Launchdarkly Flag Discovery

This is your audit layer for LaunchDarkly feature flags. It surfaces cleanup candidates by staleness, checks removal readiness with a safety verdict system (safe/caution/blocked), and helps you understand what's actually happening across environments. The workflow pushes you to categorize flags into actionable buckets rather than just listing them. The removal readiness tool is the standout piece here since it orchestrates multiple API calls to check for blockers like dependent flags or active requests. Good for quarterly cleanups or when you inherit a project and need to understand the flag landscape. It won't remove anything, just tells you what's worth investigating.

skills.sh installs: 2.5K
GitHub stars: 19
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add launchdarkly/agent-skills --skill launchdarkly-flag-discovery --agent claude-code

Installs into .claude/skills of the current project.

Files

LaunchDarkly Flag Discovery

You're using a skill that will guide you through auditing and understanding the feature flag landscape in a LaunchDarkly project. Your job is to explore the project, assess the health of its flags, identify what needs attention, and provide actionable recommendations.

Prerequisites

This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.

Required MCP tools:

get-flags: search and browse flags with filtering by state, type, tags; with flagKey, get full configuration for a single flag in a specific environment
get-flag-status-across-envs: check a flag's lifecycle status across all environments

Optional MCP tools (enhance depth):

search-stale-flags: find flags that are candidates for cleanup, sorted by staleness
get-flag-health: get combined health view for a single flag (merges status + config)
get-removal-readiness: detailed safety check for a specific flag