Index of every page on this site: llms.txt
All skills
launchdarkly avatar

/configs-update

@f0ee110 official
Run it yourself

Update, retire, and delete LaunchDarkly configs and their variations. Use when you need to modify config properties, change model parameters, update instructions or messages, take unused configs out of service, or permanently remove them.

Use this Skill: https://skilld.dev/gh/launchdarkly/ai-tooling/configs-update

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

README.md

≈338 tokens on demand. Your agent reads this file only when SKILL.md points to it.

LaunchDarkly Config Update Skill

An Agent Skill for updating, retiring, and deleting configs and their variations.

Overview

This skill teaches agents how to:

  • Assess config health using get-agent-configs with section: "health" before making changes
  • Update config metadata (name, description, tags) via update-agent-config (resource: "config")
  • Modify variation instructions, messages, models, and parameters via update-agent-config (resource: "variation")
  • Retire configs by turning targeting off (reversible) or delete them (permanent, irreversible)
  • Verify changes via get-agent-configs

Installation (Local)

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

Prerequisites

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

Usage

Update the instructions for our support agent config
Switch the content writer config to use Claude instead of GPT-4
Retire the old chatbot config

Structure

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

Related

License

Apache-2.0

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts11d3 checks · Risk SAFE
  • Gen Agent Trust Hub15d

    This skill is safe. It enables agents to manage LaunchDarkly AI configurations through official MCP tools. It implements strong safety practices, including mandatory user confirmation for destructive actions, verification of changes, and suggesting reversible alternatives to permanent deletion. All external resources belong to the official vendor.

  • Socket11d

    No alerts

  • Snyk15d

    Risk: LOW · No issues

Signed by skilld at f0ee110. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 weeks ago
compatibility
Requires the remotely hosted LaunchDarkly MCP server
metadata
{
  "author": "launchdarkly",
  "version": "1.0.0-experimental"
}
  • MCP
  • launchdarkly
  • config-management
  • ai-models
  • lifecycle
  • variations
  • archival

README badge

README badge for launchdarkly/ai-tooling/configs-update

Modifies, archives, and deletes LaunchDarkly AI configs and their variations through the LaunchDarkly MCP server. Use this skill to update config metadata, change model parameters, swap instructions or messages, or retire configs—with built-in health checks and verification steps to catch orphaned tools and missing models before publishing changes.

Generated from the current SKILL.md.

What's the difference between archiving and deleting a config?
Archiving is reversible and hides the config from active lists while preserving it; deletion is permanent and irreversible. Always suggest archiving unless the user explicitly requests permanent removal.
Does this skill require any setup?
Yes. It requires the remotely hosted LaunchDarkly MCP server to be configured in your environment with the required MCP tools (get-ai-config-health, get-ai-config, update-ai-config, update-ai-config-variation).
Can I update multiple config properties at once?
No. The skill guidance is to make incremental changes and verify each one rather than batching updates together.
What should I check before making changes?
Always run get-ai-config-health first to assess the config's current state and detect issues like missing models, orphaned tool references, or empty configs. Then use get-ai-config to review full details before modifying.

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