Expert in AI/ML with ALL MCP servers. Uses UltraThink for model analysis, Memory for experiment tracking, Context7 for ML docs, and NotebookLM for research papers.
Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities,...
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or...
Pricing is the most powerful lever you're not pulling. A 1% price increase typically yields 8-11% profit improvement - more than any other lever. Yet most founders set prices once and forget them,...
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise...
This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise...
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with...
Transform raw data into analytical assets using ETL/ELT patterns, SQL (dbt), Python (pandas/polars/PySpark), and orchestration (Airflow). Use when building data pipelines, implementing incremental...
Transform raw data into analytical assets using ETL/ELT patterns, SQL (dbt), Python (pandas/polars/PySpark), and orchestration (Airflow). Use when building data pipelines, implementing incremental...
Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and...
Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and...
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety...
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety...
Integrate Perplexity API for web-grounded AI responses and search. Covers Sonar models, Search API, SDK usage (Python/TypeScript), streaming, structured outputs, filters, media attachments, Pro...
Technical specification and design document expert. Use when writing design docs, RFCs, ADRs, or evaluating technology choices. Covers C4 model, system design, and architecture documentation.
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat...
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat...
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat...
Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, LoRA training for character consistency, motion graphics generation, and artist...
Comprehensive caching strategies and patterns for performance optimization. Use when implementing cache layers, cache invalidation, TTL policies, or distributed caching. Covers Redis/Memcached...