Claude MarketplacesSubmit
launchdarkly avatar

Migrate

launchdarkly/agent-skillsOfficial

If you're sitting on hardcoded OpenAI or Anthropic calls and want to move model, prompt, and tool definitions into LaunchDarkly, this walks you through a five stage migration: audit what's hardcoded, wrap the call with the SDK, externalize tool schemas, wire tracking for tokens and duration, then attach evaluators. It knows the common footguns in LangChain and LangGraph agent loops, especially where to scope the tracker so you don't accidentally mint a new run ID on every iteration. Python and Node.js get worked examples for direct provider calls, LangGraph agents, and CrewAI. Other languages stop at install commands. The skill prepares inputs for each LaunchDarkly write but doesn't auto invoke the sibling skills, so you'll manually run configs-create and the rest at the right checkpoints.

skills.sh installs
1.3K
GitHub stars
19
last updated
Jul 14, 2026
View on GitHub

Install

$ npx -y skills add launchdarkly/agent-skills --skill migrate --agent claude-code

Installs into .claude/skills of the current project.

Files

Migrate to AgentControl

You're using a skill that will guide you through migrating an application from hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation. Your job is to run the migration in five stages, stopping at each stage for the user to confirm:

  1. Audit the code — read-only scan that produces a structured list of everything hardcoded (prompt, model, parameters, tools, app-scoped knobs).
  2. Wrap the call — install the SDK, create the config in LaunchDarkly with a fallback that mirrors the hardcoded values, and rewrite the call site to fetch the config fresh on every request.
  3. Move the tools — extract each tool's JSON schema, attach it to the config, and swap every call site that references the old tool list.
  4. Add tracking — wire the per-request tracker (duration, tokens, success/error) around the provider call.
  5. Attach evaluators — either offline evals via the Playground + Datasets, or online judges that score sampled traffic automatically.
SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Details

Repository
github.com/launchdarkly/agent-skills
Category
AI & Agent Building
First seen
Jul 14, 2026

More from launchdarkly/agent-skills

All 41

Recommended

More AI & Agent Building
1launchdarkly avatartoolslaunchdarkly/agent-skillstools1.3Kskills.sh installs
2heygen-com avatarliveavatar-integrateheygen-com/liveavatar-agent-skillsBuild a LiveAvatar integration end-to-end — assesses the user's existing stack, recommends the optimal path, and guides implementation. Use when: (1) Building a1.2Kskills.sh installs
3orchestra-research avatargguf-quantizationorchestra-research/ai-research-skillsGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible 1.1Kskills.sh installs
4orchestra-research avatarquantizing-models-bitsandbytesorchestra-research/ai-research-skillsQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want fast1Kskills.sh installs
5orchestra-research avataroutlinesorchestra-research/ai-research-skillsGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize in1Kskills.sh installs
6openai avatarcodex-cli-runtimeopenai/codex-plugin-ccInternal helper contract for calling the codex-companion runtime from Claude Code808skills.sh installs