skilld
All skills
launchdarkly avatar

/onboarding

@45fcc25 official
by launchdarklylaunchdarkly/agent-skills25 stars
10

Scripted onboarding for LaunchDarkly: quiet execution, fixed sequence, SDK install, first flag with a live reveal, MCP offered afterwards. Enforces step completion before advancing and redirects drift. Use when adding LaunchDarkly, setting up or integrating feature flags in a project, SDK integration, or 'onboard me'.

Ask your Agent

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

This session only. Nothing lands on disk.

README.md

≈694 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Onboarding Skill

An Agent Skill that onboards a project to LaunchDarkly end to end: install the SDK, create a first flag, and let the user watch it flip in their running app.

Overview

The skill runs a fixed sequence and keeps the conversation quiet between decision points, so the user can delegate the work and come back to a finished state:

  1. Safe workspace — create the launchdarkly-onboarding branch and leave every change uncommitted for the user to review.
  2. Explore — classify the workspace from dependency manifests and entrypoints. A multi-package workspace is always ambiguous, so the skill asks which package to integrate instead of guessing. An empty workspace gets an offer to scaffold a small demo app.
  3. Install the SDK — hand off to sdk-install (detect, plan, apply), or use the fast path when the app was just scaffolded. The SDK key comes from MCP when it is already configured, otherwise from a direct dashboard link.
  4. First flag — create the flag, add a flag-gated banner to the app, start the dev server, and hand the reveal to the user so they see the banner change when the flag turns on.
  5. MCP (optional) — offered only after the flag works, via mcp-configure.

Notable behaviors:

  • No log or summary file. State is detected from the repository, so "continue onboarding" resumes at the first incomplete step.
  • Drift is redirected, not refused. When the user asks to skip ahead, the skill acknowledges the request, names the concrete consequence in one sentence, and offers the choice.
  • No internal leakage. Step labels, skill file names, workflow jargon, and MCP or SDK internals never reach the user.

Installation

npx skills add launchdarkly/ai-tooling --skill onboarding -y --agent <agent>

Or copy skills/onboarding/ into your client's skills path.

Prerequisites

  • An MCP-capable coding agent (Cursor, Claude Code, Windsurf, GitHub Copilot, and others).
  • npx on PATH for optional companion skill installs.
  • A LaunchDarkly account. SDK keys, client-side IDs, and mobile keys are only needed when the SDK key step runs.

Usage

Ask the agent to onboard the project:

Set up LaunchDarkly in my project.

Nested skills

Skill Purpose
sdk-install Detect the stack, plan the integration, apply the code changes
mcp-configure Configure the hosted LaunchDarkly MCP server

Evaluations

evals/onboarding/ scores the kickoff and the early decision points: kickoff voice, monorepo ambiguity, MCP staying out of the way until the flag works, and drift handling.

cd evals && npm run eval:onboarding

Source: SKILL.md on GitHub

Third-party checks

2 warnings16d4 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill provides a guided, multi-step onboarding workflow to integrate LaunchDarkly SDKs into a project. It strictly enforces safe defaults such as isolated git branches, avoiding hardcoded secrets by guiding users on environment variable setup with explicit consent, and leverages standard tools or hosted Model Context Protocol (MCP) integrations with no hazardous behaviors identified.

  • Socket16d

    1 alert: gptAnomaly

  • Snyk16d

    Risk: LOW · No issues

  • ZeroLeaks5mo

    Scan incomplete

Provenance

Signed by skilld at 45fcc25. 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 last month

Capability

metadata
{
  "author": "launchdarkly",
  "version": "0.3.0"
}
Other metadata
compatibility
Requires an MCP-capable coding agent and `npx` on PATH for optional skill installs. SDK keys, client-side IDs, and mobile keys are only needed when the SDK key step runs.

Topics

  • MCP
  • TypeScript
  • launchdarkly
  • feature-flags
  • sdk
  • onboarding
  • integration
  • javascript

README badge

README badge for launchdarkly/agent-skills/onboarding

What it does

Orchestrates LaunchDarkly SDK setup in an existing codebase: creates a resumable onboarding log, explores the repo to detect the language and framework, installs companion flag-management skills, configures the LaunchDarkly MCP server, installs and initializes the SDK, and scaffolds a first feature flag. Designed for projects adding LaunchDarkly from scratch or integrating feature flags into an existing codebase.

Generated from the current SKILL.md.

Frequently asked

Does this skill require a LaunchDarkly account upfront?
No. Steps 0–3 (log, explore, detect, install skills) run without an account. Account status is confirmed naturally during Step 4 via MCP OAuth, or surfaced at Step 5 if you need to provide SDK keys manually.
What coding agent platforms does this work with?
It requires an MCP-capable coding agent (like Cursor or Claude Code). Task tracking uses your agent's native tool if available (TodoWrite in Cursor, TaskCreate in Claude Code), or falls back to an in-chat checklist.
Do I need SDK keys or API tokens before starting?
No. The skill defers credential collection until the step that actually uses them — MCP uses OAuth (Step 4), and the SDK install collects keys only when wiring environment variables (Step 5).
Can I pause and resume onboarding later?
Yes. Step 0 writes a living onboarding log file (LAUNCHDARKLY_ONBOARDING.md) that tracks progress, so a new session or another agent can pick up where you left off.
What if I do not have the MCP server configured?
The skill falls back to ldcli or REST API for SDK discovery and flag creation, though MCP is preferred. Onboarding remains completable without it.

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