creating-experiments

Start an A/B test the quick way: a name, a hypothesis, and the switch that turns it on. How the traffic gets divided and what counts as winning are settled afterwards, each by its own skill.

WHEN TO USE

SCOPE

USE FOR

Create a new A/B test experiment as a draft the user can refine afterward.
Set up the feature flag and hypothesis for a new experiment in one step.
Get pointed to the right rollout and metrics skills right after creating an experiment.
Launch a freshly created experiment once its metrics are configured.

NOT FOR

Updating an existing experiment, managing its lifecycle, or only browsing experiments.
Setting up a no-code toolbar experiment — that has to be done in the PostHog UI.

This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.

In this document (6)

Creating experiments

This skill walks through the 3-step flow for creating a new A/B test experiment.

Core principle: draft first, iterate on details

Create the experiment as a draft quickly, then iterate on metrics and configuration. The user gets a tangible draft immediately and can refine it.

The 3-step creation flow

Step 1: What are we testing?

Gather these before calling experiment-create:

Experiment name — descriptive, inferred from context when possible
Hypothesis — what you expect to happen (goes in description)
Feature flag key — kebab-case. Ask if they want a new flag or to reuse an existing one. The flag is auto-created — do NOT create one separately.
Type — leave empty (will internally default to "product". The "web" value is reserved for no-code experiments configured visually with the PostHog toolbar in a browser; it cannot be meaningfully driven via MCP. If a user asks for a no-code/toolbar experiment, point them to the PostHog UI instead of creating one here.)

If the user gives enough context to infer these, don't ask — just proceed.

Step 2: Who sees what variant?

This is about rollout configuration.

Before asking any rollout question, load configuring-experiment-rollout. The disambiguation wording, recommendations, and post-answer branches live there — do not formulate rollout questions yourself, and do not assume an example you remember covers the user's path.

Key decision points (covered in detail by configuring-experiment-rollout):

Variant split (how many variants, what percentage each)
Overall rollout percentage (what % of all users enter the experiment)
Whether to persist the flag across authentication steps

If the user doesn't mention rollout specifics, use defaults: 50/50 control/test, 100% rollout.

Step 3: How to measure impact?

This is about analytics and metrics. Load the configuring-experiment-analytics skill for guidance. That skill's first step checks for an existing shared metric to reuse before building a new one — don't duplicate a metric the project already has set up.

Do NOT configure metrics on creation. Metrics are not passed to experiment-create — they are added afterwards via experiment-update. This keeps the creation call lightweight.

When the user specifies metrics upfront, acknowledge them and add them immediately after creation. When they don't, create the draft and then guide them through metric setup as a follow-up.

How to create

Call experiment-create with:

{
  "name": "Descriptive experiment name",
  "feature_flag_key": "kebab-case-key",
  "description": "Hypothesis: [what you expect to happen]",
  "feature_flag": {
    "filters": {
      "multivariate": {
        "variants": [
          { "key": "control", "name": "Control", "rollout_percentage": 50 },
          { "key": "test", "name": "Test", "rollout_percentage": 50 }
        ]
      },
      "groups": [{ "properties": [], "rollout_percentage": 100 }]
    },
    "ensure_experience_continuity": false
  }
}

Flag config goes in the feature_flag object, in the flag's own filters shape (not the deprecated parameters keys). Two different percentages live in there, do NOT mix them up:

filters.multivariate.variants[].rollout_percentage is how users inside the experiment are split across variants (must sum to 100, recommended to have an even split).
filters.groups[0].rollout_percentage is the overall gate: what fraction of all users enter the experiment at all (0-100, defaults to 100).

Key details:

Minimum 2, maximum 20 variants. No specific variant key is required — the analysis baseline defaults to the variant keyed "control" when present, else the first variant (override with stats_config.baseline_variant_key). Convention: key the baseline "control" unless the user asks for specific keys.
filters.groups[0].rollout_percentage defaults to 100 if omitted.
ensure_experience_continuity persists a user's variant across authentication steps; leave it false unless the flag is shown to both logged-out and logged-in users (see configuring-experiment-rollout).
Stats default to Bayesian. Only set stats_config if the user requests Frequentist.

After creation

Always show the experiment URL. The experiment-create response includes _posthogUrl — always display this link so the user can view and configure the experiment in the UI.
Remind the user to implement the feature flag in code. Link to the experiment page and say "implement the flag as shown here" — the experiment detail page shows implementation snippets for the user's SDK.
Guide through metrics if not yet configured — load the configuring-experiment-analytics skill.
Launch when ready — use the experiment-launch tool.

Related skills

configuring-experiment-rollout — variant splits, rollout percentage, and who sees the test
configuring-experiment-analytics — exposure criteria and primary/secondary metrics
managing-experiment-lifecycle — launch, pause, ship, and end once the experiment exists

This skill ships inside the PostHog AI Plugin. Listed package contents include 3 slash commands, 1 agent, hooks and an MCP server. Installed components and skill versions may vary by AI tool.

Install just this skill

Run this outside your AI tool, using Node.js 22.20.0 or newer. Skills CLI 1.7.2 skips skill selection; prompts cancel installation without an interactive terminal. If choosing Project when asked about installation scope, open your project's folder before running this.

Install checklist

Check selected tools if a picker appears; Claude Code may be unchecked under Additional agents. ↑/↓ moves, Space toggles selections, Enter confirms.
Without a tool picker, check Installing to: for your intended tool. Stop if it names a different tool.
If asked, choose Symlink (Recommended) for shared files or Copy to all agents for separate copies; review the summary before confirming installation.
Install the find-skills skill? defaults to Yes, adding another skill for all projects. Choose No if you don't want that extra installation.

Skills CLI 1.7.2 sends install data to skills.sh by default, including the source, skill names, target tools and file details; GitHub sources are reported only when GitHub confirms the repository is public, while other remote sources can also be reported. Confirmed-public GitHub sources also trigger a security-audit request. Before installing, set the environment variable DO_NOT_TRACK=1 or DISABLE_TELEMETRY=1 to disable both.

npx skills add posthog/ai-plugin --skill "creating-experiments" --full-depth

After installing for Claude Code, open it in the installation project if you chose Project; Global makes the skill available across projects on this computer. Once Claude Code loads the skill, its description helps Claude decide when to use it.

If installation created a top-level skills folder that did not exist when your Claude Code session started, run /reload-skills in that session. Run it again after later changes in that folder.

MCP server required

The skill's steps call for tools from the PostHog MCP server. Installing just this skill doesn't add that connection; set it up in your AI tool if it isn't there yet: PostHog MCP setup. Installing the whole plugin instead includes the connection settings.

Requirements for the PostHog MCP server

Connecting is free; sign in with your PostHog account.
Some tools use AI internally and may incur PostHog AI charges. Those tools require AI data processing to be enabled in your organization settings.

Install the whole plugin

This route installs the posthog plugin package selected for your AI tool.

Claude Code

Add PostHog's marketplace, then install the plugin

Run both lines in a terminal. They install PostHog's posthog plugin: this skill, PostHog's other skills, and a connection to PostHog's hosted MCP server.

claude plugin marketplace add PostHog/ai-plugin

02
```
claude plugin install posthog@posthog
```

Installation and loading

The plugin installs for you in every project and loads the next time you start Claude Code, or after /reload-plugins in an open session.
To connect your PostHog account, start claude, type /mcp, select plugin:posthog:posthog and follow the browser prompts.

Good to know

The plugin includes PostHog's session-capture hook; PostHog's README says it sends sessions to LLM Analytics only when POSTHOG_LLMA_CC_ENABLED=true and POSTHOG_API_KEY are both set.
If you use the separate posthog-telemetry plugin, PostHog says to keep only one of the two, because both register the same hook.
On a self-hosted PostHog, this route's MCP connection won't reach your instance: the plugin's config is fixed to https://mcp.posthog.com/mcp, which routes to PostHog's US or EU region. POSTHOG_MCP_URL works only for the Gemini CLI extension.

What's inside

Files included with this skill.

View on GitHub

Same repository

adding-warehouse-person-properties
Sync columns from a synced data warehouse table onto PostHog person or group properties, so warehouse data becomes usable anywhere person and group properties already work: feature flag targeting, cohorts, insight filters and breakdowns, surveys, session replay filters, workflows, and the person profile. Use when the user wants to "add a person property from my warehouse", "enrich people with Stripe/Postgres/Salesforce data", "put ARR or plan tier on my persons", "target a feature flag by a warehouse column", "sync warehouse columns onto groups or organizations", or wants to inspect, backfill, disable, or debug an existing warehouse-backed person or group property.Read full description
analyzing-expensive-users
Analyze the most expensive users in AI observability and explain why they cost so much. Use when the user asks about top spenders, expensive users, per-user LLM cost, user-level cost drivers, or patterns behind high AI observability spend.Read full description
analyzing-experiment-session-replays
Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with different experiment variants, identify usability issues, compare behavior patterns between control and test groups, or get qualitative insights to complement quantitative experiment results. Also covers pairing the observed behavior with a linked survey when the user wants qualitative feedback beyond what recordings show.Read full description
assessing-heatmaps
Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by cross-referencing autocapture events on the same page, and can create a saved heatmap the user opens in PostHog, then summarizes the behavior and proposes improvements. TRIGGER when: user asks what a heatmap shows, why people aren't clicking something, where users rage-click, how far they scroll, what to change on a page based on heatmap/click data, or to 'analyze/assess/review the heatmap' for a URL. DO NOT TRIGGER when: the user only wants to create a saved heatmap screenshot with no analysis (use heatmaps-saved-create directly), or is asking about session replay in general (use investigating-replay).Read full description
auditing-endpoints
Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.Read full description
auditing-experiments-flags
Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.Read full description

Creating experiments

Core principle: draft first, iterate on details

The 3-step creation flow

Step 1: What are we testing?

Step 2: Who sees what variant?

Step 3: How to measure impact?

How to create

After creation

Related skills

MCP connection required

Install just this skill

Install the whole plugin

Add PostHog's marketplace, then install the plugin

What's inside

More skills

adding-warehouse-person-properties

analyzing-expensive-users

analyzing-experiment-session-replays

assessing-heatmaps

auditing-endpoints

auditing-experiments-flags