Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →rshankras/error-monitoring
Generates protocol-based error/crash monitoring with swappable providers (Sentry, Crashlytics).
Passed 15 of 20 test cases with the skill, and 12 of 20 without it.
and 1 more in the full report
4 fixed13 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
What methods should a complete Swift error monitoring protocol declare to handle lifecycle, exception capturing, breadcrumb logs, and user identification?
| Checked | Without skill | With skill |
|---|---|---|
| Includes configure, captureError, captureMessage, addBreadcrumb, setUser, and reset methods. | Missed | Passed |
| Ensures the protocol conforms to Sendable for safe concurrent execution. | Passed | Passed |
The instructions your model reads when the skill loads.
Generates a production-ready error monitoring infrastructure with protocol-based architecture for easy provider swapping.
Before generating, ALWAYS check:
# 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
If existing crash reporting found:
Ask user via AskUserQuestion:
test cases passed, vs 12 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.