Agent Skills
› anthropics/knowledge-work-plugins
› debug-zoom
debug-zoom
GitHub用于调试 Zoom 集成故障，定位认证、API、Webhook 或 SDK 等层级的失败点。通过收集证据生成按可能性排序的假设列表，提供针对性修复步骤和验证清单，辅助快速解决集成问题。
触发场景
Zoom 集成出现认证错误
API 请求或 Webhook 回调异常
SDK 初始化或 MCP 传输行为失败
安装
npx skills add anthropics/knowledge-work-plugins --skill debug-zoom -g -y
SKILL.md
Frontmatter
{
"name": "debug-zoom",
"description": "Debug a broken Zoom integration by isolating the failure point and routing into the right Zoom references. Use when auth, API, webhook, SDK, or MCP behavior is failing and you need a ranked hypothesis list plus verification steps.",
"argument-hint": "<symptoms, error, or failing flow>"
}
/debug-zoom
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Debug Zoom auth, API, webhook, SDK, or MCP issues without wandering through the entire docs set.
Usage
/debug-zoom $ARGUMENTS
Workflow
- Identify the failing layer: auth, API request, webhook, SDK init, media/session behavior, or MCP transport.
- Ask for the minimum missing evidence: exact error, platform, request/response, event payload, or code path.
- Produce 2-4 plausible causes ranked by likelihood.
- Route to the most relevant deep references in
skills/. - Give a short verification plan so the user can confirm the fix.
Output
- Most likely failure layer
- Ranked hypotheses
- Targeted fix steps
- Verification checklist
- Relevant skill links
Related Skills
版本历史
- 6f13415 当前 2026-07-05 18:31
