The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to perform reconnaissance on the local project directory to identify existing error monitoring setups.\n
It executes commands like rg and grep on Package.swift and Swift source files to detect existing integrations with Sentry or Firebase.\n
These operations are limited to local context gathering to ensure templates are correctly integrated without conflicts.\n- [EXTERNAL_DOWNLOADS]: The skill references external SDKs from well-known services for error monitoring functionality.\n
It provides instructions to include the official Sentry SDK repository (https://github.com/getsentry/sentry-cocoa) in the project's dependency manager.\n
It points users to official Firebase and Sentry domains for account setup and documentation, which are recognized well-known services.\n- [SAFE]: The skill implements a standard template generation workflow with an inherent indirect prompt injection surface that is managed through best practices.\n
Ingestion points: The skill reads local project metadata and source code using rg, cat, and grep to detect existing SDKs.\n
Boundary markers: No specific delimiters or 'ignore' instructions are used when interpreting the output of the reconnaissance commands.\n
Capability inventory: The agent has access to Bash, Read, Write, Edit, and Grep tools to modify the project structure.\n
Sanitization: The skill does not explicitly sanitize the content of the project files it reads before using that information to customize generated templates.\n- [SAFE]: The skill includes explicit security and privacy guidance for the developer.\n
It provides a NoOpErrorMonitoring implementation to support privacy-focused modes or users who opt out of tracking.\n
Documentation within the skill (error-monitoring-patterns.md) emphasizes the importance of GDPR compliance, avoiding PII collection, and anonymizing user identifiers using hashing techniques.

error-monitoring