Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
vercel/vercel-plugin
Comprehensive Vercel ecosystem plugin — relational knowledge graph, skills for every major product, specialized agents, and Vercel conventions. Turns any AI agent into a Vercel expert.
根据公开文档整理，未运行实测；费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
上手GET STARTED
npx plugins add vercel/vercel-plugin选择与你的环境对应的方式。命令来自项目文档，未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查，未执行项目代码；扫描没有命中，不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01执行 Shell 命令Runs shell commands.claude/skills/benchmark-agents/SKILL.md
**Never use `claude --print`, eval scripts, or `Bun.spawn(["claude", ...])`**. These do not work because:
02读写本地文件Reads and writes local files.claude/skills/benchmark-sandbox/SKILL.md
| **Artifact access** | Direct filesystem (`~/.claude/debug/`) | `sandbox.readFile()` / poll via `runCommand` |
03控制浏览器Controls a browserskills/access-protected-vercel-deployment/SKILL.md
Then continue the normal browser workflow in the same session. For Playwright or another browser driver, set the same header in the browser
04读取 API KeyReads an API keyskills/ai-gateway/SKILL.md
- Use an **AI Gateway API key** for local scripts, CI, external servers, and non-Vercel deployments. Store it in `AI_GATEWAY_API_KEY` and ne
05读取 API KeyReads an API keyskills/auth/SKILL.md
clientSecret: process.env.GITHUB_CLIENT_SECRET!,
06控制浏览器Controls a browserskills/deployments-cicd/SKILL.md
# ... checkout, install, bypass header in playwright.config.ts (see references/deployment-checks.md) ...
07需要系统权限Needs system permissionsskills/vercel-sandbox/SKILL.md
Commands run as a **non-root** user (`ubuntu`, in the sudo group) by default; pass `sudo: true` for root.
08执行 Shell 命令Runs shell commandsskills/vercel-sandbox/SKILL.md
Do **not** use in-process sandboxes like `vm2` (known escapes) or `child_process`/`eval` for untrusted code. Those share your process; a San
09需要系统权限Needs system permissionsskills/vercel-sandbox/upstream/SKILL.md
Commands run as a **non-root** user (`ubuntu`, in the sudo group) by default; pass `sudo: true` for root.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
26 OCT 202626 OCT 2026
增长GROWTH
+4.1%+4.1%
315 → 328 stars · 13 个快照315 → 328 stars · 13 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
2 条外部提及2 external mentions
状态STATUS
持续活跃Active
HN_STORY · 8 points · 6 comments
HN_STORY · 2 points · 1 comments
依赖：Dependencies:detect-agent, minisearch
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
},
{
"agent": "codex",
"evidence": "readme: …pilot-cli) | Supported | | [OpenAI Codex](https://openai.com/index/cod…"
},
{
"agent": "opencode",
"evidence": "readme: …| Supported | | [OpenCode](https://opencode.ai) 2…"
},
{
"agent": "copilot",
"evidence": "readme: …| Supported | | [GitHub Copilot CLI](https://github.com/githu…"
}
],
"apiKey": "API key from macOS Keychain (`ANTHROPIC_AUTH_TOKEN` — a `vck_*` Vercel Claude Key for AI G",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 3,
"dev-tools": 1,
"indie-web": 0,
"skill-agent": 1,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": null,
"skillMdTotal": 55,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 3,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "55 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 298 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": ".mcp.json (configures servers it uses)",
"weight": 0.3
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".claude/skills/benchmark-agents/SKILL.md",
".claude/skills/benchmark-e2e/SKILL.md",
".claude/skills/benchmark-sandbox/SKILL.md",
".claude/skills/benchmark-testing/SKILL.md",
".claude/skills/plugin-audit/SKILL.md",
".claude/skills/release/SKILL.md",
".claude/skills/vercel-plugin-eval/SKILL.md",
"skills/access-protected-vercel-deployment/SKILL.md",
"skills/ai-gateway/SKILL.md",
"skills/ai-sdk/SKILL.md",
"skills/ai-sdk/upstream/SKILL.md",
"skills/auth/SKILL.md",
"skills/bootstrap/SKILL.md",
"skills/build-agents/SKILL.md",
"skills/cdn-caching/SKILL.md",
"skills/chat-sdk/SKILL.md",
"skills/chat-sdk/upstream/SKILL.md",
"skills/create-a-backend/SKILL.md",
"skills/custom-metrics/SKILL.md",
"skills/daemons/SKILL.md",
"skills/deployments-cicd/SKILL.md",
"skills/domains/SKILL.md",
"skills/env-vars/SKILL.md",
"skills/eve/SKILL.md",
"skills/eve/upstream/SKILL.md",
"skills/flags-sdk/SKILL.md",
"skills/flags-sdk/upstream/SKILL.md",
"skills/is-agentic/SKILL.md",
"skills/is-agentic/upstream/SKILL.md",
"skills/knowledge-update/SKILL.md",
"skills/marketplace/SKILL.md",
"skills/microfrontends/SKILL.md",
"skills/offload-to-sandbox/SKILL.md",
"skills/queues/SKILL.md",
"skills/react-best-practices/SKILL.md",
"skills/react-best-practices/upstream/SKILL.md",
"skills/routing-middleware/SKILL.md",
"skills/runtime-cache/SKILL.md",
"skills/vercel-agent/SKILL.md",
"skills/vercel-cli/SKILL.md",
"skills/vercel-cli/upstream/SKILL.md",
"skills/vercel-connect/SKILL.md",
"skills/vercel-firewall/SKILL.md",
"skills/vercel-flags/SKILL.md",
"skills/vercel-flags/upstream/SKILL.md",
"skills/vercel-functions/SKILL.md",
"skills/vercel-sandbox/SKILL.md",
"skills/vercel-sandbox/upstream/SKILL.md",
"skills/vercel-schedules/SKILL.md",
"skills/vercel-services/SKILL.md",
"skills/vercel-storage/SKILL.md",
"skills/vercel-tracing/SKILL.md",
"skills/verification/SKILL.md",
"skills/workflow/SKILL.md",
"skills/workflow/upstream/SKILL.md"
],
"skillMdFetched": 55
}