debug-zoom — Claude Code skill: what it does, how to install
Debug Zoom integration issues across auth, APIs, webhooks, SDKs, and MCP transports with targeted verification steps.
npx skills add anthropics/knowledge-work-plugins --skill debug-zoom -a claude-codeWhat debug-zoom does
The skill isolates failure points in Zoom integrations without requiring manual searches through documentation. It pinpoints whether a breakdown occurs in authentication, API requests, webhook handling, SDK initialization, media sessions, or MCP transport.
The workflow begins by requesting minimal evidence, such as the exact error message, payload, or code path. Missing details stall debugging. Once evidence is provided, the skill ranks plausible causes and outlines a verification checklist to confirm the fix.
What it helps with
- isolate Zoom authentication and token failures
- diagnose broken API calls and webhook deliveries
- troubleshoot SDK initialization and MCP transport issues
- generate a verification checklist to confirm the fix
Example prompts for the agent
- /debug-zoom auth error when calling Zoom API
- /debug-zoom webhook events are not delivered
- /debug-zoom MCP transport fails during handshake
How to install debug-zoom
1Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill debug-zoom -a claude-code2Manually: put the files in place
~/.claude/skills/debug-zoom/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/debug-zoom/
1Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill debug-zoom -a codex2Manually: put the files in place
.agents/skills/debug-zoom/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill debug-zoom -a cursor2Manually: put the files in place
.cursor/skills/debug-zoom/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install anthropics/knowledge-work-plugins debug-zoom2Manually: put the files in place
.github/skills/debug-zoom/SKILL.md1Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill debug-zoom -a gemini-cli2Platform CLI
gemini skills install https://github.com/anthropics/knowledge-work-plugins --path partner-built/zoom-plugin/skills/debug-zoomManually: put the files in place
.devin/skills/debug-zoom/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add anthropics/knowledge-work-plugins --skill debug-zoom -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set89
The whole set →Similar
Questions about debug-zoom
How do I install debug-zoom in Claude Code?
Run npx skills add anthropics/knowledge-work-plugins --skill debug-zoom -a claude-code in your terminal. This registers the skill for Claude Code.
What does debug-zoom do?
It analyzes Zoom integration failures across auth, API, webhook, SDK, and MCP layers, returning ranked hypotheses and verification steps.
What information does debug-zoom require?
The skill asks for missing evidence, including the exact error text, platform name, request or response payloads, event data, or failing code path.
Source text
SKILL.md · Apache-2.0
--- 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)
© anthropics · Apache-2.0 · anthropics/knowledge-work-plugins