mcpbeat Sign in

Live Debugging MCP Agent Skill

Use this whenever debugging an iOS DAT app with local DAT Inspector MCP tools, live device events, Meta AI app/device boundary issues, permissions, registration, sessions, streaming, callbacks, or user reports that the app cannot communicate with glasses.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
500
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/facebook/meta-wearables-dat-ios --skill live-debugging-mcp

The instruction itself

6 sections, as written by the author

Live DAT Debugging with MCP (iOS)

Use this skill when a developer is debugging an iOS DAT app and has a local DAT

Inspector MCP server or DAT debug server available to the agent. This is the

live-runtime counterpart to dat-docs-mcp: use docs search for API lookup, and

use this skill for observed app/device behavior.

Ground rules

  • Stay read-only unless the user explicitly asks for an app code change.
  • Do not mutate Meta AI app, device, account, permission, registration, or app

state.

  • Treat companion-app/device results as boundary diagnosis from app-visible DAT

events, not as direct access to companion app internals.

  • Use live DAT evidence before guessing: registration, permissions, device

selection, link state, session state, stream state, typed errors, and SDK logs.

  • If the MCP tools are not configured, ask the developer to enable their local

DAT debug setup and fall back to logs plus search_dat_docs.

Normal agent loop

  • Discover and connect to the running app debug server:
  • discover_debug_servers
  • connect_to_debug_server
  • Establish the baseline with all three calls before diagnosing deeper:
  • get_connection_status
  • get_sdk_state
  • get_dat_readiness

Do not skip get_connection_status; it separates MCP/debug-server

connectivity from SDK, registration, permission, session, and stream state.

  • If the issue looks like Meta AI app or device boundary behavior, inspect:
  • get_companion_boundary_diagnosis
  • get_device_path
  • get_permissions
  • get_device_properties
  • Ask the developer to reproduce the failing iOS flow while connected.
  • Wait for narrow evidence instead of polling everything:
  • wait_for_events with category or source
  • get_errors
  • get_event_digest
  • For handoff, collect a redacted bundle:
  • export_diagnostic_bundle

Evidence map

  • Configuration: app logs around Wearables.configure()
  • URL callbacks: Wearables.shared.handleUrl(_:) return handling
  • Registration: Wearables.shared.startRegistration() and

wearables.registrationState

  • Device availability: device selectors, wearables.devices,

device.compatibility, and device.properties

  • Device link: device.linkState
  • Permissions: DAT permission APIs, device.permission, check_permissions,

and get_permissions

  • Session: DeviceSession creation/start, deviceSession.state,

session.state, and session errors

  • Stream: stream start, stream.state, frame counters, and stream errors
  • DAM/DWA-visible transport: sdk.usesDam and DAM/DWA error values

Diagnosis patterns

  • Registration blocked: verify Info.plist DAT configuration, app URL scheme,

Developer Mode setup, and callback handling.

  • No eligible device: inspect discovered devices, selector behavior, device

compatibility, and device.linkState before changing stream code.

  • Permission failure: use get_permissions and get_companion_boundary_diagnosis;

do not assume iOS system permission is the same as DAT permission through the

Meta AI app/device boundary.

  • Session fails before stream creation: inspect session errors and selected

device compatibility before changing camera code.

  • Stream fails after session start: inspect stream state, camera permission, and

recent errors before changing frame processing.

Output expectations

When summarizing, name the evidence plane, the blocking state, and the next

developer action. Example:

DAT readiness is blocked at registration: the app-visible registration state is
not registered. Check the Info.plist DAT URL scheme and MetaAppID, complete the
Meta AI callback through handleUrl(_:), then retry while the MCP connection waits
for registration and device-link events.

Other skills for the same job

different authors, same section of the catalogue
Loki Mode
by ComeOnOliver
×2

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

3528k tokens scripts
Error Debugging Multi Agent Review
by lingxling
×1

Use when working with error debugging multi agent review

2k tokens
Evaluation
by lingxling
×1

Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time.

3k tokens
Agent Communication Debugger
by ComeOnOliver
×1

Diagnoses and debugs A2A agent communication issues including agent status, message routing, transport connectivity, and log analysis. Use when agents aren't responding, messages aren't being delivered, routing is incorrect, or when debugging orchestrator, coder-agent, tester-agent communication problems.

23k tokens scripts
Error Debugging Multi Agent Review
by ComeOnOliver
×1

Use when working with error debugging multi agent review

4k tokens
Micro Skill Creator
by ComeOnOliver
×1

Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.

6k tokens
Ohmg
by ComeOnOliver
×1

Ultimate multi-agent framework for Google Antigravity. Orchestrates specialized domain agents (PM, Frontend, Backend, Mobile, QA, Debug) via Serena Memory.

3k tokens
Evaluation
by ComeOnOliver
×1

This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.

13k tokens scripts

How to use it

Copy the folder

Take facebook/live-debugging-mcp from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.