Launchdarkly Flag Targeting
This walks Claude through the complete lifecycle of changing LaunchDarkly feature flag targeting: checking current state, applying rollouts or targeting rules, handling approval workflows when needed, and verifying the result. It covers the evaluation order that determines which users see what (individual targets beat rules, rules beat default rollout), and includes safety checks for production changes. The instructions map directly to LaunchDarkly's MCP server tools for toggling flags, updating percentage rollouts, managing targeting rules, and copying configurations between environments. One thing to note: it's opinionated about always confirming the environment first, which is smart given how easy it is to accidentally target production when you meant staging.
- skills.sh installs
- 2.5K
- GitHub stars
- 19
- last updated
- Jul 14, 2026
Install
$ npx -y skills add launchdarkly/agent-skills --skill launchdarkly-flag-targeting --agent claude-codeInstalls into .claude/skills of the current project.
Files
LaunchDarkly Flag Targeting & Rollout
You're using a skill that will guide you through changing who sees what for a feature flag. Your job is to understand the current state of the flag, figure out the right targeting approach for what the user wants, make the changes safely, and verify the resulting state.
Prerequisites
This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment.
Required MCP tools:
get-flags: understand current state before making changestoggle-flag: turn targeting on or off for a flag in an environmentupdate-rollout: change the default rule (fallthrough) variation or percentage rolloutupdate-targeting-rules: add, remove, or modify custom targeting rulesupdate-flag-targeting: add or remove specific users/contexts from individual targeting
Optional MCP tools:
copy-flag-config: copy targeting configuration from one environment to anothercreate-approval-request: create an approval request when direct changes are blockedget-approval-requests: check on pending approval requests for a flagapply-approval-request: apply an already-approved approval request
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/launchdarkly/agent-skills
- Category
- AI & Agent Building
- First seen
- May 16, 2026
More from launchdarkly/agent-skills
All 41- Aiconfig Create2.3K
- Aiconfig Projects2.3K
- Aiconfig Tools2.3K
- Aiconfig Update2.3K
- Aiconfig Variations2.3K
- Launchdarkly Metric Choose2.3K
- Launchdarkly Metric Create2.3K
- Launchdarkly Metric Instrument2.3K
- Aiconfig Online Evals2.2K
- Aiconfig Targeting2.2K
- Aiconfig Ai Metrics2K
- Aiconfig Custom Metrics2K
- Aiconfig Migrate2K
- Apply2K
- Detect2K
- First Flag2K
- Launchdarkly Experiment Setup2K
- Launchdarkly Guarded Rollout2K
- Mcp Configure2K
- Plan2K
- Sdk Install2K
- Aiconfig Agent Graphs1.8K
- Aiconfig Snippets1.8K
- Agent Graphs1.3K
Recommended
More AI & Agent Building
speckit-tasksdceoy/speckit-agent-skillsGenerate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.2.5Kskills.sh installs
ml-paper-writingorchestra-research/ai-research-skillsWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying ci2.5Kskills.sh installs
frontend-design-ui-uxulpi-io/skillsProduce a distinctive, LOCKED design language plus an implementation-ready UX/UI spec, written to `.ulpi/design/`: a per-brief visual identity (palette, type, s2.4Kskills.sh installs
elite-longterm-memorynextfrontierbuilds/elite-longterm-memoryUltimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose2.4Kskills.sh installs
laravel-best-practicesasyrafhussin/agent-skillsLaravel 13 conventions and best practices. Use when creating controllers, models, migrations, validation, services, or structuring Laravel applications. Trigger2.4Kskills.sh installs
frontend-designjwynia/agent-skillsCreate distinctive, production-grade frontend interfaces with high design quality. Provides analysis tools for auditing existing designs and generation tools fo2.3Kskills.sh installs