Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build and operate Python Azure IoT Edge modules with robust messaging, deployment manifests, observability, and production readiness checks.
.claude/skills/python-azure-iot-edge-modules/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 51% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 124% | 0% |
Use this skill to design, implement, and validate Python-based IoT Edge modules for telemetry processing, local inference, protocol translation, and edge-to-cloud integration.
Use this skill for requests like:
Before recommending runtime behavior or deployment decisions, review:
Minimum checks:
If documentation cannot be fetched, proceed with explicit assumptions and flag them clearly.
Before proposing Python implementation details, consult official Python sources:
Prefer official docs over community snippets unless there is a specific compatibility reason to deviate.
Define:
Specify:
Implement and validate:
Require:
Define:
When relevant, combine with:
azure-smart-city-iot-solution-builder for platform-level architecture.appinsights-instrumentation for telemetry instrumentation approaches.azure-resource-visualizer for architecture diagrams and dependency mapping.Also use references/python-official-best-practices.md as baseline quality criteria for module design and implementation guidance.
Always provide:
Use references/python-edge-module-template.md to structure implementation proposals and reviews.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 31,177 | 23,706 | -24% | 1 | 1 | 0% | 6,211 | 7,127 | +15% | 0 | 0 | — |
case-02 | fail→pass | 35,025 | 29,328 | -16% | 1 | 1 | 0% | 6,208 | 7,124 | +15% | 0 | 0 | — |
case-03 | fail→pass | 26,798 | 25,195 | -6% | 1 | 1 | 0% | 6,198 | 6,693 | +8% | 0 | 0 | — |
case-04 | fail→fail | 37,776 | 19,252 | -49% | 1 | 1 | 0% | 4,500 | 5,558 | +24% | 0 | 0 | — |
case-05 | fail→fail | 17,749 | 20,229 | +14% | 1 | 1 | 0% | 3,828 | 5,547 | +45% | 0 | 0 | — |
case-06 | fail→fail | 19,241 | 19,374 | +1% | 1 | 1 | 0% | 3,984 | 4,805 | +21% | 0 | 0 | — |
case-07 | fail→pass | 14,597 | 15,878 | +9% | 1 | 1 | 0% | 3,446 | 4,412 | +28% | 0 | 0 | — |
case-08 | pass→pass | 19,367 | 26,208 | +35% | 1 | 1 | 0% | 3,434 | 5,941 | +73% | 0 | 0 | — |
case-09 | fail→pass | 16,858 | 18,087 | +7% | 1 | 1 | 0% | 3,176 | 4,794 | +51% | 0 | 0 | — |
case-10 | fail→pass | 11,814 | 19,696 | +67% | 1 | 1 | 0% | 2,143 | 4,793 | +124% | 0 | 0 | — |
case-11 | pass→pass | 10,944 | 16,077 | +47% | 1 | 1 | 0% | 2,242 | 4,444 | +98% | 0 | 0 | — |
case-12 | pass→pass | 13,069 | 20,167 | +54% | 1 | 1 | 0% | 2,903 | 5,274 | +82% | 0 | 0 | — |
case-13 | pass→pass | 18,470 | 15,657 | -15% | 1 | 1 | 0% | 3,851 | 4,636 | +20% | 0 | 0 | — |
case-14 | pass→pass | 27,876 | 28,794 | +3% | 1 | 1 | 0% | 5,399 | 6,066 | +12% | 0 | 0 | — |
case-15 | pass→pass | 15,134 | 19,832 | +31% | 1 | 1 | 0% | 2,858 | 4,935 | +73% | 0 | 0 | — |
case-16 | fail→fail | 22,048 | 21,032 | -5% | 1 | 1 | 0% | 5,421 | 5,833 | +8% | 0 | 0 | — |
case-17 | fail→pass | 18,875 | 23,947 | +27% | 1 | 1 | 0% | 4,422 | 6,460 | +46% | 0 | 0 | — |
case-18 | fail→pass | 16,904 | 20,122 | +19% | 1 | 1 | 0% | 2,889 | 5,562 | +93% | 0 | 0 | — |
case-19 | pass→pass | 15,220 | 19,615 | +29% | 1 | 1 | 0% | 2,517 | 4,863 | +93% | 0 | 0 | — |
case-20 | pass→pass | 14,967 | 18,443 | +23% | 1 | 1 | 0% | 2,691 | 4,413 | +64% | 0 | 0 | — |
case-21 | fail→fail | 20,040 | 24,615 | +23% | 1 | 1 | 0% | 4,331 | 5,894 | +36% | 0 | 0 | — |
case-22 | fail→pass | 21,331 | 21,636 | +1% | 1 | 1 | 0% | 3,819 | 5,501 | +44% | 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. The headline lift of +36 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/26/2026 | +36% |
| gemini-3.6-flash | verified | 7/26/2026 | +18% |
Other measured skills in the registry, with their headline benchmark lift.