Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot official · Anthropic

probe-sdk — Claude Code skill: what it does, how to install

Reference skill for the Zoom Probe SDK: checks browser compatibility, media permissions, audio or video diagnostics and network readiness before users join a meeting.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add anthropics/knowledge-work-plugins --skill probe-sdk -a claude-code
Open on GitHub

What probe-sdk does

probe-sdk is a reference skill for the Zoom Probe SDK covering preflight checks before a session: browser compatibility, media permissions, audio and video diagnostics, network readiness. It is not user-invocable; an agent reaches it after routing to a preflight workflow.

The skill documents a lifecycle: initialize Prober/Reporter, request media permissions and enumerate devices, run targeted checks diagnoseAudio and diagnoseVideo, run a comprehensive network diagnostic via startToDiagnose while streaming stats to the UI, then produce a report and clean up with cleanup. Listed scenarios include a pre-join diagnostics page before a Meeting SDK join, a support workflow that captures a structured report, device certification for kiosks, and browser capability gating for advanced media features.

If the task needs an actual meeting join, the skill routes to meeting-sdk; for custom real-time session UX it routes to video-sdk, and for backend handling of events and reports it chains to rivet-sdk, oauth and rest-api.

What it helps with

  • check browser compatibility before a call
  • request camera and microphone access and enumerate devices
  • diagnose audio and video before joining a meeting
  • score network readiness and produce a diagnostic report
  • certify devices for kiosk or controlled endpoints

Example prompts for the agent

  • Check browser compatibility with Zoom Probe SDK before the call
  • Run a preflight check on the user's media devices
  • Run a network diagnostic before joining the meeting

How to install probe-sdk

1Skills CLI (Vercel)

npx skills add anthropics/knowledge-work-plugins --skill probe-sdk -a claude-code

2Manually: put the files in place

~/.claude/skills/probe-sdk/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/probe-sdk/

From the same set133

The whole set →
data-visualization official anthropics Selects chart types based on data structure and produces Python visualization code in matplotlib, seaborn, and plotly. Useful for reports and research figures. Claude Code CX Codex Cursor +1 13,700installs documentation official anthropics A skill for technical writing that drafts READMEs, API references, runbooks, architecture docs and onboarding guides. Useful when the code exists but the description does not. Claude Code CX Codex Cursor +1 10,300installs build-dashboard official anthropics Builds a self-contained HTML dashboard with Chart.js charts, KPI cards, and filterable tables. Useful for turning raw data or queries into a standalone browser report. Claude Code CX Codex Cursor +1 9,100installs memory-management official anthropics This skill organizes workplace shorthand, names, and project details into files an agent can consult. It fits projects where requests rely on an internal vocabulary and shared context. Claude Code CX Codex Cursor +1 7,400installs task-management official anthropics Tracks commitments, active work, and follow-ups in a local TASKS.md file. Useful when managing project to-dos directly from the AI coding chat. Claude Code CX Codex Cursor +1 7,200installs architecture official anthropics Writes an Architecture Decision Record or reviews a system design: options, trade-offs, consequences. Useful when you have to pick between technologies. Claude Code CX Codex Cursor +1 6,700installs knowledge-synthesis official anthropics Merges search results across chats, emails, and documents into deduplicated answers with source attribution. Flags conflicting facts and scores source reliability. Claude Code CX Codex Cursor +1 6,400installs testing-strategy official anthropics This skill designs testing strategies and test plans for a project. Use it when you need test types, coverage goals, or gaps in existing checks. Claude Code CX Codex Cursor +1 6,400installs

Similar

nav-tieout official anthropics Recomputes an LP capital account from the fund's NAV pack components. Flags mismatches on the generated LP statement before distribution. Claude Code CX Codex Cursor +1 1,200installs multi-reviewer-patterns Seth Hobson This skill coordinates parallel reviews across code-quality dimensions and merges the results into one report. Use it when a change needs several review angles. Claude Code CX Codex Cursor 9,800installs pua-loop tanweai This skill runs iterative verification loops with explicit commands and stop conditions. Use it when an agent must check its work before finishing. Claude Code CX Codex Cursor +1 1,800installs vue-testing-best-practices github.com/vuejs-ai Skill offering Vue 3 testing patterns and best practices. It helps configure Vitest and write blackbox component tests without brittle assertions. Claude Code CX Codex Cursor +1 13,600installs argent-tv-interact software-mansion Controls and inspects TV apps on Apple TV, Android TV, and Fire TV via argent. It inspects UI focus, executes D-pad remote navigation, inputs text, and captures screen images. Claude Code CX Codex Cursor +1 20,800installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs design-taste-frontend Leonxlnx This skill directs the design of public pages and work screens, then checks the result in a browser through screenshots. Use it when an interface feels generic or unfinished. Claude Code CX Codex Cursor +1 673,100installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs

Questions about probe-sdk

How to install probe-sdk in Claude Code?

Run npx skills add anthropics/knowledge-work-plugins --skill probe-sdk -a claude-code. The skill will then be available at ~/.claude/skills/probe-sdk/SKILL.md.

What does probe-sdk do?

It is a reference skill for the Zoom Probe SDK that covers browser compatibility checks, media permission requests, audio and video diagnostics, and network readiness before a user joins a meeting. An agent uses it after routing to a preflight workflow.

When should probe-sdk be used instead of meeting-sdk or video-sdk?

probe-sdk is for client-side diagnostics and readiness scoring of device, network and browser, not for joining a session. For embedded meeting join it routes to meeting-sdk, and for custom real-time session UX it routes to video-sdk.

Source text

SKILL.md · Apache-2.0 
---
name: probe-sdk
description: "Reference skill for Zoom Probe SDK. Use after routing to a preflight workflow when testing browser compatibility, media permissions, audio or video diagnostics, and network readiness before users join."
user-invocable: false
triggers:
  - "probe sdk"
  - "zoom probe"
  - "@zoom/probesdk"
  - "media diagnostics"
  - "network diagnostic"
  - "preflight check"
  - "diagnose audio video"
  - "browser compatibility diagnostics"
  - "diagnostic report"
---

# Zoom Probe SDK

Background reference for preflight diagnostics on user devices and networks before meeting or session workflows.

Official docs:
- https://developers.zoom.us/docs/probe-sdk/
- https://marketplacefront.zoom.us/sdk/probe/index.html

Reference sample:
- https://github.com/zoom/probesdk-web

## Routing Guardrail

- Use Probe SDK when the user needs client-side diagnostics and readiness scoring (device/network/browser capability), not meeting/session join.
- If user needs embedded meeting flows, route to [../meeting-sdk/SKILL.md](../meeting-sdk/SKILL.md).
- If user needs custom real-time session UX, route to [../video-sdk/SKILL.md](../video-sdk/SKILL.md).
- If user needs backend orchestration of events/APIs, chain with [../rivet-sdk/SKILL.md](../rivet-sdk/SKILL.md), [../oauth/SKILL.md](../oauth/SKILL.md), and [../rest-api/SKILL.md](../rest-api/SKILL.md).

## Quick Links

Start here:
1. [probe-sdk.md](probe-sdk.md)
2. [concepts/architecture-and-lifecycle.md](concepts/architecture-and-lifecycle.md)
3. [scenarios/high-level-scenarios.md](scenarios/high-level-scenarios.md)
4. [examples/diagnostic-page-pattern.md](examples/diagnostic-page-pattern.md)
5. [examples/comprehensive-network-pattern.md](examples/comprehensive-network-pattern.md)
6. [references/probe-reference-map.md](references/probe-reference-map.md)
7. [references/environment-variables.md](references/environment-variables.md)
8. [references/versioning-and-compatibility.md](references/versioning-and-compatibility.md)
9. [references/samples-validation.md](references/samples-validation.md)
10. [references/source-map.md](references/source-map.md)
11. [troubleshooting/common-issues.md](troubleshooting/common-issues.md)
12. [RUNBOOK.md](RUNBOOK.md)

## Common Lifecycle Pattern

1. Initialize `Prober` / `Reporter`.
2. Request media permissions and enumerate devices.
3. Run targeted diagnostics (`diagnoseAudio`, `diagnoseVideo`).
4. Run comprehensive network diagnostic (`startToDiagnose`) and stream stats to UI.
5. Produce final report and apply readiness gates.
6. Stop/cleanup (`stopToDiagnose`, `stopToDiagnoseVideo`, `releaseMediaStream`, `cleanup`).

## High-Level Scenarios

- Pre-join diagnostics page before Meeting SDK join action.
- Support workflow that captures structured report for customer troubleshooting.
- Device certification flow for kiosk or controlled endpoint environments.
- Browser capability gating for advanced media features.

See [scenarios/high-level-scenarios.md](scenarios/high-level-scenarios.md) for details.

## Chaining

- Meeting pre-join gate: [../meeting-sdk/web/SKILL.md](../meeting-sdk/web/SKILL.md)
- Video session readiness gate: [../video-sdk/web/SKILL.md](../video-sdk/web/SKILL.md)
- Telemetry/report ingestion backend: [../rivet-sdk/SKILL.md](../rivet-sdk/SKILL.md) + [../rest-api/SKILL.md](../rest-api/SKILL.md)

## Environment Variables

- See [references/environment-variables.md](references/environment-variables.md) for optional `.env` keys and how to source values.

## Operations

- [RUNBOOK.md](RUNBOOK.md) - 5-minute preflight and debugging checklist.

© anthropics · Apache-2.0 · anthropics/knowledge-work-plugins

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor