sdk-install

launchdarkly/ai-tooling

Install and initialize the correct LaunchDarkly SDK by detecting stack, planning integration, and applying code changes.

Source View on skills.sh

What is sdk-install?

This skill automates LaunchDarkly SDK setup during onboarding by running three nested workflows in sequence: detect your project's language and framework, generate an integration plan, and apply the necessary code changes. Use it when onboarding a new project to LaunchDarkly feature flags.

Detects project language, package manager, monorepo structure, and existing LaunchDarkly usage
Generates an SDK integration plan tailored to your stack (server-side, client-side, or mobile)
Installs the appropriate LaunchDarkly SDK package(s) and initializes them in your codebase
Handles dual-SDK scenarios (e.g., Next.js server + client) by installing and configuring both
Manages environment variables and secrets with user consent, avoiding hardcoded keys
Validates integration with a compile check after applying changes

How to install sdk-install

npx skills add https://github.com/launchdarkly/ai-tooling --skill sdk-install

Prerequisites

Project context from parent onboarding Step 1 (Explore the Project)
SDK key, client-side ID, or mobile key (required only when reaching the Apply step, not for Detect or Plan alone)
Supported language/framework in the project (Node.js, Python, Java, Go, Ruby, etc.)

Claude Code

Cursor

Windsurf

Cline

How to use sdk-install

1.Run the Detect nested skill to analyze your project's language, framework, package manager, and existing LaunchDarkly usage
2.Review the integration plan generated by the Plan nested skill, which recommends SDK type and files to modify
3.Provide SDK credentials (key/client-side ID/mobile key) when prompted during the Apply step
4.Allow the skill to install the LaunchDarkly SDK package(s) and initialize them in your codebase
5.Verify the compile check passes after code changes are applied
6.Continue with parent onboarding Step 4 to create your first feature flag

Use cases

Good for

Onboarding a new project to LaunchDarkly by automatically selecting and installing the correct SDK variant
Setting up feature flags in a monorepo by detecting the target package and integrating within its subtree
Configuring dual-SDK environments (frontend + backend) in frameworks like Next.js or similar
Migrating an existing project to LaunchDarkly by detecting current setup and planning the integration path
Ensuring SDK credentials are properly wired through environment variables without hardcoding secrets

Who it's for

Developers onboarding projects to LaunchDarkly
Teams managing monorepos or multi-environment applications
Engineers setting up feature flag infrastructure for the first time
DevOps or platform engineers automating SDK deployment across projects

sdk-install FAQ

Do I need to provide SDK credentials before running this skill?

No. Credentials are only required when you reach the Apply step (the third nested skill). Detect and Plan can run without them.

What if my project uses both server-side and client-side code (e.g., Next.js)?

The skill detects this and generates a dual-SDK plan, installing and initializing both the server-side and client-side SDKs with appropriate environment variable configuration.

Can this skill work with monorepos?

Yes. The skill detects monorepo structure and integrates the LaunchDarkly SDK into the specific package you selected during parent onboarding.

Will this skill hardcode my SDK key in the source code?

No. The skill manages SDK credentials through environment variables (e.g., LAUNCHDARKLY_SDK_KEY) and adds .env.example entries; it never hardcodes keys.

What happens if LaunchDarkly is already installed in my project?

The Detect step identifies existing SDK usage. If already initialized, the parent onboarding may skip this skill entirely, or the skill will plan around the existing setup.

Full instructions (SKILL.md)

Source of truth, from launchdarkly/ai-tooling.

name: sdk-install description: "Install and initialize the correct LaunchDarkly SDK during onboarding by running nested skills in order: detect, plan, apply. Parent onboarding Step 4 is first flag." license: Apache-2.0 compatibility: Requires a supported language/framework in the project. SDK credentials are required by Apply, not for Detect / Plan alone (see parent onboarding Prerequisites). metadata: author: launchdarkly version: "0.2.0"

LaunchDarkly SDK Install (onboarding)

Installs and initializes the right LaunchDarkly SDK for the user’s project by following three nested skills in order. Do not skip ahead to feature flags here—the parent LaunchDarkly onboarding continues with Step 4: First flag.

Prerequisites

Project context from parent Step 1: Explore the Project (reuse it; only re-run deep detection if something is unclear)
SDK key / client-side ID / mobile key: Needed when you reach Apply code changes (env wiring). Do not ask the user for these during detect or plan solely because you opened this skill—follow parent onboarding: account status is inferred via MCP OAuth when MCP is already configured, or surfaced at D7 in apply; key material is collected at apply (see parent Prerequisites).

Key types (summary)

SDK Type	Variable (logical)	Source in LaunchDarkly
Server-side	`LAUNCHDARKLY_SDK_KEY`	Environments → SDK key
Client-side	Client-side ID (bundler-prefixed env names)	Environments → Client-side ID
Mobile	`LAUNCHDARKLY_MOBILE_KEY`	Environments → Mobile key

Never hardcode keys. Full env rules, consent, and bundler tables: Apply code changes Step 2.

Workflow — run these nested skills in order

Execute all three unless the detect decision tree short-circuits (e.g. skip to apply only). Each nested skill may contain decision points — some blocking (marked D<N> -- BLOCKING, where you must call your structured question tool and wait for the user's response before continuing) and some non-blocking (where you present information and continue unless the user objects). Do NOT batch tool calls across blocking boundaries.

Order	Nested skill	Role
1	Detect repository stack	Language, package manager, monorepo target, entrypoint, existing LD usage
2	Generate integration plan	SDK choice, files to change, env plan -- presented to user (non-blocking; see plan SKILL.md D6)
3	Apply code changes	Install package(s), `.env` / secrets with consent, init code, compile check (both tracks when dual-SDK plan)

Shared references for all steps: SDK recipes, SDK snippets.

After Step 3 completes

Continue with the parent skill:

Step 4: First flag

Do not add standalone “sample flag” evaluation in this skill unless the user explicitly needs a throwaway check; the parent flow creates the first flag in order.

Guidelines

Match existing codebase conventions for imports, config, and style.
Prefer TypeScript in TypeScript projects.
If the project uses a shared config layer, initialize LaunchDarkly there.
Add .env.example entries when the project uses dotenv.
Dependency scope: Add only LaunchDarkly SDK package(s) from the recipe unless the user explicitly approves upgrading or adding other packages (Apply — Permission before changing other dependencies).

Edge cases

Multiple environments (e.g. Next.js server + client) or user asked for frontend + backend: Use a dual-SDK plan and apply both packages and both inits—never summarize the second SDK as done without lockfile + entrypoint evidence.
Monorepo: Integrate the package the user chose in parent onboarding; stay within that subtree.
SDK already installed and initialized: Parent may skip this handoff—see parent Edge Cases and detect decision tree.
Unsupported or uncommon stack: Use SDK recipes and the full SDK catalog.