skilld
All skills
launchdarkly avatar

/launchdarkly-flag-command

@24e9c7e official
by launchdarklylaunchdarkly/agent-skills25 stars
10

Resolve `/flag` style requests into the right LaunchDarkly flag lookup flow. Use when the user types `/flag`, asks to quickly find a flag by name/key, wants a direct flag detail summary, or needs fast disambiguation between similar flags.

Ask your Agent

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

This session only. Nothing lands on disk.

README.md

≈449 tokens on demand. Your agent reads this file only when SKILL.md points to it.

LaunchDarkly Flag Command Skill

An Agent Skill for handling quick /flag lookups with fast resolution, disambiguation, and actionable summaries.

Overview

This skill teaches agents how to:

  • Parse /flag style user requests
  • Resolve flag keys from fuzzy queries
  • Disambiguate between similar flags safely
  • Return concise flag detail summaries
  • Route users into deeper create/targeting/cleanup workflows when needed

Installation (Local)

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

Examples:

  • Generic: copy skills/feature-flags/launchdarkly-flag-command/ 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 for quick flag lookups:

/flag dark mode
find flag checkout
show me the new-checkout flag in staging

Structure

launchdarkly-flag-command/
├── SKILL.md
├── marketplace.json
└── 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 LaunchDarkly Flag Command skill allows for quick, read-only lookups of feature flags via a dedicated MCP server. It includes strong negative constraints that prevent the agent from performing modifications or providing unauthorized safety analysis on flags, instead routing those requests to appropriate specialized skills. No malicious patterns or security risks were identified.

  • Socket3mo

    No alerts

  • Snyk3mo

    Risk: LOW · No issues

Provenance

Signed by skilld at 24e9c7e. 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
  • flags
  • feature-flags
  • lookup
  • routing

README badge

README badge for launchdarkly/agent-skills/launchdarkly-flag-command

What it does

Resolves `/flag` queries into LaunchDarkly flag lookups, returning flag details (key, name, environment state, targeting rules) and routing to specialized skills for creation, targeting changes, or cleanup assessment. Use this as the read-only entrypoint when a user asks to quickly find or inspect a flag by name or key.

Generated from the current SKILL.md.

Frequently asked

Does this skill create or modify flags?
No. This is a read-only lookup entrypoint. It resolves flag details and routes to other skills for creation, targeting changes, or removal decisions.
What MCP server does this require?
The remotely hosted LaunchDarkly MCP server, configured in your environment. It uses list-flags and get-flag tools as core dependencies.
Can this skill assess whether a flag is safe to remove?
No. For removal or staleness questions, it returns the flag summary and routes to the flag discovery or flag cleanup skill instead.
What environment does this use by default?
Production, unless the user specifies a different environment like staging.
Does this handle flag disambiguation?
Yes. If multiple flags match the query, it returns a short list with key, name, and state, then asks the user to pick one.

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