Loading...
Loading...
Found 49 Skills
Attach judges to AI Config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.
Configure AI Config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts.
Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
Create and manage prompt snippets — reusable text blocks referenced inside AI Config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.
Attach judges to AI Config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.
Configure AI Config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts.
Give your AI agents capabilities through tools (function calling). Helps you identify what your AI needs to do, create tool definitions, and attach them to AI Config variations.
Use when planning A/B tests in LaunchDarkly, Optimizely, or similar platforms. Sizes the experiment (sample size, MDE, runtime), drafts hypothesis + success metrics + guardrails, and produces a launch checklist + rollback plan.
Guide for experimenting with AI configurations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.
Comprehensive guide for implementing feature flags and A/B tests using the Flags SDK (the `flags` npm package). Use when: (1) Creating or declaring feature flags with `flag()`, (2) Setting up feature flag providers/adapters (Vercel, Statsig, LaunchDarkly, PostHog, GrowthBook, Hypertune, Edge Config, OpenFeature, Flagsmith, Reflag, Split, Optimizely, or custom adapters), (3) Implementing precompute patterns for static pages with feature flags, (4) Setting up evaluation context with `identify` and `dedupe`, (5) Integrating the Flags Explorer / Vercel Toolbar, (6) Working with feature flags in Next.js (App Router, Pages Router, Middleware) or SvelteKit, (7) Writing custom adapters, (8) Encrypting/decrypting flag values for the toolbar, (9) Any task involving the `flags`, `flags/next`, `flags/sveltekit`, `flags/react`, or `@flags-sdk/*` packages. Triggers on: feature flags, A/B testing, experimentation, flags SDK, flag adapters, precompute flags, Flags Explorer, feature gates, flag overrides.
A/B testing infrastructure, feature flags (LaunchDarkly, Unleash), experimentation platforms, PLG patterns, and funnel optimization. Use when building experimentation systems, implementing feature toggles, or optimizing conversion funnels.
Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly", "GrowthBook", "Statsig", "Unleash", "Flipt", or any progressive-delivery question. Ships flag debt scanner, rollout planner, and kill-switch auditor (all stdlib Python), 4 references on flag taxonomy + provider trade-offs + rollout strategies + lifecycle, plus a /flag-cleanup slash command.