Finding Experiments

by PostHog469d1773e9cbNo licenseListed Oct 8, 2026Updated Oct 8, 2026

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with disambiguation when multiple experiments match. Use when the user names or quotes an experiment ("split test demo", "the File engagement boost experiment", "onboarding retention test", "landing page hero experiment", "pricing experiment"), describes it loosely ("the signup experiment", "my pricing test", "the one with the new checkout"), uses a relative reference ("latest", "most recent", "the one I created yesterday"), filters by status (running, draft, paused, exposure frozen, stopped, archived), or otherwise refers to an experiment by anything other than its concrete ID.

Instructions onlyAI & Agents
AI-generated overview

Resolves natural-language references to PostHog experiments into concrete experiment IDs using the experiment-list tool.

What it does
This skill turns loose user references to a PostHog experiment — names, descriptions, relative terms, or status filters — into a concrete experiment ID. It browses the experiment-list tool from the Posthog-local MCP server and matches on name, recency, status, or feature flag key. When several experiments match, it lists them with name, status, and creation date and asks the user to choose; when none match, it reports that and suggests alternatives. It can then call experiment-get for full details such as metrics, flag details, and parameters.
When to use it
Use it when a user names, quotes, loosely describes, or refers to an experiment by anything other than its ID, including relative references like latest or most recent, or filters by status such as running, draft, paused, or archived. It is not needed when the experiment ID is already known from the conversation, a create response, or the user directly.
Requirements
Requires the Posthog-local MCP server with the experiment-list and experiment-get tools. Ships no scripts; instructions only.

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

text
User: "pause my signup experiment"
Agent:1. Calls experiment-list2. 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

Related skills

  • managing-experiment-lifecycle — act on the experiment once you've resolved its ID
  • diagnosing-experiment-results — investigate the experiment you found

Source and attribution

Source:PostHog/ai-plugininskills/finding-experimentsat commit469d177

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from PostHog/ai-plugin

Writing Simplified Technical English

PostHog

Applies ASD-STE100 simplified technical English rules to make agent-written prose unambiguous and actionable.

Writing & ContentOct 8, 2026

Working With Task Comments

PostHog

Reads and interprets comments on PostHog tasks, artifacts, and canvases through the PostHog MCP exec dispatcher.

Productivity & WorkflowOct 8, 2026

Working With Skills

PostHog

Guides agents in using PostHog's skill-* MCP tools to discover, read, create, update, and refactor skills.

AI & AgentsOct 8, 2026

Working With Scouts

PostHog

Operating manual for delegating watching jobs to PostHog Signals scouts, acting on their reports, and steering the fleet over time.

AI & AgentsOct 8, 2026

Validating And Publishing Canvases

PostHog

Validate and publish a canvas source project safely: the source-project shape, declared capabilities, reading the current version pointer, iterating on validation diagnostics, guarded publishing with expected_current_version_id, staging a draft build and promoting it, waiting out the queued build, and recovering from a 409 version_conflict or a 429 capacity limit without overwriting concurrent work. Use whenever a canvas edit is ready to save, a draft build is wanted, a canvas publish or build returns diagnostics or a conflict, or a task needs to understand canvas version history.

Awaiting classificationOct 8, 2026

Understanding Billing Usage

PostHog

Explains PostHog billing usage and spend from the customer's visible Billing MCP tools. Use when the user asks why usage or spend is high, which product or project is driving usage, what a usage type means, how to reduce usage, what changed over time, why they got a usage change alert, or whether a spike/drop alert was real or noisy. Also use before product-specific analytics skills when the user names a billable PostHog product metric such as events, recordings, feature flag requests, exceptions, survey responses, synced rows, logs, AI events, AI credits, or Inbox credits. Starts from Billing usage/spend tools, then routes to customer-visible product MCP surfaces for deeper investigation.

Awaiting classificationOct 8, 2026