mcpbeat Sign in

Debugging Agent Skill

Common issues, Developer Mode, version compatibility, state machine diagnosis

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 debugging

The instruction itself

16 sections, as written by the author

Debugging (iOS)

Diagnose common setup, registration, and streaming issues in DAT SDK integrations.

If local DAT Inspector MCP tools are available, use the live-debugging-mcp

skill before changing app code. Prefer get_dat_readiness,

get_companion_boundary_diagnosis, and get_device_path to separate app bugs from

Meta AI app/device boundary issues using read-only DAT evidence.

Quick diagnosis

Device not connecting?
│
├── Is Developer Mode enabled? → Enable in Meta AI app settings
│
├── Is device registered? → Check registration state
│
├── Is device in range? → Bluetooth on, glasses powered on
│
├── Is the app registered? → Check registrationStateStream()
│
└── Stream stuck in waitingForDevice? → Check device availability

Developer Mode

Developer Mode must be enabled for 3P apps to access device features.

Enabling Developer Mode

  • Open Meta AI app on phone
  • Go to Settings → (Your connected glasses)
  • Find "Developer Mode" toggle
  • Toggle ON
  • Device may restart

Symptoms of Developer Mode disabled

  • Registration completes but device never connects
  • Stream stuck in waitingForDevice
  • Permission requests fail or never appear

Watch for

  • Developer Mode toggles off after firmware updates — re-enable it
  • Developer Mode is per-device — enable for each glasses pair
  • Some features need additional permissions beyond Developer Mode

Stream state issues

Expected flow

stopped → waitingForDevice → starting → streaming → stopped

Stuck in waitingForDevice

  • Device not in range or not connected
  • Device not reporting availability
  • DeviceSelector not matching any device

Unexpected stop

  • Device disconnected (out of range, battery died)
  • Channel closed by device
  • Error in frame processing

Version compatibility

Ensure compatible versions of SDK, Meta AI app, and glasses firmware. See version dependencies for the current compatibility matrix.

Known issues

| Issue | Workaround |

|-------|-----------|

| No internet → registration fails | Internet required for registration |

| Streams started with glasses doffed pause when donned | Unpause by tapping side of glasses |

| [iOS] Meta Ray-Ban Display: no audio feedback on pause/resume | Will be fixed in future release |

Adding debug logging

import os

private let logger = Logger(subsystem: "com.yourapp", category: "Wearables")

// In your streaming code:
logger.debug("Stream state changed to: \(state)")
logger.error("Stream error: \(error)")

Live MCP evidence

When the developer has a local DAT debug server connected to the agent:

  • Start with get_sdk_state and get_dat_readiness
  • Use get_companion_boundary_diagnosis for permission, app identity, device

capability, device-selection, deeplink-return, and DAM/DWA-visible blockers

  • Use get_device_path to trace app -> DAT registration -> Meta AI app permissions ->

device selection/link -> session -> stream

  • Ask the developer to reproduce the issue, then use wait_for_events with the

narrowest category or source that matches the flow

  • Use export_diagnostic_bundle for redacted support handoff

Do not treat this as companion app introspection. It is diagnosis from

app-visible DAT debug events.

Checklist

  • [ ] Developer Mode enabled in Meta AI app
  • [ ] Meta AI app updated to compatible version
  • [ ] Glasses firmware updated to compatible version
  • [ ] Internet connection available for registration
  • [ ] Bluetooth enabled on phone
  • [ ] Correct URL scheme configured in Info.plist
  • [ ] Background modes enabled (bluetooth-peripheral, external-accessory)

Other skills for the same job

different authors, same section of the catalogue
Webapp Testing
by anthropics
vendor ×12

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

6k tokens scripts
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
Test Driven Development
by w95
×7

Use when implementing any feature or bugfix, before writing implementation code

2k tokens
Systematic Debugging
by ratacat
×7

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

10k tokens scripts
Verification Before Completion
by ZhanlinCui
×6

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

1k tokens
Backtest Expert
by BaggaT236
×3

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

15k tokens scripts
Adaptyv
by christophacham
×3

Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.

16k tokens
Aeon
by christophacham
×3

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

19k tokens

How to use it

Copy the folder

Take facebook/debugging 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.