[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71AYH5H6JQVZCGG2RQ0CQ0W":3,"skill-same:01M71AYH5H6JQVZCGG2RQ0CQ0W":76},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M71AYH5H6JQVZCGG2RQ0CQ0W","superskills-doctor",null,"Diagnose a superskills install WITHOUT changing anything: install kind, which\nskills are linked, VERSION vs the plugin manifests, gstack (real clone or\nvendor stopgap), bun and optional tools. Use when a skill is missing or won't\ntrigger, a pull or upgrade looks stale, setup failed, or the user asks whether\nsuperskills is healthy, ready, or installed correctly. Read-only: it never\ninstalls, pulls, or re-runs setup — to fix things use \u002Fsuperskills-upgrade.","ariadoss\u002Fsuperskills","ariadoss","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F414341?v=4","01M71AC7383PT6JCRZSQJ4AVTM","Danilo Stern-Sapad","01M71AC73Y7NTBTJ9KQYNENRRE",12,"MIT","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"doctor","superskills doctor","trigger","diagnose","when","things","manifests","which","read-only","re","missing","pull","upgrade","ready","only","never","version","use","fix","Bash","2026-11-10 10:12:30",false,"---\nname: superskills-doctor\nversion: 1.1.0\ndescription: |\n  Diagnose a superskills install WITHOUT changing anything: install kind, which\n  skills are linked, VERSION vs the plugin manifests, gstack (real clone or\n  vendor stopgap), bun and optional tools. Use when a skill is missing or won't\n  trigger, a pull or upgrade looks stale, setup failed, or the user asks whether\n  superskills is healthy, ready, or installed correctly. Read-only: it never\n  installs, pulls, or re-runs setup — to fix things use \u002Fsuperskills-upgrade.\ntriggers:\n  - is superskills healthy\n  - check my superskills install\n  - superskills doctor\n  - skill missing after pull\nallowed-tools:\n  - Bash\n  - Read\n---\n\n# \u002Fsuperskills-doctor\n\nRead-only health check. Report what is, never repair it.\n\n## Rules\n\n1. **Never mutate.** Do not run `.\u002Fsetup`, `git pull`, `git reset`, `curl … | bash`,\n   `bun install`, or any login. If the user wants the fix, name the command from\n   the table's \"next action\" column or point at `\u002Fsuperskills-upgrade`.\n2. **Never claim readiness the script did not.** The verdict is the script's\n   verdict. \"blocked\" or \"unverified\" means not ready, even if most rows are fine.\n3. **Report evidence, not impressions.** Reproduce the table; do not summarise\n   rows away or add checks you did not run.\n\n## Steps\n\n### Step 1: Locate and run the doctor (one command)\n\nThe script lives in the superskills repo at `scripts\u002Fdoctor.sh`. Find the repo, in\norder: the directory this skill was loaded from (if your host told you this skill's\nbase directory, put it in `SKILL_DIR` on the first line), the Claude Code plugin\nroot, then this skill's `.\u002Fsetup` symlink for Claude Code, Codex or OpenCode —\nnever the working directory. Locate and run it **in a single Bash call**: separate\ncalls do not share shell variables, so a path found in one call is gone in the next.\n\n```bash\nSKILL_DIR=\"${SKILL_DIR:-}\"   # set to this skill's base directory when the host provides it\ncase \"$SKILL_DIR\" in \u002F*) : ;; *) SKILL_DIR=\"\" ;; esac   # only an absolute path is trusted, never resolved against the cwd\nROOT=\"\"\nfor cand in \"${SKILL_DIR:+$SKILL_DIR\u002F..\u002F..}\" \"${CLAUDE_PLUGIN_ROOT}\"; do\n  [ -n \"$cand\" ] && [ -f \"$cand\u002Fscripts\u002Fdoctor.sh\" ] && { ROOT=\"$(cd \"$cand\" && pwd -P)\"; break; }\ndone\nif [ -z \"$ROOT\" ]; then\n  for probe in \"$HOME\u002F.claude\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md\" \\\n               \"$HOME\u002F.codex\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md\" \\\n               \"$HOME\u002F.config\u002Fopencode\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md\" \\\n               \"$HOME\u002F.zcode\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md\"; do\n    # Only a link that resolves to a real file counts; never fall back to the cwd.\n    [ -L \"$probe\" ] || continue\n    real=\"$(readlink -f \"$probe\" 2>\u002Fdev\u002Fnull || perl -MCwd=realpath -e 'print realpath($ARGV[0])' \"$probe\")\"\n    if [ -n \"$real\" ] && [ -f \"$real\" ]; then\n      ROOT=\"$(cd \"$(dirname \"$real\")\u002F..\u002F..\" 2>\u002Fdev\u002Fnull && pwd -P)\"\n      [ -f \"$ROOT\u002Fscripts\u002Fdoctor.sh\" ] && break\n      ROOT=\"\"\n    fi\n  done\nfi\nif [ -n \"$ROOT\" ] && [ -f \"$ROOT\u002Fscripts\u002Fdoctor.sh\" ]; then\n  echo \"DOCTOR=$ROOT\u002Fscripts\u002Fdoctor.sh\"\n  bash \"$ROOT\u002Fscripts\u002Fdoctor.sh\" \"$@\"\nelse\n  echo \"DOCTOR=missing\"\nfi\n```\n\nIf it prints `DOCTOR=missing`, that is itself the finding: report **Repo: blocked**\nwith the reinstall command below and stop. Do not improvise checks.\n\n```\ngit clone https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills.git ~\u002F.claude\u002Fskills\u002Fsuperskills && cd ~\u002F.claude\u002Fskills\u002Fsuperskills && .\u002Fsetup\n```\n\nTo inspect an install that is not the current user's (a container, a test tree,\na colleague's copy), run the same block with the flags appended to the\n`bash \"$ROOT\u002Fscripts\u002Fdoctor.sh\"` line: `--root \u003Csuperskills-checkout> --home \u003Chome-dir>`.\nTo call the script directly later, use the path from the `DOCTOR=` line.\n\n### Step 2: Read the output\n\nThe script prints a markdown table (`Check | Status | Evidence \u002F next action`)\nand a final `Verdict:` line. Statuses:\n\n| Status | Meaning |\n| --- | --- |\n| ready | passed |\n| warning | usable; something optional is off |\n| blocked | a required piece is missing or broken — the row says what to run |\n| unverified | the probe could not run (e.g. no `claude` CLI) — unknown, not fine |\n\n### Step 3: Report\n\nReturn the table verbatim, then the verdict, then one line per non-ready row\nnaming the next action from that row. Say plainly:\n\n- **Verdict: ready** → \"superskills is ready.\"\n- **ready with warnings** → ready, and list the warnings.\n- **blocked** → \"Not ready\" and the blocked rows first. The usual fix is\n  `.\u002Fsetup` from the repo, or `\u002Fsuperskills-upgrade`; offer it, do not run it.\n- **unverified** → say readiness is unknown and which probe could not run.\n","# \u002Fsuperskills-doctor\n\nRead-only health check. Report what is, never repair it.\n\n## Rules\n\n1. **Never mutate.** Do not run `.\u002Fsetup`, `git pull`, `git reset`, `curl … | bash`,\n   `bun install`, or any login. If the user wants the fix, name the command from\n   the table's \"next action\" column or point at `\u002Fsuperskills-upgrade`.\n2. **Never claim readiness the script did not.** The verdict is the script's\n   verdict. \"blocked\" or \"unverified\" means not ready, even if most rows are fine.\n3. **Report evidence, not impressions.** Reproduce the table; do not summarise\n   rows away or add checks you did not run.\n\n## Steps\n\n### Step 1: Locate and run the doctor (one command)\n\nThe script lives in the superskills repo at `scripts\u002Fdoctor.sh`. Find the repo, in\norder: the directory this skill was loaded from (if your host told you this skill's\nbase directory, put it in `SKILL_DIR` on the first line), the Claude Code plugin\nroot, then this skill's `.\u002Fsetup` symlink for Claude Code, Codex or OpenCode —\nnever the working directory. Locate and run it **in a single Bash call**: separate\ncalls do not share shell variables, so a path found in one call is gone in the next.\n\n```bash\nSKILL_DIR=\"${SKILL_DIR:-}\"   # set to this skill's base directory when the host provides it\ncase \"$SKILL_DIR\" in \u002F*) : ;; *) SKILL_DIR=\"\" ;; esac   # only an absolute path is trusted, never resolved against the cwd\nROOT=\"\"\nfor cand in \"${SKILL_DIR:+$SKILL_DIR\u002F..\u002F..}\" \"${CLAUDE_PLUGIN_ROOT}\"; do\n  [ -n \"$cand\" ] && [ -f \"$cand\u002Fscripts\u002Fdoctor.sh\" ] && { ROOT=\"$(cd \"$cand\" && pwd -P)\"; break; }\ndone\nif [ -z \"$ROOT\" ]; then\n  for probe in \"$HOME\u002F.claude\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md\" \\\n               \"$HOME\u002F.codex\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md\" \\\n               \"$HOME\u002F.config\u002Fopencode\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md\" \\\n               \"$HOME\u002F.zcode\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md\"; do\n    # Only a link that resolves to a real file counts; never fall back to the cwd.\n    [ -L \"$probe\" ] || continue\n    real=\"$(readlink -f \"$probe\" 2>\u002Fdev\u002Fnull || perl -MCwd=realpath -e 'print realpath($ARGV[0])' \"$probe\")\"\n    if [ -n \"$real\" ] && [ -f \"$real\" ]; then\n      ROOT=\"$(cd \"$(dirname \"$real\")\u002F..\u002F..\" 2>\u002Fdev\u002Fnull && pwd -P)\"\n      [ -f \"$ROOT\u002Fscripts\u002Fdoctor.sh\" ] && break\n      ROOT=\"\"\n    fi\n  done\nfi\nif [ -n \"$ROOT\" ] && [ -f \"$ROOT\u002Fscripts\u002Fdoctor.sh\" ]; then\n  echo \"DOCTOR=$ROOT\u002Fscripts\u002Fdoctor.sh\"\n  bash \"$ROOT\u002Fscripts\u002Fdoctor.sh\" \"$@\"\nelse\n  echo \"DOCTOR=missing\"\nfi\n```\n\nIf it prints `DOCTOR=missing`, that is itself the finding: report **Repo: blocked**\nwith the reinstall command below and stop. Do not improvise checks.\n\n```\ngit clone https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills.git ~\u002F.claude\u002Fskills\u002Fsuperskills && cd ~\u002F.claude\u002Fskills\u002Fsuperskills && .\u002Fsetup\n```\n\nTo inspect an install that is not the current user's (a container, a test tree,\na colleague's copy), run the same block with the flags appended to the\n`bash \"$ROOT\u002Fscripts\u002Fdoctor.sh\"` line: `--root \u003Csuperskills-checkout> --home \u003Chome-dir>`.\nTo call the script directly later, use the path from the `DOCTOR=` line.\n\n### Step 2: Read the output\n\nThe script prints a markdown table (`Check | Status | Evidence \u002F next action`)\nand a final `Verdict:` line. Statuses:\n\n| Status | Meaning |\n| --- | --- |\n| ready | passed |\n| warning | usable; something optional is off |\n| blocked | a required piece is missing or broken — the row says what to run |\n| unverified | the probe could not run (e.g. no `claude` CLI) — unknown, not fine |\n\n### Step 3: Report\n\nReturn the table verbatim, then the verdict, then one line per non-ready row\nnaming the next action from that row. Say plainly:\n\n- **Verdict: ready** → \"superskills is ready.\"\n- **ready with warnings** → ready, and list the warnings.\n- **blocked** → \"Not ready\" and the blocked rows first. The usual fix is\n  `.\u002Fsetup` from the repo, or `\u002Fsuperskills-upgrade`; offer it, do not run it.\n- **unverified** → say readiness is unknown and which probe could not run.\n",{"name":5,"version":44,"triggers":45,"description":49,"allowed-tools":50},"1.1.0",[46,47,20,48],"is superskills healthy","check my superskills install","skill missing after pull","Diagnose a superskills install WITHOUT changing anything: install kind, which\nskills are linked, VERSION vs the plugin manifests, gstack (real clone or\nvendor stopgap), bun and optional tools. Use when a skill is missing or won't\ntrigger, a pull or upgrade looks stale, setup failed, or the user asks whether\nsuperskills is healthy, ready, or installed correctly. Read-only: it never\ninstalls, pulls, or re-runs setup — to fix things use \u002Fsuperskills-upgrade.\n",[38,51],"Read","main","c7ec8d78e5dc37484c2cfe90ab04de163d97dd41","skills\u002Fsuperskills-doctor",0,"https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills","https:\u002F\u002Fhyperion360.com\u002Fblog\u002Fparallel-ai-agents-engineering-workflow\u002F","https:\u002F\u002Fgithub.com\u002Fariadoss","https:\u002F\u002Fdanilosapad.com\u002F","CEO & Founder of @Hyperion360","2026-11-13 15:29:19",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add ariadoss\u002Fsuperskills --skill superskills-doctor",{"tool":68,"command":69},"bunx","bunx skills add ariadoss\u002Fsuperskills --skill superskills-doctor",{"tool":71,"command":72},"pnpm","pnpm dlx skills add ariadoss\u002Fsuperskills --skill superskills-doctor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fsuperskills-doctor\u002FSKILL.md",true,[],[77,103,128,147,174,190],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":88,"publishedAt":39},"01M71AZE3MPF891RM354EMRYA1","youtube","Download YouTube video transcripts when user provides a YouTube URL or asks to download\u002Fget\u002Ffetch a transcript from YouTube. Also use when user wants to transcribe or get captions\u002Fsubtitles from a YouTube video.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[83],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[79,89,90,91,92,93,94,38,95,23,96,97,98,99,100,36,101,102],"user","download","transcribe","write","transcript","video transcripts","URL","Captions","get","fetch","Video","read","subtitles","transcripts",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":39},"01M71AZAYR85PW6BJGSQXS4BN2","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code. Produces an engineering plan complete with TDD tasks, DRY\u002FSOLID\u002FYAGNI principles, a required Test Plan & Verification section, and a coverage target — then auto-runs \u002Fplan-eng-review as an independent double-check before execution.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[110,111,92,112,113,114,115,116,117,23,118,119,120,121,122,123,124,125,126,127],"write plan","plan","dry","verification","review","tasks","code","you","auto","eng","coverage","complete","section","for","test plan","target","as","yagni",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":39},"01M71AZ8NDDP5ZMGEE6FSC4FKR","worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fworktrees\u002FSKILL.md",[],[130,135,136,137,36,138,139,140,141,142,143,113,144,23,145,146],"implementation","workspace","with","plans","feature","isolation","git","directory","work","git worktrees","selection","Safety",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":156,"publishedAt":39},"01M71AZ4ZQHTNWFRZVYHKQFP08","web-perf","Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-perf\u002FSKILL.md",[153],{"categoryNo":154,"categoryName":155,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000023","Skill与智能体开发",[157,158,159,160,161,162,163,164,165,23,166,167,168,169,170,28,171,172,173,34],"web","perf","web perf","resources","MCP","layout","optimize","documentation","caching","qa","knowledge","devtools","issues","render","performance","chrome devtools","vitals",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":39},"01M71AZ2KZNWYEGKKRMJH8PYG2","verify","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[176,121,181,182,143,113,183,184,23,185,36,186,187,188,189],"commands","about","claims","output","assertions","claim","prs","evidence","running",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"publishedAt":39},"01M71AZ0ACCK7N1QMWQK1FV2HJ","validate-idea","Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate-idea\u002FSKILL.md",[],[197,198,199,200,201,202,203,23,204,36,205],"validate","idea","validate idea","framework","it","minimalist","test","business","before building"]