ai-llm-telemetry
Observe LLM applications and agents from their telemetry. Reads Opik (Comet) traces and spans, LiteLLM proxy spend logs, budgets and key limits, and OpenTelemetry GenAI spans (gen_ai.* attributes) to compute cost per model, team, user and day, token percentiles, cache hit ratio, tool call frequency, failure rate and latency, time to first token, error and retry rates, cost anomalies and runaway tool loops. Bundled scripts aggregate JSON or JSONL exports offline.
When to use
Use when the user asks to "how much did our LLM calls cost", "which team burns the most tokens", "audit the agent tool calls", "find runaway loops in traces", "set up Opik with LiteLLM", "is the LLM cache working", or when an AI feature bill, latency or error rate needs an explanation. In French "cout des appels LLM", "analyser les traces Opik", "audit des tool calls de l'agent".
Inputs and tools
The skill takes the request of the user in natural language: its frontmatter declares no argument. It declares no allowed-tools: the tools available are those of the agent that loads it, under the tool policy of the project.
Reference
| Field | Value |
|---|---|
| Name | ai-llm-telemetry |
| Category | Devops |
| Version | Not declared |
| Licence | Not declared |
| Allowed tools | Not declared |
| Plugins | - |
| Source | catalog/navin/skills/ai-llm-telemetry/SKILL.md |
| Digest | sha256:7fb03d56b7be2a3bfdf82024d579dc32594f13ef6b7481ba302529488dfd00d1 |
skill_md_digest | sha256:d72914e3ff2d79ed37b22ce80b94480b34e49f6ee38e8581afcb8b097dd5013c |
| Emoji | 🧠 |
Bundled files
| Path | Count |
|---|---|
catalog/navin/skills/ai-llm-telemetry/examples | 3 |
catalog/navin/skills/ai-llm-telemetry/references | 3 |
catalog/navin/skills/ai-llm-telemetry/scripts | 2 |
Frontmatter
Every field of the SKILL.md frontmatter, with the value of the source:
| Field | Value |
|---|---|
name | ai-llm-telemetry |
description | Observe LLM applications and agents from their telemetry. Reads Opik (Comet) traces and spans, LiteLLM proxy spend logs, budgets and key limits, and OpenTelemetry GenAI spans (gen_ai.* attributes) to compute cost per model, team, user and day, token percentiles, cache hit ratio, tool call frequency, failure rate and latency, time to first token, error and retry rates, cost anomalies and runaway tool loops. Bundled scripts aggregate JSON or JSONL exports offline. Use when the user asks to "how much did our LLM calls cost", "which team burns the most tokens", "audit the agent tool calls", "find runaway loops in traces", "set up Opik with LiteLLM", "is the LLM cache working", or when an AI feature bill, latency or error rate needs an explanation. In French "cout des appels LLM", "analyser les traces Opik", "audit des tool calls de l'agent". |
metadata.navin.emoji | 🧠 |
metadata.navin.category | devops |