launch_darkly-automation
Lets your agent automate tasks in LaunchDarkly. It manages flags, environments, segments, and rollouts in a simplified way.
What it does
This tool lets you control LaunchDarkly, a service for managing software features, using text commands. You can automate tasks like creating or changing 'feature flags' (features that can be turned on or off), managing environments, and setting up how features are rolled out to users.
When to use it
- ✓When you need to create or update 'feature flags' without touching code.
- ✓To configure how new features are released to a user group.
- ✓When managing different testing or production environments for your software.
Example of what to ask your AI
“Create a new 'feature flag' called 'new-dashboard' and enable it for 50% of users.”
Want more? Open the sections below.
How to use
The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.
Skill link
Ready-to-paste message
How it works
The tool connects to LaunchDarkly through a system called Rube MCP. First, it checks which commands are available and how to use them, then it executes the action you requested, like creating a flag or changing its settings.
Installation
Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.
In the terminal (Claude Code, Codex, Cursor), in your project folder:
npx skills add ComposioHQ/awesome-claude-skills --skill launch_darkly-automationOr download just the file:
curl -L https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/launch_darkly-automation/SKILL.md -o SKILL.mdTechnical content (original SKILL.md)
Original text by the author, straight from GitHub.
LaunchDarkly Automation via Rube MCP
Automate LaunchDarkly operations through Composio's LaunchDarkly toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/launch_darkly
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active LaunchDarkly connection via
RUBE_MANAGE_CONNECTIONSwith toolkitlaunch_darkly - Always call
RUBE_SEARCH_TOOLSfirst to get current tool schemas
Setup
Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitlaunch_darkly - If connection is not ACTIVE, follow the returned auth link to complete setup
- Confirm connection status shows ACTIVE before running any workflows
Tool Discovery
Always discover available tools before executing workflows:
RUBE_SEARCH_TOOLS: queries=[{"use_case": "feature flags, environments, segments, and rollout management", "known_fields": ""}]
This returns:
- Available tool slugs for LaunchDarkly
- Recommended execution plan steps
- Known pitfalls and edge cases
- Input schemas for each tool
Core Workflows
1. Discover Available LaunchDarkly Tools
RUBE_SEARCH_TOOLS:
queries:
- use_case: "list all available LaunchDarkly tools and capabilities"
Review the returned tools, their descriptions, and input schemas before proceeding.
2. Execute LaunchDarkly Operations
After discovering tools, execute them via:
RUBE_MULTI_EXECUTE_TOOL:
tools:
- tool_slug: "<discovered_tool_slug>"
arguments: {<schema-compliant arguments>}
memory: {}
sync_response_to_workbench: false
3. Multi-Step Workflows
For complex workflows involving multiple LaunchDarkly operations:
- Search for all relevant tools:
RUBE_SEARCH_TOOLSwith specific use case - Execute prerequisite steps first (e.g., fetch before update)
- Pass data between steps using tool responses
- Use
RUBE_REMOTE_WORKBENCHfor bulk operations or data processing
Common Patterns
Search Before Action
Always search for existing resources before creating new ones to avoid duplicates.
Pagination
Many list operations support pagination. Check responses for next_cursor or page_token and continue fetching until exhausted.
Error Handling
- Check tool responses for errors before proceeding
- If a tool fails, verify the connection is still ACTIVE
- Re-authenticate via
RUBE_MANAGE_CONNECTIONSif connection expired
Batch Operations
For bulk operations, use RUBE_REMOTE_WORKBENCH with run_composio_tool() in a loop with ThreadPoolExecutor for parallel execution.
Known Pitfalls
- Always search tools first: Tool schemas and available operations may change. Never hardcode tool slugs without first discovering them via
RUBE_SEARCH_TOOLS. - Check connection status: Ensure the LaunchDarkly connection is ACTIVE before executing any tools. Expired OAuth tokens require re-authentication.
- Respect rate limits: If you receive rate limit errors, reduce request frequency and implement backoff.
- Validate schemas: Always pass strictly schema-compliant arguments. Use
RUBE_GET_TOOL_SCHEMASto load full input schemas whenschemaRefis returned instead ofinput_schema.
Quick Reference
| Operation | Approach |
|---|---|
| Find tools | RUBE_SEARCH_TOOLS with LaunchDarkly-specific use case |
| Connect | RUBE_MANAGE_CONNECTIONS with toolkit launch_darkly |
| Execute | RUBE_MULTI_EXECUTE_TOOL with discovered tool slugs |
| Bulk ops | RUBE_REMOTE_WORKBENCH with run_composio_tool() |
| Full schema | RUBE_GET_TOOL_SCHEMAS for tools with schemaRef |
Toolkit docs: composio.dev/toolkits/launch_darkly
FAQ
Do I need any special passwords?
You need to connect your LaunchDarkly account to Rube MCP. This usually involves following a link to authorize the connection, without needing direct passwords.
What are 'feature flags'?
'Feature flags' are like switches that allow you to turn software features on or off without needing a new installation or code change. This helps test new ideas safely.
Can I do multiple things at once?
Yes, you can chain multiple actions, like creating a flag and then configuring its rollout, or even perform bulk operations for many items at once.
Details
Original description by the author
Automate LaunchDarkly tasks via Rube MCP (Composio): feature flags, environments, segments, and rollout management. Always search tools first for current schemas.
Popularity
- GitHub stars
- 77k
- Ranking position
- #1302
- License
- —
- Updated
- 9/18/2026
Comments
- …
More skills from this repository
artifacts-builder
Helps your agent build complex user interfaces. It uses modern technologies to create rich, interactive web pages.
ComposioHQ/awesome-claude-skills
brand-guidelines
Helps your agent apply official brand colors and fonts to materials. It's useful for maintaining visual identity in any piece that needs to look like the company's.
ComposioHQ/awesome-claude-skills
canvas-design
Lets your agent create original visual art in .png and .pdf. Use it when the user asks to create a poster, art, or other static design.
ComposioHQ/awesome-claude-skills
changelog-generator
Helps your agent create user-facing release notes from code commits. It transforms technical information into easy-to-understand text.
ComposioHQ/awesome-claude-skills
Similar skills
benchmark
Helps your agent measure code speed and performance. It's useful for ensuring things are fast and finding slowness issues.
affaan-m/ECC
content-hash-cache-pattern
Lets your agent use content hashes to cache file processing results. This avoids repeated processing and auto-invalidates the cache when content changes. Useful for speeding up slow tasks.
affaan-m/ECC
parallel-execution-optimizer
Makes your agent speed up complex tasks by breaking them into smaller parts and running them in parallel. It ensures everything is verified at the end.
affaan-m/ECC