Error Monitoring logo

Error Monitoring

Community
rshankras
error-monitoring

Generates protocol-based error/crash monitoring with swappable providers (Sentry, Crashlytics). Use when user wants to add crash reporting, error tracking, or production monitoring.

Overview

Publisherrshankras
Repositoryclaude-code-apple-skills
Skill nameerror-monitoring
Stars
744
Forks
70
Bundled files
6
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by rshankras on GitHub. Read the source before you install it.

Installation

Install the Error Monitoring AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/rshankras/claude-code-apple-skills.git /tmp/claude-code-apple-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-apple-skills/skills/generators/error-monitoring .claude/skills/error-monitoring
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Error Monitoring in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Error Monitoring on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Error Monitoring is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Error Monitoring Generator

Generates a production-ready error monitoring infrastructure with protocol-based architecture for easy provider swapping.

When This Skill Activates

  • User asks to "add crash reporting" or "error monitoring"
  • User mentions "Sentry", "Crashlytics", or "crash analytics"
  • User wants to "track errors in production"
  • User asks about "debugging production issues"

Pre-Generation Checks (CRITICAL)

1. Project Context Detection

Before generating, ALWAYS check:

bash
# Check for existing crash reporting
rg -l "Sentry|Crashlytics|CrashReporter" --type swift

# Check Package.swift for existing SDKs
cat Package.swift | grep -i "sentry\|firebase\|crashlytics"

# Check for existing error handling patterns
rg "captureError|recordError|logError" --type swift | head -5

2. Conflict Detection

If existing crash reporting found:

  • Ask: Replace, wrap existing, or create parallel system?

Configuration Questions

Ask user via AskUserQuestion:

  1. Initial provider?

    • Sentry (recommended for indie devs)
    • Firebase Crashlytics (if already using Firebase)
    • None (set up infrastructure only)
  2. Include breadcrumbs?

    • Yes (track navigation, user actions)
    • No (errors only)
  3. Include user context?

    • Yes (anonymized user ID, app state)
    • No (minimal data collection)

Generation Process

Step 1: Create Core Files

Always generate:

Sources/ErrorMonitoring/
├── ErrorMonitoringService.swift     # Protocol
├── ErrorContext.swift               # Breadcrumbs, user info
└── NoOpErrorMonitoring.swift        # Testing/privacy

Based on provider selection:

Sources/ErrorMonitoring/Providers/
├── SentryErrorMonitoring.swift      # If Sentry selected
└── CrashlyticsErrorMonitoring.swift # If Crashlytics selected

Step 2: Read Templates

Read templates from this skill:

  • templates/ErrorMonitoringService.swift
  • templates/ErrorContext.swift
  • templates/NoOpErrorMonitoring.swift
  • templates/SentryErrorMonitoring.swift (if selected)
  • templates/CrashlyticsErrorMonitoring.swift (if selected)

Step 3: Customize for Project

Adapt templates to match:

  • Project naming conventions
  • Existing error types
  • Bundle identifier for Sentry DSN

Step 4: Integration

In App.swift:

swift
import SwiftUI

@main
struct MyApp: App {
    init() {
        // Configure error monitoring
        ErrorMonitoring.shared.configure()
    }

    var body: some Scene {
        WindowGroup {
            ContentView()
                .environment(\.errorMonitoring, ErrorMonitoring.shared.service)
        }
    }
}

Capturing errors:

swift
do {
    try await riskyOperation()
} catch {
    ErrorMonitoring.shared.service.captureError(error)
}

Adding breadcrumbs:

swift
ErrorMonitoring.shared.service.addBreadcrumb(
    Breadcrumb(category: "navigation", message: "Opened settings")
)

Provider Setup

Sentry

  1. Create account at sentry.io
  2. Create project for iOS/macOS
  3. Get DSN from Project Settings > Client Keys
  4. Add to Package.swift:
swift
.package(url: "https://github.com/getsentry/sentry-cocoa", from: "8.0.0")

Firebase Crashlytics

  1. Add Firebase to your project via console.firebase.google.com
  2. Download GoogleService-Info.plist
  3. Add Firebase SDK via SPM or CocoaPods
  4. Enable Crashlytics in Firebase console

Generated Code Patterns

Protocol (Stable Interface)

swift
protocol ErrorMonitoringService: Sendable {
    func configure()
    func captureError(_ error: Error, context: ErrorContext?)
    func captureMessage(_ message: String, level: ErrorLevel)
    func addBreadcrumb(_ breadcrumb: Breadcrumb)
    func setUser(_ user: MonitoringUser?)
    func reset()
}

Swapping Providers

swift
// In ErrorMonitoring.swift
final class ErrorMonitoring {
    static let shared = ErrorMonitoring()

    // Change this ONE line to swap providers:
    let service: ErrorMonitoringService = SentryErrorMonitoring()
    // let service: ErrorMonitoringService = CrashlyticsErrorMonitoring()
    // let service: ErrorMonitoringService = NoOpErrorMonitoring()
}

Breadcrumb Tracking

swift
// Automatic navigation breadcrumbs
struct ContentView: View {
    @Environment(\.errorMonitoring) var errorMonitoring

    var body: some View {
        Button("Open Details") {
            errorMonitoring.addBreadcrumb(
                Breadcrumb(category: "ui", message: "Tapped details button")
            )
            showDetails = true
        }
    }
}

Verification Checklist

After generation, verify:

  • App compiles without errors
  • Provider SDK added (if applicable)
  • DSN/config set correctly
  • Test error appears in dashboard
  • Breadcrumbs captured correctly
  • User context (if enabled) shows in reports
  • NoOp mode works for debug/testing

Privacy Considerations

GDPR Compliance

  • Use NoOpErrorMonitoring for EU users who opt out
  • Don't capture PII in error messages
  • Anonymize user IDs

App Store Guidelines

  • Disclose crash reporting in privacy policy
  • Use App Tracking Transparency if combining with analytics
  • Don't capture unnecessary device identifiers

Privacy Manifest (iOS 17+)

Add to PrivacyInfo.xcprivacy if using Sentry/Crashlytics:

xml
<key>NSPrivacyCollectedDataTypes</key>
<array>
    <dict>
        <key>NSPrivacyCollectedDataType</key>
        <string>NSPrivacyCollectedDataTypeCrashData</string>
        <key>NSPrivacyCollectedDataTypeLinked</key>
        <false/>
        <key>NSPrivacyCollectedDataTypeTracking</key>
        <false/>
        <key>NSPrivacyCollectedDataTypePurposes</key>
        <array>
            <string>NSPrivacyCollectedDataTypePurposeAppFunctionality</string>
        </array>
    </dict>
</array>

Common Customizations

Custom Error Types

swift
enum AppError: Error {
    case networkFailure(URLError)
    case decodingFailure(DecodingError)
    case authenticationRequired

    var context: ErrorContext {
        ErrorContext(
            tags: ["error_type": String(describing: self)],
            extra: ["recoverable": isRecoverable]
        )
    }
}

// Capture with context
errorMonitoring.captureError(error, context: error.context)

Performance Monitoring

swift
// Sentry supports performance monitoring
let transaction = SentrySDK.startTransaction(name: "Load Data", operation: "http")
defer { transaction.finish() }

let data = try await fetchData()

Release Tracking

swift
// Include version info
SentrySDK.start { options in
    options.dsn = "YOUR_DSN"
    options.releaseName = "\(Bundle.main.appVersion)-\(Bundle.main.buildNumber)"
}

Troubleshooting

Errors Not Appearing in Dashboard

  1. Check DSN is correct and not expired
  2. Verify network connectivity
  3. Check debug mode isn't suppressing uploads
  4. Look for SDK initialization errors in console

Symbolication Not Working

  1. Upload dSYMs to Sentry/Firebase
  2. Enable "Upload Debug Symbols" build phase
  3. Check build settings include debug info

High Volume / Costs

  1. Filter common/expected errors
  2. Sample errors (e.g., capture 10%)
  3. Group similar errors

Related Skills

  • analytics-setup - Often combined with error monitoring
  • logging-setup - Use Logger for debug, error monitoring for production

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Error Monitoring AI skill do?

Generates protocol-based error/crash monitoring with swappable providers (Sentry, Crashlytics). Use when user wants to add crash reporting, error tracking, or production monitoring.

Why use Error Monitoring on TypingMind?

Because you install it once and use it with any model. Error Monitoring is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Error Monitoring in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rshankras/claude-code-apple-skills/tree/main/skills/generators/error-monitoring. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Error Monitoring?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Error Monitoring?

As many as you like. As long as a model supports skills, you can use Error Monitoring with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Error Monitoring AI skill free?

Yes. It is published on GitHub by rshankras under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇