Agent Skills Observability

PostHog LLM Analytics agent skill

Explore LLM usage clusters, costs, traces, and experiments in PostHog.

Observability · by PostHog

What it does

Explore LLM usage clusters, costs, traces, and experiments in PostHog.

When your agent should use it

Analyzing AI/LLM traffic, cost, or experiment results.

How agent skills work

An agent skill is a packaged instruction set (a SKILL.md + assets) that a model loads on demand when a task matches — so the agent gains a capability without bloating every prompt. Skills compose: a single agent can carry many, and invoke the right one per task.

Skills are one leg of the stack

A skill tells your agent how to do something. To let it act on the world, pair skills with tools: trust-graded MCP servers (we grade every one A–F so you know it's safe to connect) and any website turned into agent tools via WebMCP — no server to build.

More Observability skills