sdk-install

작성자: launchdarkly

온보딩 중에 올바른 LaunchDarkly SDK를 설치하고 초기화하려면 중첩된 스킬을 순서대로 실행하세요: detect, plan, apply. 상위 온보딩 단계 6이 먼저입니다…

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

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 6: First feature flag using Create first feature 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 (Step 4) or surfaced at D7 in apply; key material is collected at apply (see parent Prerequisites).

Key types (summary)

SDK TypeVariable (logical)Source in LaunchDarkly
Server-sideLAUNCHDARKLY_SDK_KEYEnvironments → SDK key
Client-sideClient-side ID (bundler-prefixed env names)Environments → Client-side ID
MobileLAUNCHDARKLY_MOBILE_KEYEnvironments → 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.

OrderNested skillRole
1Detect repository stackLanguage, package manager, monorepo target, entrypoint, existing LD usage
2Generate integration planSDK choice, files to change, env plan -- presented to user (non-blocking; see plan SKILL.md D6)
3Apply code changesInstall 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:

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.

References

launchdarkly의 다른 스킬

aiconfig-agent-graphs
launchdarkly
에이전트 그래프를 생성하고 관리합니다 — 핸드오프 로직이 있는 엣지로 연결된 AI 구성의 방향 그래프입니다. 구성이 포함된 다중 에이전트 워크플로우를 구축할 때 사용합니다.
official
aiconfig-ai-metrics
launchdarkly
기존 코드베이스에 LaunchDarkly AI Config 추적을 계측합니다. 4단계 사다리(관리형 러너 → 제공자 패키지 → 사용자 정의 추출기 +…)를 따라 진행됩니다.
official
aiconfig-create
launchdarkly
LaunchDarkly에서 AI Config를 생성하고 구성합니다. 에이전트 모드와 완료 모드 중 선택하고, config를 생성하며, 모델과 프롬프트가 포함된 변형을 추가하는 데 도움을 줍니다.
official
aiconfig-custom-metrics
launchdarkly
AI Configs에 대한 맞춤형 비즈니스 메트릭을 생성, 추적, 검색, 업데이트 및 삭제합니다. 전체 수명 주기를 다룹니다: API를 통해 메트릭 종류를 정의하고, SDK를 통해 이벤트를 전송하며,…
official
aiconfig-migrate
launchdarkly
하드코딩된 LLM 프롬프트가 포함된 애플리케이션을 완전한 LaunchDarkly AI Configs 구현체로 마이그레이션하는 다섯 단계: 코드 감사, 호출 래핑, 이동…
official
aiconfig-online-evals
launchdarkly
AI Config 변형에 판정기를 연결하여 자동 LLM-as-a-judge 평가를 수행합니다. 맞춤형 판정기를 생성하고, 샘플링 비율을 구성하며, 품질 점수를 모니터링할 수 있습니다.
official
aiconfig-projects
launchdarkly
코드베이스에서 LaunchDarkly 프로젝트를 설정하기 위한 가이드입니다. 스택을 평가하고, 적절한 접근 방식을 선택하며, 프로젝트 관리를 통합하는 데 도움을 줍니다…
official
aiconfig-snippets
launchdarkly
프롬프트 스니펫을 생성하고 관리합니다 — AI Config 변형 프롬프트 내에서 참조되는 재사용 가능한 텍스트 블록입니다. 일반적인 지침, 페르소나, 가드레일을 유지합니다…
official