跳到正文
cccskills
Claude 官方免费在 GitHub 公开

verify

Verify changes to the copilot-kit-ag-ui demo by building and running its server. Check API routing, cross-origin access settings, and build configuration, then use real credentials to confirm that a requested chart appears.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Build and drive the copilot-kit-ag-ui demo to verify changes end-to-end.

anthropics/claude-quickstarts
查看安装方法

适用场景

  • Checking server routing after changes
  • Testing API wiring without real Anthropic credentials
  • Checking which website origins can access the server
  • Confirming that a visual tool renders a chart

包含的文件（1）

  • SKILL.md1.9 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

Verifying changes to this demo

Build and drive the real server. npm run typecheck is CI's job, not evidence.

Without Anthropic credentials or provisioned agents

The server boots and serves everything except a live agent turn with stub IDs:

npm install && npm run build
ANTHROPIC_API_KEY=sk-ant-test ANTHROPIC_ENVIRONMENT_ID=env_x \
  ANTHROPIC_AGENT_ID=agent_x ANTHROPIC_AGENT_VERSION=1 PORT=8799 npm start

Probes that exercise the wiring:

  • GET :8799/ returns the built web/dist/index.html (there is no SPA catch-all, so unknown paths 404).
  • GET :8799/api/copilotkit/info lists the registered agents, confirming agent id and class registration without an API call.
  • POST :8799/api/copilotkit/agent/financial-assistant/run with an AG-UI body ({"threadId":"t1","runId":"r1","messages":[{"id":"m1","role":"user","content":"hi"}],"state":{},"tools":[],"context":[],"forwardedProps":{}}) reaches the AG-UI adapter and fails with a 401 from Anthropic. That 401 in the SSE RUN_ERROR proves the full route-to-SDK path.
  • CORS: send OPTIONS with an Origin header. With ALLOWED_ORIGINS set, allowed origins get Access-Control-Allow-Origin echoed and others get none.
  • VITE_COPILOT_RUNTIME_URL=... npm run build then grep web/dist/assets for the URL to confirm build-time baking.

With real credentials

ant apply agents environments once, npm run dev, open http://localhost:5173, send a prompt that triggers a visual tool ("show me a growth projection for $500/month at 7%") and confirm the chart renders inline.

Gotchas

  • Boot requires agent identity: either claude-lock.json (from ant apply agents environments) or the three ANTHROPIC_* ID env vars. Missing both is a deliberate boot failure.
  • Static serving only activates when web/dist exists, so run npm run build before npm start probes.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护，适用 Google 的隐私权政策和服务条款。

同一仓库的技能

first-run

Claude 官方免费

Guide a first computer-use agent run from environment checks to a browser-only task and a viewer of the run history. Explain each stage so users can understand the output and review screenshots afterward.

中文简介正在准备中。当前显示英语简介。

  • Checking the environment before a first agent run
  • Trying browser automation without moving the mouse or keyboard
  • Reviewing screenshots and prompts from a completed run
anthropics/claude-quickstarts1.9万2026年10月9日 更新

verify

Claude 官方免费

Build and run computer-use-demo in Docker, then use Playwright to test its Streamlit interface without opening a visible browser. Save conversation transcripts, API exchanges, and screenshots to inspect behavior after changes.

中文简介正在准备中。当前显示英语简介。

  • Checking the interface after changing computer-use-demo
  • Testing combinations of models and tool versions
  • Checking Thinking settings and model changes during a session
anthropics/claude-quickstarts1.9万2026年10月9日 更新

查看 anthropics 的全部技能

报告此技能的问题