Agent Skills

Find reusable agent skills for coding, research, design and everyday work, with practical explanations and links to the original instructions.

Submit a skill

107 skills · Page 6 of 9

Creating Experiments

Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions to configuring-experiment-rollout and metric…

Creating Replay Vision Scanners

Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the RecordingsQuery that selects sessions, and —…

Diagnosing Experiment Results

Diagnoses bias, anomalies, and strange-looking results on a specific PostHog experiment. Covers empty / 0-exposure experiments, sample ratio mismatch, identity fragmentation, multi-variant exposure, uneven-split…

Designing Email Templates

Author, save, and edit email templates in the PostHog workflows library — compose email design JSON with Liquid personalization and create and round-trip-edit templates…

Diagnosing SDK Health

A collection of PostHog skills for enhancing AI-assisted workflows. Add this repo as a Claude Code plugin marketplace to get access to all PostHog…

Explore MCP servers

Entries link to the original documentation. Check access requirements, costs and maintenance before installing.

Agent Skills FAQ

What is an agent skill?

An agent skill packages instructions and supporting files for a particular task, so an AI agent can do that task the same way each time.

Which AI agents can use a skill?

Check the original project for its supported clients, installation steps and required tools. A skill’s page lists its compatibility and requirements when the project states them.

How do I add a skill to my agent?

Open a skill’s page for its getting-started notes and sources, then follow the original project’s documentation for your agent.