Setting the file. One moment.
Subchapter 20.7
README.mdMarkdown3 KBView on GitHub
An Agent Skill for migrating an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: extract, wrap, tools, tracking, evals.
This skill orchestrates the full migration journey from hardcoded openai.chat.completions.create(model="gpt-4o", ...) (or equivalent in any provider SDK) to a managed config with tools, tracking, and judges. It delegates each stage to a focused skill and covers the tracker wiring inline — since no existing skill owns tracker.track_* calls.
The five stages:
completion_config / completionConfig with a safe fallback — delegates the config creation to configs-createtoolstrack_duration, track_tokens, track_success/track_error, optional track_feedback — inline, with a reference doc covering every SDK method in Python and Node side by sideonline-evalsCopy skills/agentcontrol/migrate/ into your agent client’s skills path.
LD_SDK_KEY environment variable (server-side SDK key, starts with sdk-)Migrate our chat service from hardcoded OpenAI prompts to LaunchDarkly AgentControlOur LangGraph agent has its model and instructions baked in — walk me through wrapping it in a configWire up the agent tracker and attach accuracy + relevance judges to our existing configmigrate/
├── SKILL.md
├── README.md
└── references/
├── phase-1-analysis-checklist.md
├── before-after-examples.md
├── sdk-ai-tracker-patterns.md
├── agent-mode-frameworks.md
├── fallback-defaults-pattern.md
└── agent-graph-reference.mdApache-2.0