Posthog Skills

ai-plugin/skills/exploring-llm-costs

PostHog attaches per-call cost metadata to every $ai_generation and $ai_embedding event at ingestion time. Every cost question reduces to an aggregation over those two event types — the interesting variation is only in how you group, filter, and compare.

posthog/products/ai_observability/skills/exploring-llm-costs

Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost…

skills/skills/omnibus/exploring-llm-costs

PostHog attaches per-call cost metadata to every $ai_generation and $ai_embedding event at ingestion time. Every cost question reduces to an aggregation over those two event types — the interesting variation is only in how you group, filter, and compare.

ai-plugin/skills/exploring-llm-evaluations

PostHog evaluations score $ai_generation events. Each evaluation is one of two types, both first-class:

posthog/products/ai_observability/skills/exploring-llm-evaluations

PostHog evaluations score $ai_generation events. Each evaluation is one of two types, both first-class:

skills/skills/omnibus/exploring-llm-evaluations

PostHog evaluations score $ai_generation events. Each evaluation is one of two types, both first-class:

ai-plugin/skills/exploring-llm-traces

PostHog captures LLM/AI agent activity as traces. Each trace is a tree of events representing a single AI interaction — from the top-level agent invocation down to individual LLM API calls.

posthog/products/ai_observability/skills/exploring-llm-traces

PostHog captures LLM/AI agent activity as traces. Each trace is a tree of events representing a single AI interaction — from the top-level agent invocation down to individual LLM API calls.

skills/skills/omnibus/exploring-llm-traces

PostHog captures LLM/AI agent activity as traces. Each trace is a tree of events representing a single AI interaction — from the top-level agent invocation down to individual LLM API calls.

ai-plugin/skills/exploring-mcp-intent-clusters

Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates. Use when the user asks…

posthog/products/mcp_analytics/skills/exploring-mcp-intent-clusters

Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates. Use when the user asks…

ai-plugin/skills/exploring-mcp-sessions

Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use…

posthog/products/mcp_analytics/skills/exploring-mcp-sessions

Investigate individual PostHog MCP sessions — the sequence of tool calls a single agent made in one run, what it was trying to do, and where it went wrong. Use…

ai-plugin/skills/exploring-mcp-tool-quality

Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool…

posthog/products/mcp_analytics/skills/exploring-mcp-tool-quality

Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool…

ai-plugin/skills/exploring-mcp-tool-usage

Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks "how…

posthog/products/mcp_analytics/skills/exploring-mcp-tool-usage

Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks "how…

ai-plugin/skills/exploring-replay-vision-observations

Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling…

posthog/products/replay_vision/skills/exploring-replay-vision-observations

Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling…

ai-plugin/skills/exploring-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user…

posthog/products/signals/skills/exploring-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user…

ai-plugin/skills/exploring-signals-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user…

skills/skills/omnibus/exploring-signals-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user…

wizard/.claude/skills/exploring-the-wizard

Run, drive, and explore the PostHog wizard headlessly against an app — boot it on the app and decide each screen yourself over the wizard-ci MCP tools…

ai-plugin/skills/exporting-session-recordings

Export a single session recording's raw data (recording blocks + ClickHouse metadata) to a downloadable zip, and download it. Staff-only, via the django admin…

posthog/.agents/skills/extending-personhog-test-harness

When and how to add scenarios, chaos events, and invariants to the personhog e2e test harness (rust/personhog-test-harness). Use after fixing a bug or…

skills/skills/posthog/all/skills/feature-flags-android

PostHog feature flags for Android applications

skills/skills/posthog/all/skills/feature-flags-api

PostHog feature flags for API applications

skills/skills/posthog/all/skills/feature-flags-dotnet

PostHog feature flags for .NET applications

skills/skills/posthog/all/skills/feature-flags-elixir

PostHog feature flags for Elixir applications