name: skyline-nightlytests description: Use this skill when looking at nightly test results or investigating test failures.
Skyline Nightly Test Analysis
Full documentation: ai/docs/mcp/nightly-tests.md
MCP Tools (Quick Reference)
| Tool | Purpose |
|---|---|
get_daily_test_summary(report_date) |
Daily report for all 6 folders → ai/.tmp/ |
save_test_failure_history(test_name, start_date, container_path) |
Stack trace pattern analysis → ai/.tmp/ |
save_run_log(run_id) |
Full test log for grep/search → ai/.tmp/ |
get_run_failures(run_id) |
Stack traces for a specific run |
get_run_leaks(run_id) |
Leak details for a specific run |
Test Folders
| Folder | Duration | Branch |
|---|---|---|
| Nightly x64 | 540 min | master (default) |
| Performance Tests | 720 min | master |
| Release Branch | 540 min | release |
| Release Branch Performance Tests | 720 min | release |
| Integration | 540 min | assigned |
| Integration with Perf Tests | 720 min | assigned |
Typical Workflow
-
Daily review:
get_daily_test_summary("2025-12-15")→ read report -
Pattern analysis: If test failed on multiple machines, use
save_test_failure_historyto check if same root cause -
Deep dive: Use
save_run_logwhen stack traces aren't sufficient
Anomaly Detection
- Short duration (< expected) = crash or premature termination
- Full duration + low test count = hang
- Stddev-based: 3σ/4σ from trained mean flags anomalies
For server-side queries, examples, and detailed workflows, see ai/docs/mcp/nightly-tests.md.
chat Comments (0)
Sign in to join the discussion and leave a comment.
Skill Details
GitHub Stars
0
GitHub Forks
0
Created
Jan 2026
Last Updated
il y a 4 mois
tools
tools debugging
Related Skills
Build your own?
Join 12,000+ developers contributing to the Claude ecosystem.
No comments yet. Be the first to share your thoughts!