AGENT SKILLS · EQUIPAMENTO DE MISSÃO
Agent Skills úteis classificados pelo uso real
Compare Skills verificados por finalidade, conteúdo do pacote, instalações e evidências da fonte antes de adicioná-los.
- ESCOPO DO CATÁLOGO
- VERIFICADO
- Skills
- 22.640
- repositórios
- 3478
- última sincronização
- 30 de out. de 2026
orchestra-researchopenrlhf-training
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.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchoptimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchpeft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchphoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchprompt-guard
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchpytorch-lightning
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.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchpyvene-interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchray-data
Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchray-train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchrwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchserving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchsparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchspeculative-decoding
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchtensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchtensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchtransformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
orchestra-researchweights-and-biases
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
- Instalações / 1h
- 1
- GitHub Stars
- 13,7 mil
- Atualizado
- 11 de out.
deanpetersaltitude-horizon-framework
Understand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps.
- Instalações / 1h
- 1
- GitHub Stars
- 7,5 mil
- Atualizado
- 16 de out.
deanpetersansoff-matrix
Map evidence-backed growth options across the Ansoff Matrix with risk-rated sequencing. Use when the question is where the next tranche of growth comes from, and at what risk.
- Instalações / 1h
- 1
- GitHub Stars
- 7,5 mil
- Atualizado
- 16 de out.
deanpeterscompetitive-analysis-process
Orchestrate a complete competitive analysis across six steps, from landscape to strategic direction. Use when you need the full picture, not a single scan or card.
- Instalações / 1h
- 1
- GitHub Stars
- 7,5 mil
- Atualizado
- 16 de out.
deanpeterscompetitive-intel-watch
Scheduled delta monitoring against a prior competitive snapshot. Use when tracking competitors on a cadence: material shifts only, cited evidence, battle-card update flags, runs unattended.
- Instalações / 1h
- 1
- GitHub Stars
- 7,5 mil
- Atualizado
- 16 de out.
deanpeterscontext-engineering-advisor
Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.
- Instalações / 1h
- 1
- GitHub Stars
- 7,5 mil
- Atualizado
- 16 de out.
deanpetersderisk-measurement-advisor
Identify what to measure, test, or track to de-risk a product or AI idea. Use when stress-testing an idea across internal (DUFV) and external (PESTEL) dimensions.
- Instalações / 1h
- 1
- GitHub Stars
- 7,5 mil
- Atualizado
- 16 de out.
deanpetersdiscovery-process
Run a full discovery cycle from problem hypothesis to validated solution. Use when a team needs a structured path through framing, interviews, synthesis, and experiments.
- Instalações / 1h
- 1
- GitHub Stars
- 7,5 mil
- Atualizado
- 16 de out.