featurevisor
Feature flags, experiments, and remote config management with version control
Featurevisor is an agent skill that enables AI coding assistants to manage feature flags, A/B experiments, and remote configuration through version-controlled declarative workflows. By installing this skill, developers can prompt their AI agents with natural language instructions to create features, write rollout rules, debug evaluations, and integrate SDKs across JavaScript, Python, Go, Ruby, Swift, and many other languages. The skill transforms complex feature management tasks into conversational commands, allowing agents to handle progressive rollouts, segment targeting, and cross-environment promotion. It pairs with a local catalog viewer for real-time visual review of agent-generated changes.
Key Features
Use Cases
- 01Progressive feature rollouts with gradual percentage-based targeting through conversational commands
- 02A/B and multivariate experiment setup via natural language descriptions
- 03Debugging feature flag behavior for specific user segments or contexts
- 04Managing feature dependencies and deprecation workflows across environments
- 05Establishing role-based feature gating and entitlement rules through AI-assisted configuration
- 06Coordinating microfrontend feature releases across multiple teams
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
featurevisor — FAQ
What is the Featurevisor agent skill?+
The Featurevisor agent skill teaches AI coding assistants like Claude Code and Cursor how to manage feature flags, experiments, and remote configuration in Git-based Featurevisor projects. It enables natural language prompts for creating features, writing rollout rules, debugging evaluations, and integrating SDKs.
How do I install the Featurevisor skill in my AI agent?+
Run 'npx skills add featurevisor/featurevisor' in your Featurevisor project directory or application repository. The skill will be added via skills.sh and become available to your AI coding assistant immediately.
Which AI coding assistants work with the Featurevisor skill?+
The skill is compatible with Claude Code, Cursor, Codex, and OpenCode. It works in any AI agent that supports the skills.sh framework for agent capabilities.
What prerequisites are needed to use this skill?+
You need a Featurevisor project in a Git repository, a CI/CD pipeline for building datafiles, and a CDN or server for hosting generated JSON files. The skill itself requires Node.js to run the npx installation command.
Is the Featurevisor agent skill free to use?+
Yes, Featurevisor is open source under the MIT license and completely free to use. The skill is included in the official repository at no cost.
Can I review changes my AI agent makes to feature flags?+
Yes, run 'npx featurevisor catalog' locally to launch a browser-based visual catalog that shows every change your agent makes in real-time as it edits your feature configurations.
How do I install featurevisor?+
Open the source repository on GitHub and follow its README. featurevisor is a skill — MCP Agents Market links you directly to the official repo.
Is featurevisor free?+
featurevisor is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.