Agent Skills
› langchain-ai/design-agent
› design-agent-troubleshoot
design-agent-troubleshoot
GitHub用于诊断和修复 Design Agent 故障,涵盖模型调用、部署及渲染异常。通过运行诊断工具、测试连接并对照症状表定位问题,结合日志与 LangSmith 追踪分析原因,指导用户采取相应修复措施。
触发场景
Design Agent 命令报错或无响应
需要排查模型连接、部署或渲染失败原因
查看系统日志或追踪以定位错误
安装
npx skills add langchain-ai/design-agent --skill design-agent-troubleshoot -g -y
SKILL.md
Frontmatter
{
"name": "design-agent-troubleshoot",
"description": "Diagnose Design Agent when something fails. Setup, a render, a deploy, Slack or a model call. Run doctor and the connection tests, read logs and traces, match the symptom to its fix, and never print credentials. Use when a command errors, a reply never comes, or a file looks wrong."
}
Troubleshoot Design Agent
Report missing settings by name and never paste a key, token or .env line.
uv run design-agent doctor(add--jsonto parse it) checks every model role, keys, the brand, the sandbox, MDA declarations, MCP and Paper. Fix what it names first.- Real calls, a few cents each:
uv run design-agent test model,test sandbox,test paper,test slack,test db. - Match the symptom:
| Symptom | Fix |
|---|---|
demo needs a sandbox |
start Docker, then uv run design-agent sandbox build |
| A render is missing a font | uv run design-agent fonts verify; family in fonts.toml must be the name inside the file |
| Off-brand colours or a failed brand check | uv run design-agent brand validate, then brand css |
| "The connection to the model stalled" or "stayed unavailable" | check the provider's status, then reply continue in the thread |
| Background news arrives a minute or two late on MDA | expected: MDA schedules land on the next minute |
| "A restart may have stopped…" | a deploy or restart stopped helpers; ask the agent to resume them |
| Paper "not connected" | Paper Desktop is closed or the bridge is down; boards still render in the sandbox |
The sandbox bake runs out of disk on mda deploy |
uv run design-agent sandbox publish first |
| "Context Hub only accepts UTF-8 text files" | move the skill's binary files to skill-binaries/<skill>/ |
| "source archive … exceeds the 200 MB limit" | clear old renders in workspace/out/ |
| An MCP server is missing | the startup log names the one that failed; the rest keep working |
- Logs:
uv run mda logson MDA;docker compose -f deploy/self-host/compose.yaml logs apiwhen self-hosted. Logs carry exception classes, never provider messages or keys. - Traces: every run is traced in LangSmith (an MDA deployment's project is
<deployment>-production). Follow a bad file back to the skills read, tools called and checks run, with the langsmith-trace skill. API runs attach delivered files to the trace. The deployed agent can read its own traces too (list_traces,read_trace): ask it in the thread what went wrong. - A real bug: reproduce it with a failing test before changing code, then follow
AGENTS.md.
More: Operations.
版本历史
- 8134d7c 当前 2026-11-20 21:40


