Skill UI

Train and fine-tune transformer language models with Hugging Face TRL via CLI. Covers SFT, DPO, GRPO, RLOO, KTO and reward model training, plus LoRA adapters, YAML configs and distributed multi-GPU runs.

Configure Turborepo for efficient monorepo builds using local and remote caching strategies. This skill covers setting up build pipelines, optimizing CI/CD performance, and implementing distributed caching solutions like Vercel or self-hosted servers. It includes managing cache keys, outputs, and filtering packages for faster development workflows.

Add distributed rate limiting to API routes, middleware, and edge functions with @upstash/ratelimit and Upstash Redis. Covers sliding window, fixed window, and token bucket algorithms, per-identifier keys, and returning 429 with Retry-After headers.

Master workflow orchestration architecture with Temporal, covering fundamental design decisions, resilience patterns, and best practices for building reliable distributed systems.

This skill provides a standardized framework for evaluating autonomous AI agents. It tracks task completion rates, planning accuracy, tool invocation precision, and operational costs. Suitable for engineering teams managing distributed systems, it enables reproducible benchmarking, regression monitoring, and compliance tracking through structured data models like CSV, SQL, and JSON schemas.

Registers zero-knowledge SNARK proof verification keys, circuit complexity constraints, and nullifier tracking for double-spending prevention in privacy systems. Provides standardized field schemas, SQL DDL, JSON validation, and best practices for auditable cryptographic verification across distributed applications and smart contracts.