Create a new artifact (text, code, plan, data) under specified constraints. Use when producing content, writing...
AI & LLM
LLM integrations, prompt engineering, and AI orchestration
7,400 skills
Produce clear reasoning with assumptions, causal chains, and evidence. Use when clarifying decisions, teaching...
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when...
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment,...
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms....
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM...
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4...
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models...
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training...
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks,...
Break a goal into subgoals, constraints, and acceptance criteria. Use when planning complex work, creating work...
Execute the Debug Code Change workflow end-to-end with safety gates. Use when debugging code changes, investigating...
Find failure modes, edge cases, ambiguities, and exploit paths in plans, code, or designs. Use when reviewing...
Enforce policies, guardrails, and permission boundaries; refuse unsafe actions and apply least privilege. Use when...
Compare multiple alternatives using explicit criteria, weighted scoring, and tradeoff analysis. Use when choosing...
Assign labels or categories to items based on characteristics. Use when categorizing entities, tagging content,...
Create a safety checkpoint marker before mutation or execution steps. Use when about to modify files, execute plans,...
Identify capability gaps and propose new skills with prioritization. Use when analyzing missing capabilities,...
Produce a comprehensive audit trail of actions, tools used, changes made, and decision rationale. Use when recording...
Establish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies,...
Read and search Gmail messages. Use when user wants to check email, search inbox, or read messages.
Virtual Pub for AI Agents
Deep architectural planning with --ultrathink (32K tokens) followed by phased creation with fresh context. Two-stage...