Launchdarkly Flag Cleanup

{
  "name": "launchdarkly-flag-cleanup",
  "description": "Safely automate feature flag cleanup workflows using LaunchDarkly MCP server",
  "version": "1.0.0-experimental",
  "author": "LaunchDarkly",
  "repository": "https://github.com/launchdarkly/ai-tooling",
  "skills": ["./"],
  "tags": [
    "launchdarkly",
    "feature-flags",
    "feature-management",
    "stale-flags",
    "tech-debt",
    "cleanup",
    "code-removal",
    "devops",
    "mcp"
  ],
  "requirements": {
    "mcp-servers": ["@launchdarkly/mcp-server"]
  }
}


# LaunchDarkly Flag Cleanup Skill

An Agent Skill for safely automating feature flag cleanup workflows using LaunchDarkly as the source of truth.

## Overview

This skill teaches agents how to:
- Determine if a feature flag is ready for removal
- Calculate the correct forward value to preserve production behavior
- Safely remove flag references from code
- Create well-documented pull requests

## Installation (Local)

For now, install by placing this skill directory where your agent client loads skills.

Examples:

- **Generic**: copy `skills/feature-flags/launchdarkly-flag-cleanup/` into your client's skills path

## Prerequisites

This skill requires the remotely hosted LaunchDarkly MCP server to be configured in your environment. The remote server provides higher-level, agent-optimized tools that orchestrate multiple API calls and return pruned, actionable responses.

Refer to your LaunchDarkly account settings for instructions on connecting to the remotely hosted MCP server.

## Usage

Once installed, the skill activates automatically when you ask about flag cleanup:

```
Remove the `new-checkout-flow` feature flag
```

```
Is the `dark-mode` flag ready to be cleaned up?
```

```
Clean up stale feature flags in this codebase
```

## Structure

```
launchdarkly-flag-cleanup/
├── SKILL.md
├── marketplace.json
├── README.md
└── references/
    ├── pr-template.md
    └── sdk-patterns.md
```

## Related

- [LaunchDarkly MCP Server](https://github.com/launchdarkly/mcp-server)
- [LaunchDarkly Docs](https://docs.launchdarkly.com)
- [Agent Skills Specification](https://agentskills.io/specification)

## License

Apache-2.0


# PR Template for Flag Removal

Use this template when creating pull requests for flag cleanup.

```markdown
## Flag Removal: `{flag-key}`

### Removal Summary
- **Forward Value**: `{variation value being preserved}`
- **Critical Environments**: {list environments}
- **Status**: ✅ Ready for removal / ⚠️ Proceed with caution / ❌ Not ready

### Removal Readiness Assessment

**Configuration Analysis:**
| Environment | State | Serving | Rules | Targets |
|-------------|-------|---------|-------|---------|
| production | ON/OFF | `{value}` | none/present | none/count |
| {other env} | ON/OFF | `{value}` | none/present | none/count |

**Lifecycle Status:**
| Environment | Status | Evaluations (7d) |
|-------------|--------|------------------|
| production | launched/active/inactive/new | {count} |
| {other env} | launched/active/inactive/new | {count} |

**Code References:**
- Repositories with references: `{count}`
- This PR addresses: `{current repo}`
- Other repos requiring cleanup: `{list if any}`

### Changes Made
- Removed flag evaluation calls: `{count}` occurrences
- Files modified: `{list files}`
- Preserved behavior: `{describe what code now does}`
- Cleaned up: `{list dead code removed}`

### Risk Assessment

{Explain why this change is safe. Address:}
- Why the forward value is correct
- Any edge cases considered
- Impact on other environments (if any)

### Reviewer Checklist

- [ ] Forward value matches production behavior
- [ ] All flag references removed
- [ ] No unrelated changes included
- [ ] Tests pass (if applicable)
- [ ] Dead code properly removed

### Post-Merge Actions

- [ ] Archive flag in LaunchDarkly (after deployment confirmed)
- [ ] Notify other teams if they have code references
```

## Example: Ready for Removal

```markdown
## Flag Removal: `new-checkout-flo