Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Analyze application logs for performance insights and issue detection including slow requests, error patterns, and resource usage. Use when troubleshooting performance issues or debugging errors. Trigger with phrases like "analyze logs", "find slow requests", or "detect error patterns".
.claude/skills/jeremylongshore-analyzing-logs/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 100% | 0% |
| case-02 | ✓→✗ | ▼ Worse | -30% | 0% |
| case-10 | ✓→✗ | ▼ Worse | -62% | 0% |
| case-12 | ✓→✗ | ▼ Worse | -18% | 0% |
| case-21 | ✓→✗ | ▼ Worse | -61% | 0% |
Analyze application logs to identify slow requests, recurring error patterns, and resource usage anomalies with structured reporting and optimization recommendations.
This skill empowers Claude to automatically analyze application logs, pinpoint performance bottlenecks, and identify recurring errors. It streamlines the debugging process and helps optimize application performance by extracting key insights from log data.
This skill activates when you need to:
User request: "Analyze logs for slow requests."
The skill will:
User request: "Find error patterns in the application logs."
The skill will:
This skill can be integrated with other tools for monitoring and alerting. For example, it can be used in conjunction with a monitoring plugin to automatically trigger alerts based on log analysis results. It can also work with deployment tools to rollback deployments when critical errors are detected in the logs.
If log analysis fails:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 10,591 | 3,030 | -71% | 1 | 1 | 0% | 1,995 | 1,077 | -46% | 0 | 0 | — |
case-02 | pass→fail | 6,983 | 4,346 | -38% | 1 | 1 | 0% | 1,278 | 899 | -30% | 0 | 0 | — |
case-03 | fail→fail | 6,753 | 5,408 | -20% | 1 | 1 | 0% | 1,111 | 1,017 | -8% | 0 | 0 | — |
case-04 | pass→pass | 8,346 | 7,665 | -8% | 1 | 1 | 0% | 1,617 | 2,226 | +38% | 0 | 0 | — |
case-05 | pass→pass | 11,203 | 12,838 | +15% | 1 | 1 | 0% | 2,508 | 3,664 | +46% | 0 | 0 | — |
case-06 | pass→pass | 10,142 | 10,588 | +4% | 1 | 1 | 0% | 2,143 | 3,058 | +43% | 0 | 0 | — |
case-07 | fail→fail | 3,942 | 5,979 | +52% | 1 | 1 | 0% | 230 | 1,090 | +374% | 0 | 0 | — |
case-08 | fail→fail | 4,107 | 3,994 | -3% | 1 | 1 | 0% | 175 | 932 | +433% | 0 | 0 | — |
case-09 | fail→pass | 12,890 | 23,251 | +80% | 1 | 1 | 0% | 2,462 | 4,931 | +100% | 0 | 0 | — |
case-10 | pass→fail | 11,299 | 4,802 | -58% | 1 | 1 | 0% | 2,397 | 922 | -62% | 0 | 0 | — |
case-11 | fail→fail | 3,032 | 5,574 | +84% | 1 | 1 | 0% | 358 | 872 | +144% | 0 | 0 | — |
case-12 | pass→fail | 7,554 | 5,089 | -33% | 1 | 1 | 0% | 1,199 | 989 | -18% | 0 | 0 | — |
case-13 | fail→fail | 2,235 | 4,548 | +103% | 1 | 1 | 0% | 283 | 907 | +220% | 0 | 0 | — |
case-14 | fail→fail | 5,246 | 7,422 | +41% | 1 | 1 | 0% | 253 | 920 | +264% | 0 | 0 | — |
case-15 | fail→fail | 4,378 | 4,438 | +1% | 1 | 1 | 0% | 259 | 925 | +257% | 0 | 0 | — |
case-16 | fail→fail | 3,425 | 5,094 | +49% | 1 | 1 | 0% | 120 | 904 | +653% | 0 | 0 | — |
case-17 | fail→fail | 4,058 | 6,202 | +53% | 1 | 1 | 0% | 434 | 913 | +110% | 0 | 0 | — |
case-18 | fail→fail | 24,083 | 3,056 | -87% | 1 | 1 | 0% | 6,301 | 902 | -86% | 0 | 0 | — |
case-19 | fail→fail | 4,494 | 3,633 | -19% | 1 | 1 | 0% | 238 | 846 | +255% | 0 | 0 | — |
case-20 | fail→fail | 2,466 | 4,523 | +83% | 1 | 1 | 0% | 288 | 962 | +234% | 0 | 0 | — |
case-21 | pass→fail | 13,083 | 5,106 | -61% | 1 | 1 | 0% | 2,534 | 989 | -61% | 0 | 0 | — |
case-22 | pass→fail | 19,109 | 5,522 | -71% | 1 | 1 | 0% | 4,471 | 912 | -80% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 6 counted toward the lift figure. The other 16 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -33 percentage points is the difference between those two pass rates over the 6 comparable cases. 6 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.