All Skills

Redige acao rescisoria - acao autonoma de impugnacao para desconstituir coisa julgada (CPC 966 hipoteses I a VIII; 967 legitimidade; 968 requisitos + deposito de 5% no inciso II; 969 nao suspende o cumprimento em regra; 975 prazo decadencial de 2 anos do transito em julgado). Competencia originaria do tribunal. Use quando o operador disser acao rescisoria, rescindir sentenca transitada, desconstituir coisa julgada, violacao de norma na sentenca, ou prova nova depois do transito.

Redige acao declaratoria pelo rito comum: interesse limitado a declaracao (CPC 19 - existencia, inexistencia ou modo de ser de relacao juridica; autenticidade ou falsidade de documento), admissibilidade ainda que ja ocorrida a violacao do direito (CPC 20). Declaratoria positiva x negativa; declaratoria incidental. Use quando o operador disser acao declaratoria, declarar inexistencia de debito, declarar relacao juridica, declaratoria de nulidade, ou quero que o juiz declare.

Estrutura o requerimento e a estrategia de provas no rito comum (CPC 369-484): documental (434+), testemunhal (rol, ate 10 — 357 §6/450-457), pericial (464-480 — quesitos e assistente tecnico), depoimento pessoal (385-388), inspecao judicial. Trata o onus da prova (373) e a vedacao a prova ilicita (369 + CF 5 LVI). Use quando o operador disser provas, requerer provas, rol de testemunhas, pericia, quesitos, depoimento pessoal, prova documental, prova emprestada, ou montar a estrategia probatoria do caso.

Redige acao de cobranca pelo rito comum (quando nao ha prova escrita) ou acao monitoria (CPC 700-702 - prova escrita SEM eficacia de titulo executivo): cheque prescrito, nota promissoria sem forca, contrato sem aceite. Mandado de pagamento + honorarios 5% (701); embargos ao mandado (702); prazos prescricionais (CC 206). Use quando o operador disser cobrar divida, acao de cobranca, monitoria, cheque prescrito, nota promissoria sem forca, ou contrato sem titulo executivo.

Avalia riscos e oportunidades do caso civel e sugere os proximos passos processuais. Pondera probabilidade de exito, onus da prova, custos/beneficios de acordo x litigio, momento de tutela de urgencia, escolha de pedidos e de via (conhecimento x cumprimento), e calibra a postura. Use quando o operador disser qual a estrategia, vale a pena recorrer, devo fazer acordo, quais os riscos, proximo passo, ou pedir analise estrategica do caso.

Argui impedimento (CPC 144, hipoteses objetivas I a IX) ou suspeicao (CPC 145, amizade intima/inimizade, presente/aconselhamento, credor/devedor, interesse no julgamento — I a IV) do juiz, em peticao especifica no prazo de 15 dias do conhecimento do fato (CPC 146), que o juiz reconhece ou remete ao tribunal — efeito suspensivo declarado pelo relator (146 §2), extensiva a MP, auxiliares da justica e demais sujeitos imparciais (CPC 148). Use quando o operador disser suspeicao, impedimento do juiz, juiz parcial, recusar o juiz, excecao de suspeicao, juiz amigo da parte contraria.

Redige pedido de gratuidade da justica (CPC 98-102) e impugnacao a gratuidade da parte contraria. Trata a diferenca PF x PJ: pessoa fisica tem presuncao relativa (CPC 99 §3); pessoa juridica deve PROVAR a insuficiencia (Sumula 481/STJ). Use ao requerer ou impugnar justica gratuita, ao analisar declaracao de hipossuficiencia, quando o operador disser pedir gratuidade, justica gratuita, hipossuficiencia, impugnar a gratuidade do autor, beneficio da assistencia. Acionada pelo civel-master na gestao processual transversal.

Redige a impugnacao ao cumprimento de sentenca (CPC 525) — defesa do executado em titulo JUDICIAL, no prazo de 15 dias apos os 15 do art. 523 e independentemente de penhora, com as hipoteses do §1 (I-VII: nulidade de citacao, ilegitimidade, inexigibilidade, penhora/avaliacao, excesso de execucao, incompetencia, causa extintiva superveniente), dever de declarar o valor correto sob pena de rejeicao (§4-5) e efeito suspensivo so com garantia + grave dano (§6). Use quando o operador disser impugnar cumprimento, impugnacao ao cumprimento de sentenca, excesso de execucao, defender de cumprimento de sentenca, executado quer se defender de sentenca.

Redige o agravo do CPC 1.042 contra a decisao que INADMITE REsp ou RE na origem (salvo inadmissao por repercussao geral/repetitivo, caso em que cabe agravo interno) e os embargos de divergencia do CPC 1.043-1.044 (acordao de orgao fracionario do STJ/STF divergente). Use quando o operador disser agravo em recurso especial/extraordinario, agravo do 1.042, REsp/RE inadmitido, nao subiu o recurso, embargos de divergencia, divergencia entre turmas do STJ/STF.

Faz o juizo de admissibilidade recursal completo antes de interpor: cabimento, tempestividade (dias uteis + dobro + feriado local da Lei 14.939/2024), preparo/desercao (CPC 1.007), regularidade formal, legitimidade/interesse e sucumbencia. Gate transversal de TODO recurso. Use quando o operador disser esse recurso e cabivel?, vai ser conhecido?, conferir admissibilidade, checar preparo, desercao, feriado local, interesse recursal, antes de protocolar o recurso.

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

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 flexible infrastructure backends.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

---

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

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 flexible infrastructure backends.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

---