Loading...
Loading...
Found 55 Skills
Set up asciinema chunker daemon with interactive wizard. Guides through PAT creation, Keychain storage, Pushover setup, and launchd installation. TRIGGERS - daemon setup, install chunker, configure backup.
Guide for setting up AI configuration in your application. Helps you choose between agent vs completion mode, select the right approach for your stack, and create AI Configs that make sense for your use case.
Guide for giving your AI agents capabilities through tools. Helps you identify what your AI needs to do, create tool definitions, and attach them in a way that makes sense for your framework.
Create and manage agent graphs — directed graphs of AI Configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
Create a boolean first flag, add evaluation, toggle on/off for end-to-end proof. Parent onboarding Step 6; uses MCP, API, or ldcli; optional flag-create skill.
Configure guarded rollouts with progressive traffic increases, metric monitoring, and automatic rollback. Use when releasing features gradually with safety thresholds.
Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.
Create, track, retrieve, update, and delete custom business metrics for AI Configs. Covers full lifecycle: define metric kinds via API, emit events via SDK, and query results.
Create and manage prompt snippets — reusable text blocks referenced inside AI Config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.
Set up automated trading strategies — DCA, limit orders, and stop losses — by composing mp CLI commands with OS scheduling (cron/launchd).
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.
Attach judges to AI Config variations for automatic LLM-as-a-judge evaluation. Create custom judges, configure sampling rates, and monitor quality scores.