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.
Install with the open skills CLI (global, non-interactive — available in every Claude Code session):
npx skills add anthropics/knowledge-work-plugins --skill "debug-zoom" -g -a claude-code -yOr manually — copy the SKILL.md below into:
~/.claude/skills/debug-zoom/SKILL.md---
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](../../CONNECTORS.md).
Debug Zoom auth, API, webhook, SDK, or MCP issues without wandering through the entire docs set.
## Usage
```text
/debug-zoom $ARGUMENTS
```
## Workflow
1. Identify the failing layer: auth, API request, webhook, SDK init, media/session behavior, or MCP transport.
2. Ask for the minimum missing evidence: exact error, platform, request/response, event payload, or code path.
3. Produce 2-4 plausible causes ranked by likelihood.
4. Route to the most relevant deep references in `skills/`.
5. 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
- [debug-zoom-integration](../debug-zoom-integration/SKILL.md)
- [setup-zoom-oauth](../setup-zoom-oauth/SKILL.md)
- [design-mcp-workflow](../design-mcp-workflow/SKILL.md)
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when implementing any feature or bugfix, before writing implementation code