skilld
All skills
launchdarkly avatar

/configs-targeting

@ef54971 official
by launchdarklylaunchdarkly/agent-skills25 stars
10

Configure config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts.

Ask your Agent

Use this Skill: https://skilld.dev/gh/launchdarkly/agent-skills/configs-targeting

This session only. Nothing lands on disk.

README.md

≈328 tokens on demand. Your agent reads this file only when SKILL.md points to it.

LaunchDarkly Config Targeting Skill

An Agent Skill for configuring config targeting rules via the LaunchDarkly API.

Overview

This skill teaches agents how to:

  • Turn targeting on/off for configs
  • Add attribute-based targeting rules
  • Configure percentage rollouts for A/B testing
  • Set fallthrough (default) variations
  • Target individual contexts or segments

Installation (Local)

Copy skills/agentcontrol/configs-targeting/ into your agent client's skills path.

Prerequisites

  • LaunchDarkly API access token with ai-configs:write permission
  • Existing config with variations (use configs-create skill)
  • Understanding of contexts (see context-basic skill)

Usage

Set up targeting rules for model-selector: route sonnet requests to the Sonnet variation, mistral to Mistral, and default to Opus
Add a percentage rollout: 60% to variation A, 40% to variation B for premium users

Structure

configs-targeting/
├── SKILL.md
└── README.md

Related

License

Apache-2.0

Source: SKILL.md on GitHub

Third-party checks

No alerts2d3 checks · Risk SAFE
  • Gen Agent Trust Hub2d

    The skill provides instructions and tools for managing LaunchDarkly configuration targeting rules. It includes methods for detecting API tokens from environment variables or local configuration files and provides code to interact with the official LaunchDarkly API. All identified behaviors are consistent with the skill's stated administrative purpose.

  • Socket2d

    No alerts

  • Snyk2d

    Risk: LOW · No issues

Provenance

Signed by skilld at ef54971. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 3 days ago

Capability

compatibility
Requires LaunchDarkly API access token with ai-configs:write permission.
metadata
{
  "author": "launchdarkly",
  "version": "0.1.0"
}

Topics

  • API
  • launchdarkly
  • feature-flags
  • targeting
  • rollouts
  • segments
  • config-management
  • semantic-patch

README badge

README badge for launchdarkly/agent-skills/configs-targeting

What it does

Configures targeting rules for LaunchDarkly AI configs to control which variations serve to different contexts via percentage rollouts, attribute-based rules, and segment targeting. Uses the LaunchDarkly semantic patch API with individual targets, custom rules, and fallthrough defaults evaluated in order.

Generated from the current SKILL.md.

Frequently asked

Does this skill work with LaunchDarkly feature flags or only configs?
This skill targets LaunchDarkly configs (AI-specific targeting) only, not feature flags. The semantic patch API and instruction set are specific to the ai-configs endpoint.
Do I need to fetch variation IDs before setting up targeting rules?
Yes. The skill requires variation UUIDs (not keys) to configure rules. You must call the GET targeting endpoint first to retrieve the _id field for each variation.
Can I use turnTargetingOn to enable a config?
No. The turnTargetingOn instruction does not work for configs. Instead, use updateFallthroughVariationOrRollout to set the fallthrough to an enabled variation.
What permissions does my API token need?
Your LaunchDarkly API token must have ai-configs:write permission to modify targeting rules.
Does this support percentage rollouts and segment targeting?
Yes. The skill supports percentage rollouts via percentageRolloutConfig, attribute-based rules, individual context targeting, and segment targeting via segmentMatch clauses.

Generated from the current SKILL.md. These answers refresh after source changes.