Skip to main content
Agent skill

LaunchDarkly Automation

Automate LaunchDarkly feature flag management -- list projects and environments, create and delete trigger workflows, and track code references via the Composio MCP integration.

Get started

Get the complete skill folder, including its scripts and reference files.

This workflow depends on an external MCP integration. Check the source for the server, account access and setup it requires.

·

When to use this skill

Use LaunchDarkly Automation when an AI agent needs a reusable SKILL.md workflow for this job: Automate LaunchDarkly feature flag management -- list projects and environments, create and delete trigger workflows, and track code references via the Composio MCP integration.

When not to use it

Skip LaunchDarkly Automation when the task is outside the productivity category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/launchdarkly-automation
# Save SKILL.md to ~/.claude/skills/launchdarkly-automation/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/launchdarkly-automation/SKILL.md. For a shared project, commit the folder at .claude/skills/launchdarkly-automation/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the LaunchDarkly Automation skill for this task: Use LaunchDarkly Automation when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

72/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
77/100
Practical detail
68/100
Source evidence
63/100
Source signals
80/100
Model compatibility evidence
  • claudeinferred

    The skill text mentions Claude or a closely associated term. This is keyword-derived compatibility; no hands-on model test is recorded.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# LaunchDarkly Automation

Automate your LaunchDarkly feature flag workflows -- enumerate projects and environments, create webhook-driven flag triggers, manage trigger lifecycle, and audit code references across repositories.

**Toolkit docs:** [composio.dev/toolkits/launch_darkly](https://composio.dev/toolkits/launch_darkly)

---

## Setup

1. Add the Composio MCP server to your client: `https://rube.app/mcp` 2. Connect your LaunchDarkly account when prompted (API key authentication) 3. Start using the workflows below

---

## Core Workflows

### 1. List Projects

Use `LAUNCH_DARKLY_LIST_PROJECTS` to discover all projects and their keys for subsequent operations.

``` Tool: LAUNCH_DARKLY_LIST_PROJECTS Inputs: - filter: string (e.g., "query:myproject" or "keys:proj1,proj2" or "tags:mytag") - expand: string (e.g., "environments" to include env list per project) - limit: integer (default 20) - offset: integer (pagination start index) - sort: string (e.g., "name" or "-name" for descending) ```

### 2. Get Environments for a Project

Use `LAUNCH_DARKLY_GET_ENVIRONMENTS` to list all environments within a project (production, staging, test, etc.).

``` Tool: LAUNCH_DARKLY_GET_ENVIRONMENTS Inputs: - project_key: string (required) -- e.g., "my-project", "default" - filter: string (e.g., "query:production") - limit: integer (default 20) - offset: integer (pagination) - sort: string (e.g., "name" or "-name") ```

### 3. Create a Flag Trigger Workflow

Use `LAUNCH_DARKLY_CREATE_TRIGGER_WORKFLOW` to set up automated flag toggles triggered by external events (webhooks, Datadog alerts, etc.).

``` Tool: LAUNCH_DARKLY_CREATE_TRIGGER_WORKFLOW Inputs: - project_key: string (required) - feature_flag_key: string (required) -- e.g., "new-feature", "enable-dark-mode" - environment_key: string (required) -- e.g., "production", "staging" - integration_key: string (default "generic-trigger") -- or "datadog", "honeycomb", "dynatrace" - instructions: array of objects (optional): - kind: "flag_action" (fixed) - action: "turnFlagOn" | "turnFlagOff" - comment: string (optional) -- description of the trigger purpose ```

The trigger generates a unique webhook URL that can be called to execute the configured flag action.

### 4. Delete a Flag Trigger Workflow

Use `LAUNCH_DARKLY_DELETE_TRIGGER_WORKFLOW` to permanently remove a trigger and its URL.

``` Tool: LAUNCH_DARKLY_DELETE_TRIGGER_WORKFLOW Inputs: - project_key: string (required) - feature_flag_key: string (required) - environment_key: string (required) - id: string (required) -- the trigger ID returned during creation ```

**Warning:** Deletion is irreversible. The trigger and its URL cannot be recovered.

### 5. List Code Reference Repositories

Use `LAUNCH_DARKLY_LIST_CODE_REFERENCE_REPOSITORIES` to track where feature flags are used in your codebase.

``` Tool: LAUNCH_DARKLY_LIST_CODE_REFERENCE_REPOSITORIES Inputs: - projKey: string (optional) -- filter by project key - flagKey: string (optional) -- filter by feature flag key - withBranches: string (any value to include branch data) - withReferencesForDefaultBranch: string (any value to include code refs for default branch) ```

**Note:** Code references is an Enterprise feature requiring `code-reference-repository` write permissions.

---

## Known Pitfalls

| Pitfall | Detail | |---------|--------| | Project key discovery | Always use `LAUNCH_DARKLY_LIST_PROJECTS` first to find valid project keys before calling other tools. | | Environment key format | Environment keys are lowercase slugs (e.g., "production", "test"), not display names. | | Trigger deletion is permanent | Once deleted via `LAUNCH_DARKLY_DELETE_TRIGGER_WORKFLOW`, the trigger URL is unrecoverable. | | Enterprise-only code refs | `LAUNCH_DARKLY_LIST_CODE_REFERENCE_REPOSITORIES` requires Enterprise plan and write permissions. | | Trigger instructions format | Each instruction object requires `kind: "flag_action"` (fixed constant) and `action` as either `turnFlagOn` or `turnFlagOff`. |

---

## Quick Reference

| Tool Slug | Description | |-----------|-------------| | `LAUNCH_DARKLY_LIST_PROJECTS` | List all projects with filtering and pagination | | `LAUNCH_DARKLY_GET_ENVIRONMENTS` | List environments within a project | | `LAUNCH_DARKLY_CREATE_TRIGGER_WORKFLOW` | Create a webhook-driven flag trigger | | `LAUNCH_DARKLY_DELETE_TRIGGER_WORKFLOW` | Permanently delete a flag trigger | | `LAUNCH_DARKLY_LIST_CODE_REFERENCE_REPOSITORIES` | List repos with code references to flags |

---

*Powered by [Composio](https://composio.dev)*

Intended uses

  • Use LaunchDarkly Automation when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.