Check deployed URLs after releases for page and API failures, broken assets, streaming connection issues, and slower performance. Run a single check, monitor over a set period, or compare staging and production with baseline reports.
Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or dependency upgrades. Smoke / canary / post-deploy verification.
Review the instructions the agent will receive before you install.
Monitors a deployed URL for regressions. Runs in a loop until stopped or until the watch window expires.
1. HTTP Status — is the page returning 200?
2. Console Errors — new errors that weren't there before?
3. Network Failures — failed API calls, 5xx responses?
4. Performance — LCP/CLS/INP regression vs baseline?
5. Content — did key elements disappear? (h1, nav, footer, CTA)
6. API Health — are critical endpoints responding within SLA?
7. Static Assets — are JS, CSS, image, and font requests returning 2xx/3xx with expected content types?
8. SSE Streams — do event-stream endpoints connect and receive an initial event or heartbeat?
Quick check (default): single pass, report results
/canary-watch https://myapp.com
Sustained watch: check every N minutes for M hours
/canary-watch https://myapp.com --interval 5m --duration 2h
Diff mode: compare staging vs production
/canary-watch --compare https://staging.myapp.com https://myapp.com
critical: # immediate alert
- HTTP status != 200
- Console error count > 5 (new errors only)
- LCP > 4s
- API endpoint returns 5xx
- Static asset returns 4xx/5xx
- SSE endpoint cannot connect or drops before first heartbeat
warning: # flag in report
- LCP increased > 500ms from baseline
- CLS > 0.1
- New console warnings
- Response time > 2x baseline
- Static asset content type changed unexpectedly
- SSE heartbeat latency > 2x baseline
info: # log only
- Minor performance variance
- New network requests (third-party scripts added?)
When a critical threshold is crossed:
~/.claude/canary-watch.log## Canary Report — myapp.com — 2026-03-23 03:15 PST
### Status: HEALTHY ✓
| Check | Result | Baseline | Delta |
|-------|--------|----------|-------|
| HTTP | 200 ✓ | 200 | — |
| Console errors | 0 ✓ | 0 | — |
| LCP | 1.8s ✓ | 1.6s | +200ms |
| CLS | 0.01 ✓ | 0.01 | — |
| API /health | 145ms ✓ | 120ms | +25ms |
| Static assets | 42/42 ✓ | 42/42 | — |
| SSE /events | connected ✓ | connected | +80ms heartbeat |
### No regressions detected. Deploy is clean.
Pair with:
/browser-qa for pre-deploy verificationgit push to auto-check after deploysNo reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Design and audit interfaces for Web, iOS, and Android using WCAG 2.2 accessibility guidance. Check screen-reader labels, keyboard navigation, contrast, and control sizes to identify barriers and guide implementation for people using assistive technology.
Investigate unreliable AI agents across 12 layers, including instructions, memory, tool execution, and display. Use code and logs to trace failures, rank findings by severity, and produce an ordered repair plan that prioritizes code changes.
Compare coding agents on tasks from your own codebase. Define success checks, run agents in separate Git working directories, and report pass rates, available API costs, completion time, and consistency across repeated trials.
Design and refine an AI agent’s available actions, tool inputs, and result formats. Define recovery steps for errors, manage the information kept in context, and evaluate changes through completion rates, retries, and cost per successful task.
Diagnose failed AI agent runs by capturing errors, checking likely causes, and choosing small, reversible recovery actions. The workflow produces a structured report of the failure, recovery steps, and evidence, helping explain repeated retries or stalled progress.
Diagnose AI agent runs that fail repeatedly, loop through tools, or lose track of the task. Capture errors and environment details, test a focused recovery action, and produce a report explaining the evidence and outcome.