[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DDYF486CKFD4643DE8FTFF":3,"skill-same:01M6DDYF486CKFD4643DE8FTFF":75},{"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":29,"publishedAt":50,"linkOnly":51,"markdownContent":52,"markdownBody":53,"frontMatter":54,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":14,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M6DDYF486CKFD4643DE8FTFF","clone-website",null,"Use when the user wants to clone, replicate, reverse-engineer, or create a pixel-perfect copy of a website or web app as a single self-contained HTML prototype — extracts design tokens, assets, computed CSS, interaction patterns, and content via Playwright, then rebuilds one dependency-free HTML file.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fclone-website\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"website","clone website","dependency","free","app","as","html prototype","tokens","self","pixel","engineer","design","use","replicate","file","create","web","playwright","prototype","css","2026-11-10 10:12:30",false,"---\nname: clone-website\ndescription: Use when the user wants to clone, replicate, reverse-engineer, or create a pixel-perfect copy of a website or web app as a single self-contained HTML prototype — extracts design tokens, assets, computed CSS, interaction patterns, and content via Playwright, then rebuilds one dependency-free HTML file.\n---\n\n\u003C!-- Source: cherry-picked from https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco (skills\u002Fclone-website) on 27.08.2026 per grill decision G-11\u002F11B; itself adapted from https:\u002F\u002Fgithub.com\u002FJCodesMore\u002Fai-website-cloner-template. Adapted to house format; coco brain-DB integration removed. -->\n\n# Clone Website — Single-File HTML Prototype Builder\n\nReverse-engineer one or more target URLs into a pixel-perfect single-file HTML prototype:\n\n- **One HTML file** with `\u003Cstyle>` + markup + `\u003Cscript>` sections\n- **Zero external dependencies** — all CSS inline, all JS inline, all assets base64-encoded or SVG inline\n- **Real data injection** — actual data from the project's files where available, not lorem ipsum\n- **Project design system** when available — use tokens from a `design-system.json` colocated with the project\n\n## Pre-Flight\n\n1. **Playwright is required.** Verify: `npx playwright --version`. If missing, install (`npm i -D playwright`) or use the resident Playwright MCP.\n2. Validate each target URL is accessible.\n3. Create an output directory for captured assets (e.g. `{project}\u002FScreenshots-clone\u002F`).\n4. Determine clone mode:\n   - **Full clone** (default): pixel-perfect reproduction of the entire page\n   - **Design extraction only**: capture design tokens, screenshots, and component specs without building\n   - **Selective clone** (e.g. \"header,table,sidebar\"): clone only named sections\n\n## Phase 1: Reconnaissance (Playwright)\n\n### 1.1 Screenshots\n\n```javascript\nimport { chromium } from 'playwright';\nconst browser = await chromium.launch();\nconst page = await browser.newPage({ viewport: { width: 1440, height: 900 } });\nawait page.goto(URL);\nawait page.screenshot({ path: 'full-desktop.png', fullPage: true });\nawait page.screenshot({ path: 'viewport-desktop.png' });\nawait page.setViewportSize({ width: 390, height: 844 });\nawait page.screenshot({ path: 'viewport-mobile.png', fullPage: true });\n```\n\n### 1.2 Design Token Extraction\n\nRun in `page.evaluate()`:\n\n```javascript\nconst tokens = await page.evaluate(() => {\n  const colorMap = new Map();\n  document.querySelectorAll('*').forEach(el => {\n    const cs = getComputedStyle(el);\n    ['color','backgroundColor','borderColor','borderTopColor','borderBottomColor'].forEach(p => {\n      const v = cs[p];\n      if (v && v !== 'rgba(0, 0, 0, 0)' && v !== 'transparent') colorMap.set(v, (colorMap.get(v)||0)+1);\n    });\n  });\n  const fontMap = new Map();\n  document.querySelectorAll('*').forEach(el => {\n    const cs = getComputedStyle(el);\n    const key = `${cs.fontFamily}|${cs.fontSize}|${cs.fontWeight}|${cs.lineHeight}`;\n    fontMap.set(key, (fontMap.get(key)||0)+1);\n  });\n  const spacingSet = new Set(), shadowSet = new Set(), radiusSet = new Set();\n  document.querySelectorAll('*').forEach(el => {\n    const cs = getComputedStyle(el);\n    ['padding','margin','gap'].forEach(p => { const v = cs[p]; if (v && v !== '0px') spacingSet.add(v); });\n    if (cs.boxShadow && cs.boxShadow !== 'none') shadowSet.add(cs.boxShadow);\n    if (cs.borderRadius && cs.borderRadius !== '0px') radiusSet.add(cs.borderRadius);\n  });\n  return {\n    colors: [...colorMap.entries()].sort((a,b) => b[1]-a[1]).slice(0,30),\n    typography: [...fontMap.entries()].sort((a,b) => b[1]-a[1]).slice(0,20),\n    spacing: [...spacingSet].sort(),\n    shadows: [...shadowSet],\n    radii: [...radiusSet].sort()\n  };\n});\n```\n\n### 1.3 Component CSS Extraction (Deep)\n\nFor each major component\u002Fsection, extract exact computed styles recursively (depth ≤ 4), keeping only meaningful values:\n\n```javascript\nconst componentCSS = await page.evaluate((selector) => {\n  const el = document.querySelector(selector);\n  if (!el) return null;\n  const props = [\n    'fontSize','fontWeight','fontFamily','lineHeight','letterSpacing','color',\n    'textTransform','textDecoration','backgroundColor','background',\n    'padding','paddingTop','paddingRight','paddingBottom','paddingLeft',\n    'margin','marginTop','marginRight','marginBottom','marginLeft',\n    'width','height','maxWidth','minWidth','display','flexDirection',\n    'justifyContent','alignItems','gap','gridTemplateColumns',\n    'borderRadius','border','boxShadow','overflow','position',\n    'top','right','bottom','left','zIndex','opacity','transform','transition'\n  ];\n  function extract(element, depth) {\n    if (depth > 4) return null;\n    const cs = getComputedStyle(element);\n    const styles = {};\n    props.forEach(p => {\n      const v = cs[p];\n      if (v && v !== 'none' && v !== 'normal' && v !== 'auto' && v !== '0px' && v !== 'rgba(0, 0, 0, 0)')\n        styles[p] = v;\n    });\n    return {\n      tag: element.tagName.toLowerCase(),\n      classes: element.className?.toString().split(' ').slice(0,5).join(' '),\n      text: element.childNodes.length === 1 && element.childNodes[0].nodeType === 3\n        ? element.textContent.trim().slice(0,200) : null,\n      styles,\n      children: [...element.children].slice(0,20).map(c => extract(c, depth+1)).filter(Boolean)\n    };\n  }\n  return extract(el, 0);\n}, selector);\n```\n\n### 1.4 Interaction Sweep\n\n- **Scroll sweep:** step `window.scrollTo` in ~300px increments; watch for sticky headers and scroll-triggered animations.\n- **Hover sweep:** hover `button, a, [role=\"tab\"], .nav-item, .card` (cap ~30 elements).\n- **Click sweep:** click tabs\u002Fdropdowns (`[role=\"tab\"], .tab-item, .nav-tab`) and observe state changes.\n\n### 1.5 Asset Extraction\n\n- Extract all inline `\u003Csvg>` elements as code (with parent class and dimensions).\n- Collect all `\u003Cimg>` URLs with alt text and natural dimensions for download\u002Fbase64 embedding.\n\n## Phase 2: Foundation Build\n\nConvert extracted tokens into CSS custom properties (`--color-bg`, `--color-text`, `--color-accent`, `--font-family`, `--shadow-sm`, ...), mapped to semantic names.\n\n## Phase 3: Section Building\n\nFor each major section of the page:\n\n1. Write a spec with exact CSS values + screenshot + content\n2. Build the section's HTML + CSS + JS (dispatch parallel builder subagents only if the environment allows it — on RAM-constrained boxes build sequentially)\n3. **Complexity budget:** if a section spec exceeds ~150 lines, split it\n\n## Phase 4: Assembly\n\n1. Deduplicate CSS — combine all section styles, remove duplicates\n2. Order HTML — sections in visual order (top to bottom)\n3. Combine JS — all event handlers and render functions in one `\u003Cscript>` block\n4. Base64-encode any images that couldn't be replaced with CSS\u002FSVG\n5. Verify: open in browser, compare against original screenshots\n\n## Phase 5: Quality Check\n\nUse Playwright to open the built HTML file, re-screenshot at the same viewpoints as Phase 1, compare side-by-side, test all interactions (clicks, hovers, tabs), and report visual differences.\n\n## Project-Specific Mode\n\nWhen a `design-system.json` exists in the project: load its tokens as CSS custom properties in the output, and inject any real data the project references (Excel, JSON).\n","\u003C!-- Source: cherry-picked from https:\u002F\u002Fgithub.com\u002Fcoco-research\u002Fcoco (skills\u002Fclone-website) on 27.08.2026 per grill decision G-11\u002F11B; itself adapted from https:\u002F\u002Fgithub.com\u002FJCodesMore\u002Fai-website-cloner-template. Adapted to house format; coco brain-DB integration removed. -->\n\n# Clone Website — Single-File HTML Prototype Builder\n\nReverse-engineer one or more target URLs into a pixel-perfect single-file HTML prototype:\n\n- **One HTML file** with `\u003Cstyle>` + markup + `\u003Cscript>` sections\n- **Zero external dependencies** — all CSS inline, all JS inline, all assets base64-encoded or SVG inline\n- **Real data injection** — actual data from the project's files where available, not lorem ipsum\n- **Project design system** when available — use tokens from a `design-system.json` colocated with the project\n\n## Pre-Flight\n\n1. **Playwright is required.** Verify: `npx playwright --version`. If missing, install (`npm i -D playwright`) or use the resident Playwright MCP.\n2. Validate each target URL is accessible.\n3. Create an output directory for captured assets (e.g. `{project}\u002FScreenshots-clone\u002F`).\n4. Determine clone mode:\n   - **Full clone** (default): pixel-perfect reproduction of the entire page\n   - **Design extraction only**: capture design tokens, screenshots, and component specs without building\n   - **Selective clone** (e.g. \"header,table,sidebar\"): clone only named sections\n\n## Phase 1: Reconnaissance (Playwright)\n\n### 1.1 Screenshots\n\n```javascript\nimport { chromium } from 'playwright';\nconst browser = await chromium.launch();\nconst page = await browser.newPage({ viewport: { width: 1440, height: 900 } });\nawait page.goto(URL);\nawait page.screenshot({ path: 'full-desktop.png', fullPage: true });\nawait page.screenshot({ path: 'viewport-desktop.png' });\nawait page.setViewportSize({ width: 390, height: 844 });\nawait page.screenshot({ path: 'viewport-mobile.png', fullPage: true });\n```\n\n### 1.2 Design Token Extraction\n\nRun in `page.evaluate()`:\n\n```javascript\nconst tokens = await page.evaluate(() => {\n  const colorMap = new Map();\n  document.querySelectorAll('*').forEach(el => {\n    const cs = getComputedStyle(el);\n    ['color','backgroundColor','borderColor','borderTopColor','borderBottomColor'].forEach(p => {\n      const v = cs[p];\n      if (v && v !== 'rgba(0, 0, 0, 0)' && v !== 'transparent') colorMap.set(v, (colorMap.get(v)||0)+1);\n    });\n  });\n  const fontMap = new Map();\n  document.querySelectorAll('*').forEach(el => {\n    const cs = getComputedStyle(el);\n    const key = `${cs.fontFamily}|${cs.fontSize}|${cs.fontWeight}|${cs.lineHeight}`;\n    fontMap.set(key, (fontMap.get(key)||0)+1);\n  });\n  const spacingSet = new Set(), shadowSet = new Set(), radiusSet = new Set();\n  document.querySelectorAll('*').forEach(el => {\n    const cs = getComputedStyle(el);\n    ['padding','margin','gap'].forEach(p => { const v = cs[p]; if (v && v !== '0px') spacingSet.add(v); });\n    if (cs.boxShadow && cs.boxShadow !== 'none') shadowSet.add(cs.boxShadow);\n    if (cs.borderRadius && cs.borderRadius !== '0px') radiusSet.add(cs.borderRadius);\n  });\n  return {\n    colors: [...colorMap.entries()].sort((a,b) => b[1]-a[1]).slice(0,30),\n    typography: [...fontMap.entries()].sort((a,b) => b[1]-a[1]).slice(0,20),\n    spacing: [...spacingSet].sort(),\n    shadows: [...shadowSet],\n    radii: [...radiusSet].sort()\n  };\n});\n```\n\n### 1.3 Component CSS Extraction (Deep)\n\nFor each major component\u002Fsection, extract exact computed styles recursively (depth ≤ 4), keeping only meaningful values:\n\n```javascript\nconst componentCSS = await page.evaluate((selector) => {\n  const el = document.querySelector(selector);\n  if (!el) return null;\n  const props = [\n    'fontSize','fontWeight','fontFamily','lineHeight','letterSpacing','color',\n    'textTransform','textDecoration','backgroundColor','background',\n    'padding','paddingTop','paddingRight','paddingBottom','paddingLeft',\n    'margin','marginTop','marginRight','marginBottom','marginLeft',\n    'width','height','maxWidth','minWidth','display','flexDirection',\n    'justifyContent','alignItems','gap','gridTemplateColumns',\n    'borderRadius','border','boxShadow','overflow','position',\n    'top','right','bottom','left','zIndex','opacity','transform','transition'\n  ];\n  function extract(element, depth) {\n    if (depth > 4) return null;\n    const cs = getComputedStyle(element);\n    const styles = {};\n    props.forEach(p => {\n      const v = cs[p];\n      if (v && v !== 'none' && v !== 'normal' && v !== 'auto' && v !== '0px' && v !== 'rgba(0, 0, 0, 0)')\n        styles[p] = v;\n    });\n    return {\n      tag: element.tagName.toLowerCase(),\n      classes: element.className?.toString().split(' ').slice(0,5).join(' '),\n      text: element.childNodes.length === 1 && element.childNodes[0].nodeType === 3\n        ? element.textContent.trim().slice(0,200) : null,\n      styles,\n      children: [...element.children].slice(0,20).map(c => extract(c, depth+1)).filter(Boolean)\n    };\n  }\n  return extract(el, 0);\n}, selector);\n```\n\n### 1.4 Interaction Sweep\n\n- **Scroll sweep:** step `window.scrollTo` in ~300px increments; watch for sticky headers and scroll-triggered animations.\n- **Hover sweep:** hover `button, a, [role=\"tab\"], .nav-item, .card` (cap ~30 elements).\n- **Click sweep:** click tabs\u002Fdropdowns (`[role=\"tab\"], .tab-item, .nav-tab`) and observe state changes.\n\n### 1.5 Asset Extraction\n\n- Extract all inline `\u003Csvg>` elements as code (with parent class and dimensions).\n- Collect all `\u003Cimg>` URLs with alt text and natural dimensions for download\u002Fbase64 embedding.\n\n## Phase 2: Foundation Build\n\nConvert extracted tokens into CSS custom properties (`--color-bg`, `--color-text`, `--color-accent`, `--font-family`, `--shadow-sm`, ...), mapped to semantic names.\n\n## Phase 3: Section Building\n\nFor each major section of the page:\n\n1. Write a spec with exact CSS values + screenshot + content\n2. Build the section's HTML + CSS + JS (dispatch parallel builder subagents only if the environment allows it — on RAM-constrained boxes build sequentially)\n3. **Complexity budget:** if a section spec exceeds ~150 lines, split it\n\n## Phase 4: Assembly\n\n1. Deduplicate CSS — combine all section styles, remove duplicates\n2. Order HTML — sections in visual order (top to bottom)\n3. Combine JS — all event handlers and render functions in one `\u003Cscript>` block\n4. Base64-encode any images that couldn't be replaced with CSS\u002FSVG\n5. Verify: open in browser, compare against original screenshots\n\n## Phase 5: Quality Check\n\nUse Playwright to open the built HTML file, re-screenshot at the same viewpoints as Phase 1, compare side-by-side, test all interactions (clicks, hovers, tabs), and report visual differences.\n\n## Project-Specific Mode\n\nWhen a `design-system.json` exists in the project: load its tokens as CSS custom properties in the output, and inject any real data the project references (Excel, JSON).\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fclone-website","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill clone-website",{"tool":67,"command":68},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill clone-website",{"tool":70,"command":71},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill clone-website","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fclone-website\u002FSKILL.md",true,[],[76,96,124,147,161,177],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":50},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[83,84,85,86,87,88,89,90,91,42,92,93,94,95,44],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":105,"publishedAt":50},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[102],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[106,107,108,109,110,111,112,113,114,115,116,117,118,119,42,33,120,121,122,123],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","molecular dynamics","local","do","MCP",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":134,"publishedAt":50},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[130,133],{"categoryNo":131,"categoryName":132,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,137,138,46,139,140,141,142,143,107,144,145,47,146],"review","visual","visual review","pages","false","iteration","take","check","slides","ui","screenshot","screenshots",{"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":153,"publishedAt":50},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[149,154,155,156,157,158,159,160],"setup","report","project","installation","project setup","issues","state",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":50},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[167],{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},[163,169,88,170,171,172,42,173,174,175,176],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":178,"name":154,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":50},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[154,156,121,183,158,184],"files","interactive"]