[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M718Z7JPG0V4022NBCPHEW4W":3,"skill-same:01M718Z7JPG0V4022NBCPHEW4W":82},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M718Z7JPG0V4022NBCPHEW4W","xtarterize",null,"Apply production-grade conformance configurations (linting, type checking, CI, editor settings, AI skills, release tooling) to JS\u002FTS projects. Scans package.json and config files to auto-detect framework, bundler, and styling, then resolves applicable tasks. Use when user mentions \"xtarterize\", \"conformance\", \"setup linting\", \"add CI\", \"configure project\", \"init xtarterize\", or any task name like \"lint\u002Fbiome\", \"ts\u002Fstrict\", or \"ci\u002Fworkflow\".","agustinusnathaniel\u002Fxtarter","agustinusnathaniel","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F17046154?v=4","01M718YGB8QW647KSBHW6FJE60","Agustinus Nathaniel","01M718YGBYNAB67B9CAY3AH3HH",3,"MIT","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002Fskills\u002Fxtarterize\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"configure","bundler","styling","conformance","config","release","linting","biome","tasks","workflow","when","auto","files","auto-detect","init","ci","project","projects","ai skills","2026-11-10 10:12:30",false,"---\nname: xtarterize\ndescription: Apply production-grade conformance configurations (linting, type checking, CI, editor settings, AI skills, release tooling) to JS\u002FTS projects. Scans package.json and config files to auto-detect framework, bundler, and styling, then resolves applicable tasks. Use when user mentions \"xtarterize\", \"conformance\", \"setup linting\", \"add CI\", \"configure project\", \"init xtarterize\", or any task name like \"lint\u002Fbiome\", \"ts\u002Fstrict\", or \"ci\u002Fworkflow\".\n---\n\n# xtarterize\n\nScans any JS\u002FTS project and applies curated configs via a task-based engine. **Always use `--json`** for agent-driven invocations.\n\n## When this skill loads\n\nThis skill is activated when the user asks about project conformance, linting setup, CI, or any xtarterize task. Upon loading:\n\n1. **Assess the ask** - is the user requesting a full setup (`init`), a single task (`add`), a status check (`check`), a task search (`query`), or diagnostics (`doctor`)?\n2. **Check current state first** - run `check --json` to understand what's already configured before proposing changes\n3. **Never guess task IDs** - load the task reference before using `add`\n4. **Always use `--json`** - parse structured output, never terminal text\n\n## Quick reference\n\n```bash\nnpx xtarterize check --json   # { ok, summary, tasks: [{ id, label, group, status }], diagnostics }\nnpx xtarterize diff --json    # { files: [{ filepath, stats }], ok, summary }\nnpx xtarterize list --json    # { profile, tasks }\nnpx xtarterize query \"strict typescript\" --json  # { type: \"query\", results: [...] }\nnpx xtarterize doctor --json  # { diagnostics: [{ name, status, message }] }\nnpx xtarterize add lint\u002Fbiome --json\nnpx xtarterize init --json --yes\n```\n\n## JSON parsing patterns\n\nAfter each command, parse the JSON to decide the next action:\n\n| Command | Parse this field | To decide |\n|---------|-----------------|-----------|\n| `check --json` | `tasks[].status` | If any status is `\"new\"` or `\"patch\"`, run `init` or `add` |\n| `check --json` | `diagnostics[].status` | If any is `\"fail\"`, run `doctor` before proceeding |\n| `diff --json` | `files`, `ok` | Empty `files` (or `ok: true`) means nothing to change; otherwise show `files[].filepath` and `files[].stats.added`\u002F`stats.removed` as the change magnitude |\n| `list --json` | `tasks[].status`, `profile` | Find the right task ID to pass to `add`; understand the detected stack (framework, bundler, etc.) |\n| `doctor --json` | `diagnostics[].status` | Any `\"fail\"` needs fixing; `\"warn\"` is advisory |\n| `init --json` | `ok` | If `false`, something went wrong - check stderr |\n| `query --json` | `results[].relevance` | Score >= threshold means relevant. Use `results[].signals` to see which fields matched strongest |\n| `query --json` | `results[].taskId` | Pass to `add` to apply the matched task |\n| `query --json` | `count` | If 0, no tasks met the threshold - broaden query or lower `--threshold` |\n\nTask statuses are `new`, `patch`, `skip`, and `conflict`; the parsing table above shows how to act on each.\n\n## Agent workflows\n\n### Initialize a project\n\n```bash\n# 1. Check state\nout=$(npx xtarterize check --json --cwd \"$dir\")\n# Parse out.tasks[].status - if all \"skip\", skip init\n\n# 2. Preview\nout=$(npx xtarterize diff --json --cwd \"$dir\")\n# Parse out - if empty array, nothing to do\n\n# 3. Apply\nout=$(npx xtarterize init --json --yes --cwd \"$dir\")\n```\n\n### Add one task\n\n```bash\n# MANDATORY - Load references\u002Ftasks.md first to find exact task ID\nout=$(npx xtarterize add ts\u002Fstrict --json --cwd \"$dir\")\n```\n\n### Diagnose failures\n\n```bash\nout=$(npx xtarterize doctor --json --cwd \"$dir\")\n# Parse out.diagnostics - any { \"status\": \"fail\" } needs attention\n# Common fails: \"Biome not installed\", \"Node version too old\"\n```\n\n## Error handling\n\n| Signal | Likely cause | Fix |\n|--------|-------------|-----|\n| `add \u003Cid>` → \"Task not found\" | Wrong task ID | `list --json`, parse `tasks[].id` |\n| `Unknown option --jsn ... Did you mean --json?` | Typoed flag or command | Follow the suggestion, or run the command with `--help` for valid options |\n| `doctor` shows tool not installed | Missing dep | xtarterize only writes configs; user may need to install separately |\n| Task shows `\"conflict\"` | Config differs | **Never auto-apply** - present to user, only with `--include-conflicts` |\n| `--cwd` fails preflight | No `package.json` | Verify path exists and is a JS\u002FTS project |\n| `query` returns empty results | Query too narrow or no matching tasks | Broaden the query or lower `--threshold` |\n\n## Anti-patterns\n\n- **NEVER** run `init --yes` without `diff --json` first on existing projects\n- **NEVER** edit `.xtarterize\u002Fbackups\u002F` - use `restore` to recover\n- **NEVER** use `--include-conflicts` without user approval\n- **NEVER** parse terminal output - always use `--json`\n- **NEVER** guess task IDs - load [references\u002Ftasks.md](references\u002Ftasks.md) first\n\n## Reference files\n\n- **Load** [references\u002Ftasks.md](references\u002Ftasks.md) **before `add`** - find exact task IDs. **MANDATORY - READ ENTIRE FILE.**\n- **Load** [references\u002Fcommands.md](references\u002Fcommands.md) for detailed flag descriptions and JSON output shapes. **Do NOT load** for basic usage - covered above.\n","# xtarterize\n\nScans any JS\u002FTS project and applies curated configs via a task-based engine. **Always use `--json`** for agent-driven invocations.\n\n## When this skill loads\n\nThis skill is activated when the user asks about project conformance, linting setup, CI, or any xtarterize task. Upon loading:\n\n1. **Assess the ask** - is the user requesting a full setup (`init`), a single task (`add`), a status check (`check`), a task search (`query`), or diagnostics (`doctor`)?\n2. **Check current state first** - run `check --json` to understand what's already configured before proposing changes\n3. **Never guess task IDs** - load the task reference before using `add`\n4. **Always use `--json`** - parse structured output, never terminal text\n\n## Quick reference\n\n```bash\nnpx xtarterize check --json   # { ok, summary, tasks: [{ id, label, group, status }], diagnostics }\nnpx xtarterize diff --json    # { files: [{ filepath, stats }], ok, summary }\nnpx xtarterize list --json    # { profile, tasks }\nnpx xtarterize query \"strict typescript\" --json  # { type: \"query\", results: [...] }\nnpx xtarterize doctor --json  # { diagnostics: [{ name, status, message }] }\nnpx xtarterize add lint\u002Fbiome --json\nnpx xtarterize init --json --yes\n```\n\n## JSON parsing patterns\n\nAfter each command, parse the JSON to decide the next action:\n\n| Command | Parse this field | To decide |\n|---------|-----------------|-----------|\n| `check --json` | `tasks[].status` | If any status is `\"new\"` or `\"patch\"`, run `init` or `add` |\n| `check --json` | `diagnostics[].status` | If any is `\"fail\"`, run `doctor` before proceeding |\n| `diff --json` | `files`, `ok` | Empty `files` (or `ok: true`) means nothing to change; otherwise show `files[].filepath` and `files[].stats.added`\u002F`stats.removed` as the change magnitude |\n| `list --json` | `tasks[].status`, `profile` | Find the right task ID to pass to `add`; understand the detected stack (framework, bundler, etc.) |\n| `doctor --json` | `diagnostics[].status` | Any `\"fail\"` needs fixing; `\"warn\"` is advisory |\n| `init --json` | `ok` | If `false`, something went wrong - check stderr |\n| `query --json` | `results[].relevance` | Score >= threshold means relevant. Use `results[].signals` to see which fields matched strongest |\n| `query --json` | `results[].taskId` | Pass to `add` to apply the matched task |\n| `query --json` | `count` | If 0, no tasks met the threshold - broaden query or lower `--threshold` |\n\nTask statuses are `new`, `patch`, `skip`, and `conflict`; the parsing table above shows how to act on each.\n\n## Agent workflows\n\n### Initialize a project\n\n```bash\n# 1. Check state\nout=$(npx xtarterize check --json --cwd \"$dir\")\n# Parse out.tasks[].status - if all \"skip\", skip init\n\n# 2. Preview\nout=$(npx xtarterize diff --json --cwd \"$dir\")\n# Parse out - if empty array, nothing to do\n\n# 3. Apply\nout=$(npx xtarterize init --json --yes --cwd \"$dir\")\n```\n\n### Add one task\n\n```bash\n# MANDATORY - Load references\u002Ftasks.md first to find exact task ID\nout=$(npx xtarterize add ts\u002Fstrict --json --cwd \"$dir\")\n```\n\n### Diagnose failures\n\n```bash\nout=$(npx xtarterize doctor --json --cwd \"$dir\")\n# Parse out.diagnostics - any { \"status\": \"fail\" } needs attention\n# Common fails: \"Biome not installed\", \"Node version too old\"\n```\n\n## Error handling\n\n| Signal | Likely cause | Fix |\n|--------|-------------|-----|\n| `add \u003Cid>` → \"Task not found\" | Wrong task ID | `list --json`, parse `tasks[].id` |\n| `Unknown option --jsn ... Did you mean --json?` | Typoed flag or command | Follow the suggestion, or run the command with `--help` for valid options |\n| `doctor` shows tool not installed | Missing dep | xtarterize only writes configs; user may need to install separately |\n| Task shows `\"conflict\"` | Config differs | **Never auto-apply** - present to user, only with `--include-conflicts` |\n| `--cwd` fails preflight | No `package.json` | Verify path exists and is a JS\u002FTS project |\n| `query` returns empty results | Query too narrow or no matching tasks | Broaden the query or lower `--threshold` |\n\n## Anti-patterns\n\n- **NEVER** run `init --yes` without `diff --json` first on existing projects\n- **NEVER** edit `.xtarterize\u002Fbackups\u002F` - use `restore` to recover\n- **NEVER** use `--include-conflicts` without user approval\n- **NEVER** parse terminal output - always use `--json`\n- **NEVER** guess task IDs - load [references\u002Ftasks.md](references\u002Ftasks.md) first\n\n## Reference files\n\n- **Load** [references\u002Ftasks.md](references\u002Ftasks.md) **before `add`** - find exact task IDs. **MANDATORY - READ ENTIRE FILE.**\n- **Load** [references\u002Fcommands.md](references\u002Fcommands.md) for detailed flag descriptions and JSON output shapes. **Do NOT load** for basic usage - covered above.\n",{"name":5,"description":7},"main","54ceeb165943628361fbc1a0a920988b32b59331","skills\u002Fxtarterize",1,"https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter","https:\u002F\u002Fxtarter.sznm.dev","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel","https:\u002F\u002Fagustinusnathaniel.com","1.01 ^365 = 37.7","2026-11-07 03:32:08",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add agustinusnathaniel\u002Fxtarter --skill xtarterize",{"tool":64,"command":65},"bunx","bunx skills add agustinusnathaniel\u002Fxtarter --skill xtarterize",{"tool":67,"command":68},"pnpm","pnpm dlx skills add agustinusnathaniel\u002Fxtarter --skill xtarterize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002Fskills\u002Fxtarterize\u002FSKILL.md",true,[72,78],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fcommands.md","REFERENCE","参考文档",11279,"https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002Fskills\u002Fxtarterize\u002Freferences\u002Fcommands.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Ftasks.md",9508,"https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002Fskills\u002Fxtarterize\u002Freferences\u002Ftasks.md",[83,107,128,139,165,186],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":90,"publishedAt":43},"01M718Z4WSH10F33BMKJBSRTT0","create-xtarter-app","Scaffold new JS\u002FTS projects from curated starter templates pre-configured with Biome, TypeScript strict mode, Git hooks, GitHub Actions workflows, VS Code settings, and AI agent skills. Use when user wants to create a new project, scaffold an app from a template, or mentions \"create-xtarter-app\", \"npx create-xtarter-app\", \"scaffold\", \"starter template\", or a template name like \"next-tailwind\", \"vite-chakra\", \"vite-tailwind\", or \"next-chakra\".","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002Fskills\u002Fcreate-xtarter-app\u002FSKILL.md",[89],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[91,92,93,41,40,94,95,96,97,98,99,100,101,34,102,31,103,104,105,106],"app","create","create xtarter app","Tailwind","actions","mode","hooks","github actions","new","ai agent","workflows","code","chakra","next","template","typescript",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":114,"publishedAt":43},"01M718Z3EVKF68MH1C8SCT1103","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[113],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[115,116,117,118,119,120,99,121,34,122,123,92,124,125,126,127],"write a skill","write","resources","new agent","true","progressive","use","progressive disclosure","with","structure","build","new skill","user",{"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":135,"publishedAt":43},"01M718Z1D79ZNSHRGNTVYC47Q4","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftemplate-skill\u002FSKILL.md",[134],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[105,136,123,137,119,121,34,138],"template skill","replace","it",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":143,"licenseFileUrl":144,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":43},"01M718YXSFZA8KG6NTTE77GNE9","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-creator\u002FSKILL.md",[147],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[149,150,151,152,153,99,34,154,92,155,156,157,158,159,160,161,162,163,164,119],"skill creator","creator","performance","improve","run evals","analysis","optimize","variance analysis","run","edit","benchmark","existing skill","evals","for","accuracy","scratch",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":43},"01M718YTZEGNHGEXNPEPS6BYQY","opensrc","Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm\u002FPyPI\u002Fcrates.io package is built. Triggers include \"fetch source for\", \"read the source of\", \"how does X work internally\", \"get the implementation of\", \"opensrc path\", or any task requiring access to dependency source code beyond types and docs.","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fopensrc\u002FSKILL.md",[],[167,172,173,174,175,162,176,177,119,178,179,121,180,34,181,102,182,183,184,185],"fetch","types","get","deeper","explore","triggers","pypi","package","access","Bash","ai agents","task","io","work",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":43},"01M718YS36V9F1C54TPVHSXY94","improve-codebase-architecture","Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs\u002Fadr\u002F. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.","https:\u002F\u002Fgithub.com\u002Fagustinusnathaniel\u002Fxtarter\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimprove-codebase-architecture\u002FSKILL.md",[],[152,193,194,195,196,197,198,119,199,121,34,200,201,202,203,204,205,206,127,207],"architecture","improve codebase architecture","codebase","modules","adr","domain","more","decisions","consolidate","refactoring","find","deepening","docs","language","context"]