Search everything...

Stats

Actions

Available In

growthbook

Name: growthbook
Author: growthbook

By growthbook

A suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.

Publisher marketplacegrowthbook@growthbook-skills · marketplace and plugin share one repository (growthbook/skills)

npx claudepluginhub growthbook/skills --plugin growthbook

Popularity

Stars

Top 25%

Med: 0·Avg: 842

Copy clicks

Med: 0·Avg: 2

What's Inside

Skills25

experiment-stop

/experiment-stop

Stop a running GrowthBook experiment via the REST API, optionally declaring a winning variation and rolling it out to 100% of eligible traffic. Use when the user says "stop this experiment", "end the A/B test", "declare a winner for X", "ship the winning variation", "roll back the test", or "we're done with this experiment". For interpreting results before deciding, use experiment-analyze first.

analytics-explore

/analytics-explore

Build and run a GrowthBook Product Analytics chart via the REST API — visualize a metric over time, aggregate a fact table, or chart a raw warehouse table, then return the numbers plus a deep link to the chart. Use when the user asks "show me signups by country", "chart daily active users", "how many orders last week", "plot revenue over time", "break that down by plan", or any "show me / chart / plot / how many" question about product data. For discovering what metrics and fact tables exist first, use metric-search. For experiment results, use experiment-analyze — this skill is for general analytics, not A/B test readouts.

experiment-analyze

/experiment-analyze

Fetch results for a GrowthBook experiment, refresh the snapshot only when the cached data is over 24 hours old, then interpret. Use when the user asks "what are the results of X", "analyze this experiment", "is X winning", "did the test work", "show me the results", or "dig into the dimensions". Reads only — does not stop or modify the experiment. For stopping after you've seen results, use experiment-stop.

experiment-brainstorm

/experiment-brainstorm

Propose new experiment ideas grounded in the team's past stopped experiments via the GrowthBook REST API. Use when the user asks "what should we test next", "give me experiment ideas", "brainstorm A/B tests", "what's worth testing", or "ideas for experiments". Proposes only — does not create experiments. For designing a specific test, use experiment-design. For reading results of one, use experiment-analyze.

experiment-design

/experiment-design

Help the user design a well-formed GrowthBook experiment before it's launched. Use when the user asks to "design an A/B test", "set up an experiment", "test X vs Y", "configure an experiment", or "what should we measure". Produces a complete spec — hypothesis, variations, primary metric, guardrails, sample size — ready to hand off. Does not create the experiment in GrowthBook. For launching, use experiment-launch. For ideas grounded in past results, use experiment-brainstorm first.

Stats

Version1.0.0

LanguageJavaScript

Stars18

MaintenanceExcellent

LicenseMIT

Last CommitJul 15, 2026

AddedJul 19, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Own this plugin?

Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).

Available In

growthbook-skills18 nimble-gravity-knowledge-work-plugins sg-safe-path-control

README

GrowthBook Agent Skills

GrowthBook is an open source Feature Flagging and Experimentation platform.

Agent skills for GrowthBook — feature flagging and experimentation playbooks for Claude Code, Cursor, and other agent tools that follow the Agent Skills standard.

The skills call the GrowthBook REST API directly through a small bundled helper. No MCP server required.

What's included

Setup

Skill	What it does
`gb-setup`	Walks you through API key, owner, and (self-hosted) API URL. Validates against the live API and writes `~/.config/growthbook/.env` with `chmod 600`. Re-run anytime to update.

Feature flags — Revision lifecycle

Every flag change goes through a draft revision before going live. These three skills handle the full draft → review → publish flow.

Skill	What it does
`flag-revisions`	List and inspect open drafts, check who owns them, see approval status, create or discard drafts. The "what's in flight?" skill.
`flag-review`	Request an approval review on a draft, or submit a review (approve / request-changes / comment).
`flag-publish`	Publish a draft live, resolve merge conflicts (rebase), discard, or revert to a prior revision.

Feature flags — Operations

Skill	What it does
`flag-create`	Create a new feature flag — collision check, value type, environments, defaultValue. Ships disabled everywhere.
`flag-metadata`	Update a flag's description, owner, project, tags, custom fields, or JSON schema.
`flag-default-value`	Change the fallback value served when no rules match.
`flag-toggle`	Enable or disable a flag in a specific environment (the kill switch). Review-gated.
`flag-prerequisites`	Gate an entire flag on another boolean flag being on.
`flag-cleanup`	Archive or delete a stale flag, walking through code-site inlining first. Detects temporary rollouts, handles code references, two-step safety gate (archive → verify → delete).

Feature flags — Rules

Skill	What it does
`flag-rules`	Entry point: list rules, delete a rule, reorder, or route to the right rule skill.
`flag-targeting`	Add, edit, or remove force / rollout rules — with conditions, saved groups, and rule-level prerequisites. Full operator reference for MongoDB-style conditions.
`flag-schedule`	Time-gate a rule: set a start and/or end datetime for automatic activation.
`flag-ramp`	Multi-step ramp schedule: progressively increase coverage over time with per-step intervals or manual approval gates. Includes full live ramp management (advance, pause, rollback, approve-step).
`flag-monitoring`	Monitored progressive rollout ("safe rollout"): ramp schedule with guardrail metric monitoring and optional auto-rollback.
`flag-experiment`	Add an experiment-ref rule to a flag to run an A/B test through it.

Feature flags — Discovery

Skill	What it does
`flag-search`	Search, list, and audit flags by project, tag, owner, environment state, or staleness. Read-only.
`flag-graph`	Trace a flag's dependency graph: what it depends on (prerequisites), what depends on it, linked experiments and holdouts.

Experimentation

Skill	What it does
`experiment-brainstorm`	Propose new experiment ideas grounded in your team's past stopped-experiment history.
`experiment-design`	Walk through hypothesis, variations, primary metric, guardrails, and sample size to produce a launchable spec. Reads only.
`experiment-launch`	End-to-end launch: create the experiment, prep or reuse the feature flag, wire the experiment-ref rule, and call `/start`. Works for both experiment-first and flag-first workflows. Handles approval and pre-launch checklist failure paths.
`experiment-analyze`	Trigger a fresh snapshot, poll until ready, then interpret results (SRM check, lifts, CIs, guardrails).
`experiment-stop`	Stop a running experiment, optionally declaring a winner and enabling a temporary rollout. Full post-stop flag disposition guidance.

Product analytics

Turn the metrics and fact tables you already use for experimentation into ad-hoc charts with GrowthBook's Product Analytics Explorer.

Skill	What it does
`metric-search`	Search, list, and audit fact metrics and fact tables — definitions, columns, and what's chartable. Read-only.
`analytics-explore`	Build and run a chart: a metric over time, a fact-table aggregation, or a raw warehouse table. Returns the numbers plus a deep link to the rendered chart.

Install

1. Install the plugin

Claude Code:

/plugin marketplace add growthbook/skills
/plugin install growthbook@growthbook-skills

View full README on GitHub

Similar Plugins

launchdarkly

20·

LaunchDarkly agent skills and MCP servers for feature flag management, AgentControl, and metrics

v1.0.0

launchdarkly

experiment-tracker

53·

PROACTIVELY use this agent when experiments are started, modified, or when results need analysis. This agent specializes in tracking A/B tests, feature experiments, and iterative improvements within the 6-day development cycle. Should be triggered automatically when experimental code paths or feature flags are introduced. Examples:\n\n<example>\nContext: When implementing feature flags or A/B test variants\nuser: "Add a feature flag to test the new onboarding flow"\nassistant: "I've implemented the feature flag for the onboarding flow A/B test. Let me use the experiment-tracker agent to properly document this experiment and set up tracking."\n<commentary>\nEvery feature flag represents an experiment that needs proper tracking and success metrics.\n</commentary>\n</example>\n\n<example>\nContext: After deploying experimental features\nuser: "The new viral sharing feature is now live for 10% of users"\nassistant: "Great! The viral sharing feature is deployed. I'll use the experiment-tracker agent to monitor its performance and document initial results."\n<commentary>\nLive experiments need immediate tracking setup to capture valuable data from the start.\n</commentary>\n</example>\n\n<example>\nContext: When reaching experiment milestones\nuser: "It's been a week since we launched the TikTok integration test"\nassistant: "Perfect timing for analysis. Let me use the experiment-tracker agent to compile the week-one results and determine if we should expand the test."\n<commentary>\nRegular experiment checkpoints ensure data-driven decisions about feature rollouts.\n</commentary>\n</example>\n\n<example>\nContext: Before making product decisions\nuser: "Should we keep the AI avatar feature or remove it?"\nassistant: "Let me analyze the experiment data to inform this decision. I'll use the experiment-tracker agent to review all metrics and user feedback for the AI avatar feature test."\n<commentary>\nProduct decisions should be backed by experiment data, not gut feelings.\n</commentary>\n</example>

4mo

v1.0.0

devsforge

feature-flag

13·

Feature flag implementation, management, and cleanup. Handles flag creation, gradual rollout strategies, A/B testing wiring, stale flag detection, and safe flag removal. Supports LaunchDarkly, Unleash, GrowthBook, Statsig, custom env-var flags, and database-backed toggles. Use when adding gated features, rolling out gradually, or cleaning up old flags.

1mo

v1.0.0

Andersonlimahw

posthog

64·1·

Access PostHog analytics, feature flags, experiments, error tracking, and insights directly from your AI coding tool. Optionally capture Claude Code sessions to PostHog LLM Analytics.

v1.1.54

PostHog

featbit-featbit-skills

11·

Official FeatBit feature flag management plugin for Claude Code, enabling controlled feature rollouts and A/B testing integrations.

2mo

v2.1.2

featbit

vercel-flags

608·

Vercel's feature flags system for managing feature toggles and controlled rollouts in production.

v@vercel/[email protected]

vercel

growthbook

Popularity

What's Inside

Confidence

README