FSpace content, or use for prose you have already decided to save as a standalone Markdown file, only if the user did not explicitly request a Markdown file. Honor established formats, destinations, and repository documentation. A selected Page alone does not authorize a write.","https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FOpenAI\u002Fdots\u002Fskills\u002Fwrite-page\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M77JTQ5ND23QPF6RJYJPXHSZ","software-engineering","For use only in threads for this proactive personal assistant. Investigate software issues; inspect, write, review, or test code; work on a repository or local engineering file; or create, fix, or monitor a pull request or CI run. Use for actual engineering or product QA work, not a general programming explanation.","https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FOpenAI\u002Fdots\u002Fskills\u002Fsoftware-engineering\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M77JTM3ZDPCYE8C1FW7G7S2B","slides-artifact","Use when the user asks to create, edit, or review slides or a presentation (PowerPoint or Google Slides), including when the task clearly calls for an audience-ready slide deck. Also use to answer questions that require inspecting an existing deck; not for general presentation advice or a chat-only outline.","https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FOpenAI\u002Fdots\u002Fskills\u002Fslides-artifact\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":18},"01M77JTHTWZN2J27KD2H66XDBZ","slack","Use when reading Slack conversations, deciding when to respond, or sending messages, files, and reactions in Slack.","https:\u002F\u002Fgithub.com\u002FraaOS\u002Fsystem_prompts_leaks\u002Fblob\u002Fmain\u002FOpenAI\u002Fdots\u002Fskills\u002Fslack\u002FSKILL.md",[],[]]