@launchdarkly

launchdarkly-metric-instrument guides instrumentation of track() calls across server and client SDKs, with detection of existing patterns, placement validation, and event verification via the launchdarkly mcp server.

launchdarkly-flag-targeting guides agents through safe feature flag targeting changes by first understanding current state, selecting the right mutation tool, running safety checks, applying changes, and verifying results.

aiconfig-online-evals enables attachment of llm-as-a-judge evaluators to launchdarkly ai config variations for automated quality scoring. supports built-in judges (accuracy, relevance, toxicity) and custom domain-specific judges with configurable sampling rates.

detect identifies repository stack for launchdarkly sdk onboarding by scanning language indicators, package managers, monorepo layouts, entrypoints, and existing sdk usage. confirms app target and sdk choice before proceeding to integration planning.

launchdarkly-metric-create guides users through setting up custom metrics by validating event flow, checking for duplicates, proposing configuration, and verifying creation via the LaunchDarkly API.

aiconfig-create guides users through LaunchDarkly AI config setup, covering shell creation, variation configuration, and verification. emphasizes critical targeting step before SDK evaluation to avoid false-positive failure diagnostics.

apply covers LaunchDarkly SDK installation and initialization across single or dual-SDK tracks, with explicit dual-SDK validation and credential timing guardrails to prevent incomplete setups.

generates a launchdarkly sdk integration plan by matching detected stack to appropriate sdk type(s), identifying files to modify, and documenting required configuration steps.

first-flag guides users through creating and toggling a feature flag in launchdarkly, with optional integration to the flag-create skill and fallback to manual api or ldcli flows. covers credential handling and state verification steps.

aiconfig-update manages the full lifecycle of LaunchDarkly AI configs including updates, archival, and deletion. requires MCP server integration and health assessment before changes.

launchdarkly-metric-choose guides users to select appropriate metrics for experiments and rollouts by inventorying available metrics, checking event activity, and surfacing auto-attached policies.

sdk-install orchestrates three nested skills (detect, plan, apply) to install and initialize the appropriate launchdarkly sdk for a project, deferring credential collection to the apply phase per parent onboarding workflow.

launchdarkly-guarded-rollout guides configuration of progressive feature releases with staged traffic increases and metric monitoring, but lacks actionable step-by-step procedure and explicit rollback criteria.

mcp-configure handles launchdarkly hosted mcp server setup during onboarding, enabling oauth-authenticated flag management tools. covers cursor and similar agents, with fallback guidance for restricted regions.

aiconfig-custom-metrics covers lifecycle management of business metrics (create, track, retrieve, update, delete) via launchdarkly api and sdk, with credential detection from config files and environment variables.

aiconfig-projects provides guidance for setting up launchdarkly project management within codebases, though the actual implementation steps remain largely undefined and execution flow is unclear.

deprecated redirect skill with no executable content. points users to configs-variations instead. do not invoke.

Create and configure LaunchDarkly feature flags in a way that fits the existing codebase. Use when the user wants to create a new flag, wrap code in a flag,…

Control LaunchDarkly feature flag targeting including toggling flags on/off, percentage rollouts, targeting rules, individual targets, and copying flag…

Safely remove a feature flag from code while preserving production behavior. Use when the user wants to remove a flag from code, delete flag references, or…

Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about…

Onboard a project to LaunchDarkly: kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first…

DEPRECATED redirect — this skill was renamed to tools. Do not use this skill; invoke tools instead. Kept only so old references to aiconfig-tools still point…

Create and configure LaunchDarkly feature flags in a way that fits the existing codebase. Use when the user wants to create a new flag, wrap code in a flag,…

Safely remove a feature flag from code while preserving production behavior. Use when the user wants to remove a flag from code, delete flag references, or…

Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about…

Onboard a project to LaunchDarkly: kickoff roadmap, resumable log, explore repo, MCP, companion flag skills, nested SDK install (detect/plan/apply), first…

Set up and run experiments in LaunchDarkly. Create experiments with metrics, treatments, and flag config, start iterations to collect data, swap design between…

DEPRECATED redirect — this skill was renamed to configs-targeting. Do not use this skill; invoke configs-targeting instead. Kept only so old references to…

DEPRECATED redirect — this skill was renamed to built-in-metrics. Do not use this skill; invoke built-in-metrics instead. Kept only so old references to…

DEPRECATED redirect — this skill was renamed to migrate. Do not use this skill; invoke migrate instead. Kept only so old references to aiconfig-migrate still…

DEPRECATED redirect — this skill was renamed to agent-graphs. Do not use this skill; invoke agent-graphs instead. Kept only so old references to…

DEPRECATED redirect — this skill was renamed to snippets. Do not use this skill; invoke snippets instead. Kept only so old references to aiconfig-snippets…