New to Claude Skills? Learn how to install them →

Get Claude Skills
posthog on GitHub

Finding Experiments

Free

Resolve experiment references to IDs in PostHog.

by posthog37.6k stars on posthog/posthog
1 views
Updated Aug 11, 2026
Get this skill

Free · Opens the source repo

What Finding Experiments does

Finding Experiments is a skill designed for users of PostHog who need to quickly locate experiment IDs based on natural language references. Often, users refer to experiments by their descriptive names, statuses, or relative terms rather than their concrete IDs. This skill streamlines the process of identifying the correct experiment ID, making it easier for users to manage their experiments effectively.

The skill works by utilizing the experiment-list tool from the PostHog-local MCP server, which returns a comprehensive list of experiments along with their details such as ID, name, status, and creation date. Users can invoke this skill when they mention an experiment by name, describe it loosely, or use relative references like "latest" or "most recent." The skill is particularly useful in collaborative environments where multiple experiments may be in progress, and clarity is essential.

After executing the search, the skill can handle various scenarios: if exactly one match is found, it will proceed with the action requested by the user; if multiple matches are found, it will present the options for the user to choose from; and if no matches are found, it will inform the user accordingly. This structured approach ensures that users can efficiently navigate their experiments without confusion or errors.

Finding Experiments is ideal for product managers, data analysts, and developers who frequently interact with experiments in PostHog and need a reliable way to resolve references to experiment IDs. By automating this process, the skill enhances productivity and reduces the likelihood of mistakes during experiment management.

When to use it

Use this skill when users refer to experiments by name, description, or status instead of by ID.

When not to use it

Avoid using this skill if the user has already provided the experiment ID directly or if the experiment was just created and the ID is known.

What you can build with it

Pause an Experiment

A user says, 'pause my signup experiment.' The skill resolves the correct experiment ID and proceeds to pause it.

Find Recent Experiments

A user asks for the 'most recent pricing test.' The skill retrieves and lists the latest experiments for the user to select from.

Check Experiment Status

A user inquires about the 'running experiments.' The skill fetches all experiments currently in the running status for review.

How to install Finding Experiments

View source

1. Install with the skills CLI

npx skills add posthog/posthog/finding-experiments --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by posthog

Finding experiments

Users refer to experiments by name, description, or relative references — not by ID. This skill resolves natural language references to concrete experiment IDs.

How to find an experiment

Use the experiment-list tool from the Posthog-local MCP server.

IMPORTANT: Do NOT use feature-flag-get-all or any feature flag tool to find experiments. Use the dedicated experiment list tool: experiment-list.

This tool returns experiments with their id, name, status, feature_flag_key, start_date, end_date, and created_at. Browse the returned list to find the experiment matching the user's reference:

  • By name: scan the name field for matches
  • By recency: results are ordered newest first by default
  • By status: match the status field (draft, running, paused, exposure_frozen, stopped)
  • By flag key: match the feature_flag_key field

After finding matches

  • Exactly one match: Use it. Confirm with the user by name before destructive actions (delete, ship, end).
  • Multiple matches: List them with name, status, and creation date. Ask the user to pick.
  • No matches: Tell the user. Suggest checking archived experiments or different terms.

Get full details if needed

After resolving to an ID, call experiment-get for the full object (metrics, flag details, parameters).

Examples

User: "pause my signup experiment"

Agent:
1. Calls experiment-list
2. Scans results, finds "New signup process" (ID: 1371, status: running)
3. Proceeds to pause experiment 1371

When NOT to search

  • You already have the experiment ID from earlier in the conversation
  • The user just created the experiment — you have the ID from the create response
  • The user provided the ID directly

Frequently asked questions about Finding Experiments

Similar skills

Spring Boot Testing

Master testing techniques for Spring Boot 4 applications.

GitHub Issues

Manage GitHub issues efficiently with MCP tools.

Geofeed Tuner

Optimize your IP geolocation feeds in CSV format.

Batch Files

Master Windows batch scripting for automation and task management.

Adobe Illustrator Scripting

Automate your Illustrator workflows with ExtendScript.

Plugin Structure

Create and organize Claude Code plugins effectively.