[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70NGRTPVJGRRVCKHFCZ7PSK":3,"skill-same:01M70NGRTPVJGRRVCKHFCZ7PSK":83},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":54,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":57,"updatedAt":58,"install":59,"resources":72},"01M70NGRTPVJGRRVCKHFCZ7PSK","sandbox-sdk",null,"Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI\u002FCD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fsandbox-sdk\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"sandbox","sdk","sandbox sdk","execution","lifecycle","applications","code execution","for","environments","commands","CI\u002FCD","secure","code","preview","when","files","knowledge","cloudflare","ci","interpreter","2026-11-10 10:12:30",false,"---\nname: sandbox-sdk\ndescription: Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI\u002FCD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.\n---\n\n# Cloudflare Sandbox SDK\n\nBuild secure, isolated code execution environments on Cloudflare Workers.\n\n## FIRST: Verify Installation\n\n```bash\nnpm install @cloudflare\u002Fsandbox\ndocker info  # Must succeed - Docker required for local dev\n```\n\n## Retrieval Sources\n\nYour knowledge of the Sandbox SDK may be outdated. **Prefer retrieval over pre-training** for any Sandbox SDK task.\n\n| Resource | URL |\n|----------|-----|\n| Docs | https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002F |\n| API Reference | https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fapi\u002F |\n| Examples | https:\u002F\u002Fgithub.com\u002Fcloudflare\u002Fsandbox-sdk\u002Ftree\u002Fmain\u002Fexamples |\n| Get Started | https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fget-started\u002F |\n\nWhen implementing features, fetch the relevant doc page or example first.\n\n## Required Configuration\n\n**wrangler.jsonc** (exact - do not modify structure):\n\n```jsonc\n{\n  \"containers\": [{\n    \"class_name\": \"Sandbox\",\n    \"image\": \".\u002FDockerfile\",\n    \"instance_type\": \"lite\",\n    \"max_instances\": 1\n  }],\n  \"durable_objects\": {\n    \"bindings\": [{ \"class_name\": \"Sandbox\", \"name\": \"Sandbox\" }]\n  },\n  \"migrations\": [{ \"new_sqlite_classes\": [\"Sandbox\"], \"tag\": \"v1\" }]\n}\n```\n\n**Worker entry** - must re-export Sandbox class:\n\n```typescript\nimport { getSandbox } from '@cloudflare\u002Fsandbox';\nexport { Sandbox } from '@cloudflare\u002Fsandbox';  \u002F\u002F Required export\n```\n\n## Quick Reference\n\n| Task | Method |\n|------|--------|\n| Get sandbox | `getSandbox(env.Sandbox, 'user-123')` |\n| Run command | `await sandbox.exec('python script.py')` |\n| Run code (interpreter) | `await sandbox.runCode(code, { language: 'python' })` |\n| Write file | `await sandbox.writeFile('\u002Fworkspace\u002Fapp.py', content)` |\n| Read file | `await sandbox.readFile('\u002Fworkspace\u002Fapp.py')` |\n| Create directory | `await sandbox.mkdir('\u002Fworkspace\u002Fsrc', { recursive: true })` |\n| List files | `await sandbox.listFiles('\u002Fworkspace')` |\n| Expose port | `await sandbox.exposePort(8080)` |\n| Destroy | `await sandbox.destroy()` |\n\n## Core Patterns\n\n### Execute Commands\n\n```typescript\nconst sandbox = getSandbox(env.Sandbox, 'user-123');\nconst result = await sandbox.exec('python --version');\n\u002F\u002F result: { stdout, stderr, exitCode, success }\n```\n\n### Code Interpreter (Recommended for AI)\n\nUse `runCode()` for executing LLM-generated code with rich outputs:\n\n```typescript\nconst ctx = await sandbox.createCodeContext({ language: 'python' });\n\nawait sandbox.runCode('import pandas as pd; data = [1,2,3]', { context: ctx });\nconst result = await sandbox.runCode('sum(data)', { context: ctx });\n\u002F\u002F result.results[0].text = \"6\"\n```\n\n**Languages**: `python`, `javascript`, `typescript`\n\nState persists within context. Create explicit contexts for production.\n\n### File Operations\n\n```typescript\nawait sandbox.mkdir('\u002Fworkspace\u002Fproject', { recursive: true });\nawait sandbox.writeFile('\u002Fworkspace\u002Fproject\u002Fmain.py', code);\nconst file = await sandbox.readFile('\u002Fworkspace\u002Fproject\u002Fmain.py');\nconst files = await sandbox.listFiles('\u002Fworkspace\u002Fproject');\n```\n\n## When to Use What\n\n| Need | Use | Why |\n|------|-----|-----|\n| Shell commands, scripts | `exec()` | Direct control, streaming |\n| LLM-generated code | `runCode()` | Rich outputs, state persistence |\n| Build\u002Ftest pipelines | `exec()` | Exit codes, stderr capture |\n| Data analysis | `runCode()` | Charts, tables, pandas |\n\n## Extending the Dockerfile\n\nBase image (`docker.io\u002Fcloudflare\u002Fsandbox:0.7.0`) includes Python 3.11, Node.js 20, and common tools.\n\nAdd dependencies by extending the Dockerfile:\n\n```dockerfile\nFROM docker.io\u002Fcloudflare\u002Fsandbox:0.7.0\n\n# Python packages\nRUN pip install requests beautifulsoup4\n\n# Node packages (global)\nRUN npm install -g typescript\n\n# System packages\nRUN apt-get update && apt-get install -y ffmpeg && rm -rf \u002Fvar\u002Flib\u002Fapt\u002Flists\u002F*\n\nEXPOSE 8080  # Required for local dev port exposure\n```\n\nKeep images lean - affects cold start time.\n\n## Preview URLs (Port Exposure)\n\nExpose HTTP services running in sandboxes:\n\n```typescript\nconst { url } = await sandbox.exposePort(8080);\n\u002F\u002F Returns preview URL for the service\n```\n\n**Production requirement**: Preview URLs need a custom domain with wildcard DNS (`*.yourdomain.com`). The `.workers.dev` domain does not support preview URL subdomains.\n\nSee: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fguides\u002Fexpose-services\u002F\n\n## OpenAI Agents SDK Integration\n\nThe SDK provides helpers for OpenAI Agents at `@cloudflare\u002Fsandbox\u002Fopenai`:\n\n```typescript\nimport { Shell, Editor } from '@cloudflare\u002Fsandbox\u002Fopenai';\n```\n\nSee `examples\u002Fopenai-agents` for complete integration pattern.\n\n## Sandbox Lifecycle\n\n- `getSandbox()` returns immediately - container starts lazily on first operation\n- Containers sleep after 10 minutes of inactivity (configurable via `sleepAfter`)\n- Use `destroy()` to immediately free resources\n- Same `sandboxId` always returns same sandbox instance\n\n## Anti-Patterns\n\n- **Don't use internal clients** (`CommandClient`, `FileClient`) - use `sandbox.*` methods\n- **Don't skip the Sandbox export** - Worker won't deploy without `export { Sandbox }`\n- **Don't hardcode sandbox IDs for multi-user** - use user\u002Fsession identifiers\n- **Don't forget cleanup** - call `destroy()` for temporary sandboxes\n\n## Detailed References\n\n- **[references\u002Fapi-quick-ref.md](references\u002Fapi-quick-ref.md)** - Full API with options and return types\n- **[references\u002Fexamples.md](references\u002Fexamples.md)** - Example index with use cases\n","# Cloudflare Sandbox SDK\n\nBuild secure, isolated code execution environments on Cloudflare Workers.\n\n## FIRST: Verify Installation\n\n```bash\nnpm install @cloudflare\u002Fsandbox\ndocker info  # Must succeed - Docker required for local dev\n```\n\n## Retrieval Sources\n\nYour knowledge of the Sandbox SDK may be outdated. **Prefer retrieval over pre-training** for any Sandbox SDK task.\n\n| Resource | URL |\n|----------|-----|\n| Docs | https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002F |\n| API Reference | https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fapi\u002F |\n| Examples | https:\u002F\u002Fgithub.com\u002Fcloudflare\u002Fsandbox-sdk\u002Ftree\u002Fmain\u002Fexamples |\n| Get Started | https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fget-started\u002F |\n\nWhen implementing features, fetch the relevant doc page or example first.\n\n## Required Configuration\n\n**wrangler.jsonc** (exact - do not modify structure):\n\n```jsonc\n{\n  \"containers\": [{\n    \"class_name\": \"Sandbox\",\n    \"image\": \".\u002FDockerfile\",\n    \"instance_type\": \"lite\",\n    \"max_instances\": 1\n  }],\n  \"durable_objects\": {\n    \"bindings\": [{ \"class_name\": \"Sandbox\", \"name\": \"Sandbox\" }]\n  },\n  \"migrations\": [{ \"new_sqlite_classes\": [\"Sandbox\"], \"tag\": \"v1\" }]\n}\n```\n\n**Worker entry** - must re-export Sandbox class:\n\n```typescript\nimport { getSandbox } from '@cloudflare\u002Fsandbox';\nexport { Sandbox } from '@cloudflare\u002Fsandbox';  \u002F\u002F Required export\n```\n\n## Quick Reference\n\n| Task | Method |\n|------|--------|\n| Get sandbox | `getSandbox(env.Sandbox, 'user-123')` |\n| Run command | `await sandbox.exec('python script.py')` |\n| Run code (interpreter) | `await sandbox.runCode(code, { language: 'python' })` |\n| Write file | `await sandbox.writeFile('\u002Fworkspace\u002Fapp.py', content)` |\n| Read file | `await sandbox.readFile('\u002Fworkspace\u002Fapp.py')` |\n| Create directory | `await sandbox.mkdir('\u002Fworkspace\u002Fsrc', { recursive: true })` |\n| List files | `await sandbox.listFiles('\u002Fworkspace')` |\n| Expose port | `await sandbox.exposePort(8080)` |\n| Destroy | `await sandbox.destroy()` |\n\n## Core Patterns\n\n### Execute Commands\n\n```typescript\nconst sandbox = getSandbox(env.Sandbox, 'user-123');\nconst result = await sandbox.exec('python --version');\n\u002F\u002F result: { stdout, stderr, exitCode, success }\n```\n\n### Code Interpreter (Recommended for AI)\n\nUse `runCode()` for executing LLM-generated code with rich outputs:\n\n```typescript\nconst ctx = await sandbox.createCodeContext({ language: 'python' });\n\nawait sandbox.runCode('import pandas as pd; data = [1,2,3]', { context: ctx });\nconst result = await sandbox.runCode('sum(data)', { context: ctx });\n\u002F\u002F result.results[0].text = \"6\"\n```\n\n**Languages**: `python`, `javascript`, `typescript`\n\nState persists within context. Create explicit contexts for production.\n\n### File Operations\n\n```typescript\nawait sandbox.mkdir('\u002Fworkspace\u002Fproject', { recursive: true });\nawait sandbox.writeFile('\u002Fworkspace\u002Fproject\u002Fmain.py', code);\nconst file = await sandbox.readFile('\u002Fworkspace\u002Fproject\u002Fmain.py');\nconst files = await sandbox.listFiles('\u002Fworkspace\u002Fproject');\n```\n\n## When to Use What\n\n| Need | Use | Why |\n|------|-----|-----|\n| Shell commands, scripts | `exec()` | Direct control, streaming |\n| LLM-generated code | `runCode()` | Rich outputs, state persistence |\n| Build\u002Ftest pipelines | `exec()` | Exit codes, stderr capture |\n| Data analysis | `runCode()` | Charts, tables, pandas |\n\n## Extending the Dockerfile\n\nBase image (`docker.io\u002Fcloudflare\u002Fsandbox:0.7.0`) includes Python 3.11, Node.js 20, and common tools.\n\nAdd dependencies by extending the Dockerfile:\n\n```dockerfile\nFROM docker.io\u002Fcloudflare\u002Fsandbox:0.7.0\n\n# Python packages\nRUN pip install requests beautifulsoup4\n\n# Node packages (global)\nRUN npm install -g typescript\n\n# System packages\nRUN apt-get update && apt-get install -y ffmpeg && rm -rf \u002Fvar\u002Flib\u002Fapt\u002Flists\u002F*\n\nEXPOSE 8080  # Required for local dev port exposure\n```\n\nKeep images lean - affects cold start time.\n\n## Preview URLs (Port Exposure)\n\nExpose HTTP services running in sandboxes:\n\n```typescript\nconst { url } = await sandbox.exposePort(8080);\n\u002F\u002F Returns preview URL for the service\n```\n\n**Production requirement**: Preview URLs need a custom domain with wildcard DNS (`*.yourdomain.com`). The `.workers.dev` domain does not support preview URL subdomains.\n\nSee: https:\u002F\u002Fdevelopers.cloudflare.com\u002Fsandbox\u002Fguides\u002Fexpose-services\u002F\n\n## OpenAI Agents SDK Integration\n\nThe SDK provides helpers for OpenAI Agents at `@cloudflare\u002Fsandbox\u002Fopenai`:\n\n```typescript\nimport { Shell, Editor } from '@cloudflare\u002Fsandbox\u002Fopenai';\n```\n\nSee `examples\u002Fopenai-agents` for complete integration pattern.\n\n## Sandbox Lifecycle\n\n- `getSandbox()` returns immediately - container starts lazily on first operation\n- Containers sleep after 10 minutes of inactivity (configurable via `sleepAfter`)\n- Use `destroy()` to immediately free resources\n- Same `sandboxId` always returns same sandbox instance\n\n## Anti-Patterns\n\n- **Don't use internal clients** (`CommandClient`, `FileClient`) - use `sandbox.*` methods\n- **Don't skip the Sandbox export** - Worker won't deploy without `export { Sandbox }`\n- **Don't hardcode sandbox IDs for multi-user** - use user\u002Fsession identifiers\n- **Don't forget cleanup** - call `destroy()` for temporary sandboxes\n\n## Detailed References\n\n- **[references\u002Fapi-quick-ref.md](references\u002Fapi-quick-ref.md)** - Full API with options and return types\n- **[references\u002Fexamples.md](references\u002Fexamples.md)** - Example index with use cases\n",{"name":5,"description":7},"main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Fsandbox-sdk",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill sandbox-sdk",{"tool":65,"command":66},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill sandbox-sdk",{"tool":68,"command":69},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill sandbox-sdk","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fsandbox-sdk\u002FSKILL.md",true,[73,79],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002Fapi-quick-ref.md","REFERENCE","参考文档",3220,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fsandbox-sdk\u002Freferences\u002Fapi-quick-ref.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fexamples.md",1570,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fsandbox-sdk\u002Freferences\u002Fexamples.md",[84,93,101,109,117,125],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":92},"01M73H7XKBHE1ETQDZT94MF9HH","seedance-prompt-en","Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fseedance-prompt-en\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":92},"01M73GRE9998Q1DZWC71N41JWG","onepage-pdf","Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file\u002Freport\u002Fproposal into a \"single-page PDF\", \"long PDF\", \"不分页 PDF\", \"单页 PDF\", \"长图式 PDF\", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fonepage-pdf\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":92},"01M73GQG1KZDADVPV3MHAT1J5A","native-feel-cross-platform-desktop","Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include \"cross-platform desktop\", \"Electron alternative\", \"Tauri vs native\", \"WebView wrapper\", \"near-native performance\", \"Raycast architecture\", \"WebKit\u002FWebView2 quirks\", \"WKWebView\", \"system tray app\", \"global hotkey app\", \"launcher app\". Do NOT trigger this skill for pure web apps, pure mobile apps, or for greenfield projects that have no native-feel requirement.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fnative-feel-cross-platform-desktop\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":92},"01M73G87PDNSMKG2FHWCYER6N8","gstack","Router for the gstack skill suite. (gstack)","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fgstack\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":92},"01M73G3EAQWKCM8DB8D0N0QSVG","fireworks-tech-graph","Use when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent\u002Fmemory, or concept map - and export as SVG+PNG. Trigger on: \"画图\" \"帮我画\" \"生成图\" \"做个图\" \"架构图\" \"流程图\" \"可视化一下\" \"出图\" \"generate diagram\" \"draw diagram\" \"visualize\" or any system\u002Fflow description the user wants illustrated.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Ffireworks-tech-graph\u002FSKILL.md",[],[],{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":92},"01M73G086AXAH9DW1H5G5N3CPB","dbs-video-extract","接收抖音、小红书、微信视频号等短视频链接或分享文案，查询作品／账号数据并提取语音文字稿，按作者和标题归档为 Markdown。用户希望完整解析短视频、取得数据或文字稿时使用；运行前检查 TikHub 与轻抖使用凭证，缺少时用新手能理解的方式引导购买和安全配置。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fdbs-video-extract\u002FSKILL.md",[],[]]