What it does
The skill records telemetry for local AI task runs. It measures latency, token usage, errors and verified outcomes, and ties these results to Pudu AI hardware evidence and the Ollama models installed on the machine.
It is intended for comparing local task runs, choosing a local model for a bounded subtask, and recording reproducible telemetry for later review.
Running it requires Pudu AI hardware evidence and at least one installed Ollama model. The skill is released under the MIT license and is categorised for productivity and development use.
Limitations and requirements
Requires installed Ollama models and Pudu AI hardware evidence to produce its measurements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 8
pudu-task-telemetry
Measure local AI task latency, token usage, errors and verified outcomes using Pudu AI hardware evidence and installed Ollama models. Use when comparing local task runs, choosing a local model for a bounded subtask, or recording reproducible task telemetry.
As shown on www.aitmpl.com when we last read it