[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CVXC8PWRSPFNW3VCYN3SB5":3,"skill-same:01M7CVXC8PWRSPFNW3VCYN3SB5":123},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":94,"commitSha":95,"skillDirectory":96,"forksCount":14,"repositoryHtmlUrl":97,"repositoryHomepageUrl":98,"ownerHtmlUrl":99,"ownerBlogUrl":100,"ownerDescription":101,"updatedAt":102,"install":103,"resources":116},"01M7CVXC8PWRSPFNW3VCYN3SB5","vercel-sandbox",null,"Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.","realsudarshan\u002FSD-skill","realsudarshan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128029723?v=4","01M7CTP2JEKQ9KBJ51NRZ2777Z","Sudarshan Dhakal","01M7CTP2JYR2PRY3BWGA30HX7J",0,"MIT","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fofficial-openai\u002Fopenai-local-vercel-vercel-sandbox\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vercel-sandbox\ndescription: Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.\nmetadata:\n  priority: 4\n  docs:\n    - \"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fsandbox\"\n  sitemap: \"https:\u002F\u002Fvercel.com\u002Fsitemap\u002Fdocs.xml\"\n  pathPatterns: []\n  importPatterns:\n    - '@vercel\u002Fsandbox'\n  bashPatterns:\n    - '\\bnpm\\s+(install|i|add)\\s+[^\\n]*@vercel\u002Fsandbox\\b'\n    - '\\bpnpm\\s+(install|i|add)\\s+[^\\n]*@vercel\u002Fsandbox\\b'\n    - '\\bbun\\s+(install|i|add)\\s+[^\\n]*@vercel\u002Fsandbox\\b'\n    - '\\byarn\\s+add\\s+[^\\n]*@vercel\u002Fsandbox\\b'\n  promptSignals:\n    phrases:\n      - \"@vercel\u002Fsandbox\"\n      - \"sandbox\"\n      - \"code sandbox\"\n      - \"vercel sandbox\"\n      - \"isolated environment\"\n      - \"sandboxed execution\"\n    allOf:\n      - [sandbox, code]\n      - [sandbox, execute]\n      - [sandbox, run]\n      - [sandbox, isolated]\n      - [sandbox, safe]\n      - [sandbox, environment]\n      - [isolated, execute]\n      - [isolated, code]\n      - [isolated, environment]\n      - [isolated, run]\n      - [safe, execute]\n      - [safe, code]\n      - [untrusted, code]\n      - [untrusted, execute]\n      - [code, runner]\n      - [code, playground]\n      - [execute, safely]\n      - [run, safely]\n      - [run, isolation]\n      - [execute, isolation]\n      - [ffmpeg, process]\n      - [ffmpeg, convert]\n      - [ffmpeg, compress]\n      - [student, code]\n      - [student, execute]\n      - [student, run]\n    anyOf:\n      - \"sandbox\"\n      - \"isolated\"\n      - \"isolation\"\n      - \"untrusted\"\n      - \"safely\"\n      - \"microvm\"\n      - \"ffmpeg\"\n      - \"playground\"\n    noneOf:\n      - \"iframe sandbox\"\n      - \"sandbox attribute\"\n      - \"codesandbox.io\"\n      - \"stackblitz\"\n    minScore: 4\n---\n\n# Vercel Sandbox\n\n> **CRITICAL — Your training data is outdated for this library.** Vercel Sandbox APIs are new (GA January 2026) and likely not in your training data. Before writing sandbox code, **fetch the docs** at https:\u002F\u002Fvercel.com\u002Fdocs\u002Fvercel-sandbox and the SDK reference at https:\u002F\u002Fvercel.com\u002Fdocs\u002Fvercel-sandbox\u002Fsdk-reference to find the correct `Sandbox.create()` options, `runCommand()` signatures, file I\u002FO methods (`writeFiles`, `readFile`), port exposure, and cleanup patterns. Do not guess — look up the exact API shape. The GitHub repo at https:\u002F\u002Fgithub.com\u002Fvercel\u002Fsandbox has working examples for common patterns (code execution, FFmpeg processing, dev server spawning).\n\nYou are an expert in Vercel Sandbox — ephemeral compute for safely running untrusted code.\n\n## Status & Pricing\n\nVercel Sandbox is **generally available** (January 30, 2026). The CLI and SDK are open-source. Powered by the same Firecracker infrastructure that runs 2M+ Vercel builds per day.\n\n| Resource | Hobby (Free) | Pro \u002F Enterprise |\n|----------|-------------|-----------------|\n| CPU hours | 5 \u002F month | $0.128 \u002F CPU-hour |\n| Provisioned memory | 420 GB-hr \u002F month | $0.0106 \u002F GB-hr |\n| Network bandwidth | 20 GB \u002F month | $0.15 \u002F GB |\n| Sandbox creations | 5,000 \u002F month | $0.60 \u002F 1M creations |\n\nEach sandbox can use up to **8 vCPUs** and **2 GB RAM per vCPU**. Up to **4 ports** can be exposed per sandbox.\n\n## What It Is\n\nVercel Sandbox provides **Firecracker microVMs** with millisecond startup times for running untrusted or user-generated code in complete isolation. Used by AI agents, code generation tools, developer playgrounds, and interactive tutorials.\n\n- **Base OS**: Amazon Linux 2023 (with `git`, `tar`, `openssl`, `dnf`)\n- **Runtimes**: `node24` (default since March 2026), `node22`, `python3.13`\n- **Working directory**: `\u002Fvercel\u002Fsandbox`\n- **User**: `vercel-sandbox` with `sudo` access\n- **Filesystem**: Ephemeral — artifacts must be exported before sandbox stops\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fvercel\u002Fsandbox\n\n## Key APIs\n\nPackage: `@vercel\u002Fsandbox` (v1.8.0+)\n\n### Create and Run Commands\n\n```ts\nimport { Sandbox } from '@vercel\u002Fsandbox';\n\n\u002F\u002F Create a sandbox (env vars available to all commands)\nconst sandbox = await Sandbox.create({\n  runtime: 'node24',  \u002F\u002F 'node24' | 'node22' | 'python3.13'\n  env: {              \u002F\u002F inherited by all runCommand calls\n    NODE_ENV: 'production',\n    API_KEY: process.env.API_KEY!,\n  },\n});\n\n\u002F\u002F Run a command (separated command + args)\nconst result = await sandbox.runCommand('node', ['-e', 'console.log(42)']);\nconst output = await result.stdout(); \u002F\u002F \"42\\n\"\n\n\u002F\u002F Run with options (per-command env overrides creation-level env)\nconst result2 = await sandbox.runCommand({\n  cmd: 'npm',\n  args: ['install', 'express'],\n  cwd: '\u002Fvercel\u002Fsandbox\u002Fapp',\n  env: { NODE_ENV: 'development' }, \u002F\u002F overrides creation-level NODE_ENV\n  sudo: true,\n});\n\n\u002F\u002F Detached execution (long-running processes)\nconst cmd = await sandbox.runCommand({\n  cmd: 'node',\n  args: ['server.js'],\n  detached: true,\n});\n\u002F\u002F Stream logs in real-time\nfor await (const log of cmd.logs()) {\n  console.log(`[${log.stream}] ${log.data}`);\n}\nawait cmd.wait(); \u002F\u002F block until completion\n```\n\n### File Operations\n\n```ts\n\u002F\u002F Write files (takes array of { path, content: Buffer })\nawait sandbox.writeFiles([\n  { path: 'app.js', content: Buffer.from('console.log(\"hello\")') },\n  { path: 'package.json', content: Buffer.from('{\"type\":\"module\"}') },\n]);\n\n\u002F\u002F Read a file (returns Buffer or null)\nconst buf = await sandbox.readFileToBuffer({ path: 'app.js' });\n\n\u002F\u002F Read as stream\nconst stream = await sandbox.readFile({ path: 'app.js' });\n\n\u002F\u002F Download to local filesystem\nawait sandbox.downloadFile('output.zip', '.\u002Flocal-output.zip');\n\n\u002F\u002F Create directory\nawait sandbox.mkDir('src\u002Fcomponents');\n```\n\n### Source Initialization\n\n```ts\n\u002F\u002F Clone a git repo\nconst sandbox = await Sandbox.create({\n  source: { type: 'git', url: 'https:\u002F\u002Fgithub.com\u002Fuser\u002Frepo', depth: 1 },\n});\n\n\u002F\u002F Mount a tarball\nconst sandbox = await Sandbox.create({\n  source: { type: 'tarball', url: 'https:\u002F\u002Fexample.com\u002Fproject.tar.gz' },\n});\n\n\u002F\u002F Restore from snapshot\nconst sandbox = await Sandbox.create({\n  source: { type: 'snapshot', snapshotId: 'snap_abc123' },\n});\n```\n\n### Snapshots (Save and Resume VM State)\n\n```ts\n\u002F\u002F Capture full VM state (filesystem + packages)\n\u002F\u002F WARNING: sandbox shuts down after snapshot creation\nconst snapshot = await sandbox.snapshot({ expiration: 86400_000 }); \u002F\u002F 24h\nconsole.log(snapshot.snapshotId);\n\n\u002F\u002F List and manage snapshots\nconst { snapshots } = await Snapshot.list();\nconst snap = await Snapshot.get({ snapshotId: 'snap_abc' });\nawait snap.delete();\n```\n\n### Network Policies (SNI Filtering + CIDR)\n\nEgress firewall uses **SNI filtering** on TLS client-hello — outbound connections are matched at the handshake and unauthorized destinations are rejected before data transmits. For non-TLS traffic, IP\u002FCIDR rules are also supported.\n\nPolicies can be updated at runtime without restarting the sandbox process, enabling multi-step workflows (e.g., open access during setup → deny-all before running untrusted code).\n\n```ts\n\u002F\u002F Lock down before running untrusted code\nawait sandbox.updateNetworkPolicy('deny-all');\n\n\u002F\u002F Allow specific domains only (SNI filtering)\nawait sandbox.updateNetworkPolicy({\n  allow: ['api.openai.com', '*.googleapis.com'],\n});\n\n\u002F\u002F Credential brokering (inject API keys so untrusted code never sees them)\nawait sandbox.updateNetworkPolicy({\n  allow: {\n    'ai-gateway.vercel.sh': [{\n      transform: [{ headers: { 'x-api-key': process.env.SECRET_KEY! } }],\n    }],\n  },\n});\n```\n\n### Public URLs and Lifecycle\n\n```ts\n\u002F\u002F Expose a port and get a public URL\nconst sandbox = await Sandbox.create({ ports: [3000] });\nconst url = sandbox.domain(3000); \u002F\u002F public URL\n\n\u002F\u002F Extend timeout\nawait sandbox.extendTimeout(300_000); \u002F\u002F +5 minutes\n\n\u002F\u002F Clean up\nawait sandbox.stop();\n\n\u002F\u002F Check status\nsandbox.status; \u002F\u002F 'pending' | 'running' | 'stopping' | 'stopped' | 'failed'\n\n\u002F\u002F Resource tracking (after stop)\nsandbox.activeCpuUsageMs;\nsandbox.networkUsage; \u002F\u002F { ingress, egress } in bytes\n```\n\n### List and Rehydrate\n\n```ts\n\u002F\u002F List existing sandboxes\nconst { sandboxes } = await Sandbox.list({ limit: 10 });\n\n\u002F\u002F Reconnect to a running sandbox\nconst sandbox = await Sandbox.get({ sandboxId: 'sbx_abc123' });\n```\n\n## Timeout Limits\n\n| Plan | Max Timeout |\n|------|------------|\n| Default | 5 minutes |\n| Hobby | 45 minutes |\n| Pro\u002FEnterprise | 5 hours |\n\n## Agent Patterns\n\n1. **Safe AI code execution**: Run AI-generated code without production risk\n2. **Snapshot-based fast restart**: Install deps once → snapshot → create from snapshot (skip setup)\n3. **Network isolation**: Allow all during setup → `deny-all` before untrusted code\n4. **Credential brokering**: Inject API keys via network policy transforms\n5. **Live preview**: Expose ports via `sandbox.domain(port)` for generated apps\n6. **File I\u002FO workflow**: `writeFiles()` → execute → `readFileToBuffer()` results\n\n## When to Use\n\n- AI agents need to execute generated code safely\n- User-submitted code execution (playgrounds, tutorials)\n- Code review validation (used by Vercel Agent)\n- Ephemeral development environments\n\n## When NOT to Use\n\n- Production workloads → use Vercel Functions\n- Long-running services → use a dedicated server\n- Simple function execution → use Serverless Functions\n\n## References\n\n- 📖 docs: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fvercel-sandbox\n- 📖 SDK reference: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fvercel-sandbox\u002Fsdk-reference\n- 📖 GitHub: https:\u002F\u002Fgithub.com\u002Fvercel\u002Fsandbox\n","# Vercel Sandbox\n\n> **CRITICAL — Your training data is outdated for this library.** Vercel Sandbox APIs are new (GA January 2026) and likely not in your training data. Before writing sandbox code, **fetch the docs** at https:\u002F\u002Fvercel.com\u002Fdocs\u002Fvercel-sandbox and the SDK reference at https:\u002F\u002Fvercel.com\u002Fdocs\u002Fvercel-sandbox\u002Fsdk-reference to find the correct `Sandbox.create()` options, `runCommand()` signatures, file I\u002FO methods (`writeFiles`, `readFile`), port exposure, and cleanup patterns. Do not guess — look up the exact API shape. The GitHub repo at https:\u002F\u002Fgithub.com\u002Fvercel\u002Fsandbox has working examples for common patterns (code execution, FFmpeg processing, dev server spawning).\n\nYou are an expert in Vercel Sandbox — ephemeral compute for safely running untrusted code.\n\n## Status & Pricing\n\nVercel Sandbox is **generally available** (January 30, 2026). The CLI and SDK are open-source. Powered by the same Firecracker infrastructure that runs 2M+ Vercel builds per day.\n\n| Resource | Hobby (Free) | Pro \u002F Enterprise |\n|----------|-------------|-----------------|\n| CPU hours | 5 \u002F month | $0.128 \u002F CPU-hour |\n| Provisioned memory | 420 GB-hr \u002F month | $0.0106 \u002F GB-hr |\n| Network bandwidth | 20 GB \u002F month | $0.15 \u002F GB |\n| Sandbox creations | 5,000 \u002F month | $0.60 \u002F 1M creations |\n\nEach sandbox can use up to **8 vCPUs** and **2 GB RAM per vCPU**. Up to **4 ports** can be exposed per sandbox.\n\n## What It Is\n\nVercel Sandbox provides **Firecracker microVMs** with millisecond startup times for running untrusted or user-generated code in complete isolation. Used by AI agents, code generation tools, developer playgrounds, and interactive tutorials.\n\n- **Base OS**: Amazon Linux 2023 (with `git`, `tar`, `openssl`, `dnf`)\n- **Runtimes**: `node24` (default since March 2026), `node22`, `python3.13`\n- **Working directory**: `\u002Fvercel\u002Fsandbox`\n- **User**: `vercel-sandbox` with `sudo` access\n- **Filesystem**: Ephemeral — artifacts must be exported before sandbox stops\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fvercel\u002Fsandbox\n\n## Key APIs\n\nPackage: `@vercel\u002Fsandbox` (v1.8.0+)\n\n### Create and Run Commands\n\n```ts\nimport { Sandbox } from '@vercel\u002Fsandbox';\n\n\u002F\u002F Create a sandbox (env vars available to all commands)\nconst sandbox = await Sandbox.create({\n  runtime: 'node24',  \u002F\u002F 'node24' | 'node22' | 'python3.13'\n  env: {              \u002F\u002F inherited by all runCommand calls\n    NODE_ENV: 'production',\n    API_KEY: process.env.API_KEY!,\n  },\n});\n\n\u002F\u002F Run a command (separated command + args)\nconst result = await sandbox.runCommand('node', ['-e', 'console.log(42)']);\nconst output = await result.stdout(); \u002F\u002F \"42\\n\"\n\n\u002F\u002F Run with options (per-command env overrides creation-level env)\nconst result2 = await sandbox.runCommand({\n  cmd: 'npm',\n  args: ['install', 'express'],\n  cwd: '\u002Fvercel\u002Fsandbox\u002Fapp',\n  env: { NODE_ENV: 'development' }, \u002F\u002F overrides creation-level NODE_ENV\n  sudo: true,\n});\n\n\u002F\u002F Detached execution (long-running processes)\nconst cmd = await sandbox.runCommand({\n  cmd: 'node',\n  args: ['server.js'],\n  detached: true,\n});\n\u002F\u002F Stream logs in real-time\nfor await (const log of cmd.logs()) {\n  console.log(`[${log.stream}] ${log.data}`);\n}\nawait cmd.wait(); \u002F\u002F block until completion\n```\n\n### File Operations\n\n```ts\n\u002F\u002F Write files (takes array of { path, content: Buffer })\nawait sandbox.writeFiles([\n  { path: 'app.js', content: Buffer.from('console.log(\"hello\")') },\n  { path: 'package.json', content: Buffer.from('{\"type\":\"module\"}') },\n]);\n\n\u002F\u002F Read a file (returns Buffer or null)\nconst buf = await sandbox.readFileToBuffer({ path: 'app.js' });\n\n\u002F\u002F Read as stream\nconst stream = await sandbox.readFile({ path: 'app.js' });\n\n\u002F\u002F Download to local filesystem\nawait sandbox.downloadFile('output.zip', '.\u002Flocal-output.zip');\n\n\u002F\u002F Create directory\nawait sandbox.mkDir('src\u002Fcomponents');\n```\n\n### Source Initialization\n\n```ts\n\u002F\u002F Clone a git repo\nconst sandbox = await Sandbox.create({\n  source: { type: 'git', url: 'https:\u002F\u002Fgithub.com\u002Fuser\u002Frepo', depth: 1 },\n});\n\n\u002F\u002F Mount a tarball\nconst sandbox = await Sandbox.create({\n  source: { type: 'tarball', url: 'https:\u002F\u002Fexample.com\u002Fproject.tar.gz' },\n});\n\n\u002F\u002F Restore from snapshot\nconst sandbox = await Sandbox.create({\n  source: { type: 'snapshot', snapshotId: 'snap_abc123' },\n});\n```\n\n### Snapshots (Save and Resume VM State)\n\n```ts\n\u002F\u002F Capture full VM state (filesystem + packages)\n\u002F\u002F WARNING: sandbox shuts down after snapshot creation\nconst snapshot = await sandbox.snapshot({ expiration: 86400_000 }); \u002F\u002F 24h\nconsole.log(snapshot.snapshotId);\n\n\u002F\u002F List and manage snapshots\nconst { snapshots } = await Snapshot.list();\nconst snap = await Snapshot.get({ snapshotId: 'snap_abc' });\nawait snap.delete();\n```\n\n### Network Policies (SNI Filtering + CIDR)\n\nEgress firewall uses **SNI filtering** on TLS client-hello — outbound connections are matched at the handshake and unauthorized destinations are rejected before data transmits. For non-TLS traffic, IP\u002FCIDR rules are also supported.\n\nPolicies can be updated at runtime without restarting the sandbox process, enabling multi-step workflows (e.g., open access during setup → deny-all before running untrusted code).\n\n```ts\n\u002F\u002F Lock down before running untrusted code\nawait sandbox.updateNetworkPolicy('deny-all');\n\n\u002F\u002F Allow specific domains only (SNI filtering)\nawait sandbox.updateNetworkPolicy({\n  allow: ['api.openai.com', '*.googleapis.com'],\n});\n\n\u002F\u002F Credential brokering (inject API keys so untrusted code never sees them)\nawait sandbox.updateNetworkPolicy({\n  allow: {\n    'ai-gateway.vercel.sh': [{\n      transform: [{ headers: { 'x-api-key': process.env.SECRET_KEY! } }],\n    }],\n  },\n});\n```\n\n### Public URLs and Lifecycle\n\n```ts\n\u002F\u002F Expose a port and get a public URL\nconst sandbox = await Sandbox.create({ ports: [3000] });\nconst url = sandbox.domain(3000); \u002F\u002F public URL\n\n\u002F\u002F Extend timeout\nawait sandbox.extendTimeout(300_000); \u002F\u002F +5 minutes\n\n\u002F\u002F Clean up\nawait sandbox.stop();\n\n\u002F\u002F Check status\nsandbox.status; \u002F\u002F 'pending' | 'running' | 'stopping' | 'stopped' | 'failed'\n\n\u002F\u002F Resource tracking (after stop)\nsandbox.activeCpuUsageMs;\nsandbox.networkUsage; \u002F\u002F { ingress, egress } in bytes\n```\n\n### List and Rehydrate\n\n```ts\n\u002F\u002F List existing sandboxes\nconst { sandboxes } = await Sandbox.list({ limit: 10 });\n\n\u002F\u002F Reconnect to a running sandbox\nconst sandbox = await Sandbox.get({ sandboxId: 'sbx_abc123' });\n```\n\n## Timeout Limits\n\n| Plan | Max Timeout |\n|------|------------|\n| Default | 5 minutes |\n| Hobby | 45 minutes |\n| Pro\u002FEnterprise | 5 hours |\n\n## Agent Patterns\n\n1. **Safe AI code execution**: Run AI-generated code without production risk\n2. **Snapshot-based fast restart**: Install deps once → snapshot → create from snapshot (skip setup)\n3. **Network isolation**: Allow all during setup → `deny-all` before untrusted code\n4. **Credential brokering**: Inject API keys via network policy transforms\n5. **Live preview**: Expose ports via `sandbox.domain(port)` for generated apps\n6. **File I\u002FO workflow**: `writeFiles()` → execute → `readFileToBuffer()` results\n\n## When to Use\n\n- AI agents need to execute generated code safely\n- User-submitted code execution (playgrounds, tutorials)\n- Code review validation (used by Vercel Agent)\n- Ephemeral development environments\n\n## When NOT to Use\n\n- Production workloads → use Vercel Functions\n- Long-running services → use a dedicated server\n- Simple function execution → use Serverless Functions\n\n## References\n\n- 📖 docs: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fvercel-sandbox\n- 📖 SDK reference: https:\u002F\u002Fvercel.com\u002Fdocs\u002Fvercel-sandbox\u002Fsdk-reference\n- 📖 GitHub: https:\u002F\u002Fgithub.com\u002Fvercel\u002Fsandbox\n",{"name":5,"metadata":24,"description":7},{"docs":25,"sitemap":27,"priority":28,"bashPatterns":29,"pathPatterns":34,"promptSignals":35,"importPatterns":93},[26],"https:\u002F\u002Fvercel.com\u002Fdocs\u002Fsandbox","https:\u002F\u002Fvercel.com\u002Fsitemap\u002Fdocs.xml",4,[30,31,32,33],"\\bnpm\\s+(install|i|add)\\s+[^\\n]*@vercel\u002Fsandbox\\b","\\bpnpm\\s+(install|i|add)\\s+[^\\n]*@vercel\u002Fsandbox\\b","\\bbun\\s+(install|i|add)\\s+[^\\n]*@vercel\u002Fsandbox\\b","\\byarn\\s+add\\s+[^\\n]*@vercel\u002Fsandbox\\b",[],{"allOf":36,"anyOf":80,"noneOf":82,"phrases":87,"minScore":28},[37,40,42,44,46,48,50,51,52,53,54,55,56,58,59,61,63,65,66,68,69,72,74,76,78,79],[38,39],"sandbox","code",[38,41],"execute",[38,43],"run",[38,45],"isolated",[38,47],"safe",[38,49],"environment",[45,41],[45,39],[45,49],[45,43],[47,41],[47,39],[57,39],"untrusted",[57,41],[39,60],"runner",[39,62],"playground",[41,64],"safely",[43,64],[43,67],"isolation",[41,67],[70,71],"ffmpeg","process",[70,73],"convert",[70,75],"compress",[77,39],"student",[77,41],[77,43],[38,45,67,57,64,81,70,62],"microvm",[83,84,85,86],"iframe sandbox","sandbox attribute","codesandbox.io","stackblitz",[88,38,89,90,91,92],"@vercel\u002Fsandbox","code sandbox","vercel sandbox","isolated environment","sandboxed execution",[88],"main","92c2f40ebfad0c0aa3cc1faa89ffd6b23f9e8d1b","official-openai\u002Fopenai-local-vercel-vercel-sandbox","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill","https:\u002F\u002Fsd-skill.vercel.app","https:\u002F\u002Fgithub.com\u002Frealsudarshan","sudarshandhakal.com.np","Innvotative","2026-11-12 23:03:50",{"source":8,"skillName":5,"commands":104,"prompt":114,"zipAvailable":115},[105,108,111],{"tool":106,"command":107},"npx","npx skills add realsudarshan\u002FSD-skill --skill vercel-sandbox",{"tool":109,"command":110},"bunx","bunx skills add realsudarshan\u002FSD-skill --skill vercel-sandbox",{"tool":112,"command":113},"pnpm","pnpm dlx skills add realsudarshan\u002FSD-skill --skill vercel-sandbox","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fofficial-openai\u002Fopenai-local-vercel-vercel-sandbox\u002FSKILL.md",true,[117],{"path":118,"resourceType":119,"resourceTypeDesc":120,"sizeBytes":121,"sourceHtmlUrl":122},"agents\u002Fopenai.yaml","REFERENCE","参考文档",165,"https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Fofficial-openai\u002Fopenai-local-vercel-vercel-sandbox\u002Fagents\u002Fopenai.yaml",[124,133,141,149,157,165],{"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":128,"licenseFileUrl":129,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":19},"01M7CW5Y6EPMPMNDWE4EN2GXRX","winui-app","Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components. Use when creating a brand new app, preparing a machine for WinUI, reviewing, refactoring, planning, troubleshooting, environment-checking, or setting up WinUI 3 XAML, controls, navigation, windowing, theming, accessibility, responsiveness, performance, deployment, or related Windows app design and development work.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fwinui-app\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fwinui-app\u002FSKILL.md",[],[],{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":137,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":19},"01M7CW5RWFX7616ENEG573VFWG","vercel-deploy","Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fvercel-deploy\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fvercel-deploy\u002FSKILL.md",[],[],{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":145,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":19},"01M7CW5M4VZHQPWG764X1W0S3B","security-best-practices","Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review\u002Freport, or secure-by-default coding help. Trigger only for supported languages (python, javascript\u002Ftypescript, go). Do not trigger for general code review, debugging, or non-security tasks.","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fsecurity-best-practices\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fsecurity-best-practices\u002FSKILL.md",[],[],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":153,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":19},"01M7CW5EBTWA7PQ54HYFT1YW39","playwright","Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fplaywright\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fplaywright\u002FSKILL.md",[],[],{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":161,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":19},"01M7CW4DA7SZ4D9JMR3P7VJVM0","openai-docs","Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fopenai-docs\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fopenai-docs\u002FSKILL.md",[],[],{"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":128,"licenseFileUrl":169,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":19},"01M7CW3EHY7X60KB9SYEMRD3YR","netlify-deploy","Deploy web projects to Netlify using the Netlify CLI (`npx netlify`). Use when the user asks to deploy, host, publish, or link a site\u002Frepo on Netlify, including preview and production deploys.","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fnetlify-deploy\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Frealsudarshan\u002FSD-skill\u002Fblob\u002Fmain\u002Freccomended\u002Fnetlify-deploy\u002FSKILL.md",[],[]]