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

/launchdarkly-flag-discovery

@f0ee110 official
Run it yourself

Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about flag debt, stale flags, cleanup candidates, flag health, or wants to understand their flag inventory.

Use this Skill: https://skilld.dev/gh/launchdarkly/ai-tooling/launchdarkly-flag-discovery

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

README.md

≈439 tokens on demand. Your agent reads this file only when SKILL.md points to it.

LaunchDarkly Flag Discovery Skill

An Agent Skill for auditing and understanding your LaunchDarkly feature flag landscape.

Overview

This skill teaches agents how to:

  • Survey the full feature flag inventory in a project
  • Identify stale, inactive, or fully-launched flags
  • Assess whether specific flags are ready for removal
  • Provide prioritized, actionable recommendations

Installation (Local)

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

Examples:

  • Generic: copy skills/feature-flags/launchdarkly-flag-discovery/ 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 health or inventory:

What's the state of our feature flags?
Which flags are stale and should be cleaned up?
Is the `dark-mode` flag ready to be removed?

Structure

launchdarkly-flag-discovery/
├── SKILL.md
├── marketplace.json
├── README.md
└── references/
    ├── flag-health-signals.md
    └── removal-readiness-checklist.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 alerts14d3 checks · Risk SAFE
  • Gen Agent Trust Hub15d

    The skill is an administrative tool for auditing LaunchDarkly feature flags. It uses the official LaunchDarkly MCP server to retrieve flag inventory and health data. No malicious code or risky behaviors were detected.

  • Socket14d

    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
  • feature-flags
  • flag-audit
  • flag-cleanup
  • flag-health
  • inventory

README badge

README badge for launchdarkly/ai-tooling/launchdarkly-flag-discovery

Audits LaunchDarkly feature flags to identify stale, launched, or inactive flags and assess removal readiness. Uses the LaunchDarkly MCP server to explore flag inventory, categorize cleanup candidates, and provide removal safety verdicts based on lifecycle state, staleness, and cross-environment consistency.

Generated from the current SKILL.md.

Does this skill remove flags from code or just identify candidates?
This skill only audits and identifies cleanup candidates. For actual code removal, use the launchdarkly-flag-cleanup skill.
What MCP server does this require?
The remotely hosted LaunchDarkly MCP server. Without it, the skill cannot access flag data.
Can I audit flags across multiple environments at once?
Yes. The skill can list flags in a specific environment and use get-flag-status-across-envs to check consistency across all environments.
What counts as a stale flag?
Flags with no SDK evaluations in the specified period (default 30 days), plus flags created but never evaluated and fully rolled-out flags with no recent changes. The find-stale-flags tool categorizes these separately.
How do I know if a flag is safe to remove?
Use check-removal-readiness for a specific flag. It returns a verdict (safe, caution, or blocked) based on dependencies, code references, and targeting rules.

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