skilld
All skills
launchdarkly avatar

/tools

@add614f official
by launchdarklylaunchdarkly/agent-skills25 stars
10

Give your agents capabilities through tools (function calling). Helps you identify what your agent needs to do, create tool definitions, and attach them to config variations.

Ask your Agent

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

This session only. Nothing lands on disk.

README.md

≈301 tokens on demand. Your agent reads this file only when SKILL.md points to it.

LaunchDarkly Config Tools Skill

An Agent Skill for creating tools (function calling) and attaching them to config variations. Guides identifying capabilities, creating tool schemas, and verifying attachment.

Overview

This skill teaches agents how to:

  • Identify what capabilities the agent needs
  • Create tool definitions using the create-ai-tool MCP tool
  • Attach tools to config variations via update-ai-config-variation
  • Verify tools are properly connected via get-ai-config

Installation (Local)

Copy skills/agentcontrol/tools/ into your agent client's skills path.

Prerequisites

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

Usage

Add a database search tool to our support agent config
Create tools for the content assistant to call our API

Structure

tools/
├── SKILL.md
└── README.md

Related

License

Apache-2.0

Source: SKILL.md on GitHub

Third-party checks

No alerts3mo3 checks · Risk SAFE
  • Gen Agent Trust Hub3mo

    The skill provides a workflow and code examples for managing AI tool definitions and configurations within LaunchDarkly. While it functions as a legitimate configuration utility, it handles sensitive schema data that could be a vector for indirect prompt injection if not properly sanitized by the implementation using it.

  • Socket3mo

    No alerts

  • Snyk3mo

    Risk: LOW · No issues

Provenance

Signed by skilld at add614f. 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 4 months ago

Capability

compatibility
Requires the remotely hosted LaunchDarkly MCP server
metadata
{
  "author": "launchdarkly",
  "version": "1.0.0-experimental"
}

Topics

  • MCP
  • launchdarkly
  • function-calling
  • tools
  • agent-config
  • schema
  • tool-definitions
  • openai
  • anthropic
  • bedrock

README badge

README badge for launchdarkly/agent-skills/tools

What it does

Guides agents through adding tool (function calling) capabilities using the LaunchDarkly MCP server. Covers creating tool definitions with JSON schemas, attaching them to config variations, and verifying attachment — with provider-specific conversion snippets for OpenAI, Anthropic, Bedrock, Gemini, LangChain, and Strands.

Generated from the current SKILL.md.

Frequently asked

Does this skill work with my LLM provider?
Yes. The skill covers OpenAI, Anthropic, Bedrock, Gemini, LangChain, LangGraph, CrewAI, AutoGen, and Strands Agents. LaunchDarkly stores the tool schema once; your application converts it to the shape your provider SDK expects at call time.
Do I need to write the tool implementation code?
No. This skill creates tool definitions and attaches them to config variations in LaunchDarkly. Your application code owns the handlers that actually execute the tools — LaunchDarkly stores only the schema.
What if a tool with that key already exists?
If you get a 409 conflict, use the existing tool or create a new one with a different key. Always verify the tool is attached to your config variation afterward.
Can I attach tools while creating a config?
No. Create the config first, then use this skill to create tool definitions and attach them to variations afterward.
What happens if I include other fields like instructions in the tool-attachment request?
Don't do that. Send only the `tools` field in the PATCH request. Including other fields silently overwrites UI edits and can resurrect stale values. If you need to update instructions or model settings, do that separately.

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