Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Implement distributed tracing with Jaeger and Tempo for request flow visibility across microservices.
.claude/skills/distributed-tracing/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✓→✓ | ＝ Same ✓ | — | — |
| case-23 | ✗→✗ | ＝ Same ✗ | — | — |
| case-20 | ✗→✗ | ＝ Same ✗ | — | — |
| case-08 | ✗→✗ | ＝ Same ✗ | — | — |
Trace a request across services, diagnose latency and error propagation, or add observable boundaries to a new integration.
Record installed SDK and backend versions, permitted collector endpoints, the service graph and a staging request. Inspect the installed version's primary documentation before selecting exporter APIs or deployment configuration. This bundle does not install a tracing backend.
resources/implementation-playbook.md and identify one user journey.references/instrumentation.md for propagation, shutdown and privacy checks.references/jaeger-setup.md, or the existing Tempo/collector deployment's supported configuration. Review listeners, authentication, transport protection, storage and retention before any deployment.A checkout calls inventory and payment. Verify that the root request and both downstream operations share a trace, that a simulated payment timeout is recorded, and that no card data is present. Repeat with exporter connectivity unavailable: request handling must retain the application's defined behavior.
Head sampling can discard errors before tail sampling sees them. In-memory demos do not prove durable storage. Context propagation and cross-service clocks need actual integration tests; this guide is not a runnable multi-service application.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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. 23 cases were attempted. The headline lift of +4 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.