- Optimizing Attention FlashOptimizes 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.firecrawl/ai-research-skills
- OracleBest practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).firecrawl/openclaw
- OrdercliFoodora-only CLI for checking past orders and active order status (Deliveroo WIP).firecrawl/openclaw
- OutlinesGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation libraryfirecrawl/ai-research-skills
- PeekabooCapture and automate macOS UI with the Peekaboo CLI.firecrawl/openclaw
- Peft Fine TuningParameter-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.firecrawl/ai-research-skills
- Phoenix ObservabilityOpen-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.firecrawl/ai-research-skills
- PineconeManaged 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.firecrawl/ai-research-skills
- Prompt GuardMeta'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.firecrawl/ai-research-skills
- ProseOpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.firecrawl/openclaw
- Pytorch Fsdp2Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.firecrawl/ai-research-skills
- Pytorch LightningHigh-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.firecrawl/ai-research-skills
- Pyvene InterventionsProvides 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.firecrawl/ai-research-skills
- Qdrant Vector SearchHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.firecrawl/ai-research-skills
- Quantizing Models BitsandbytesQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.firecrawl/ai-research-skills
- Ray DataScalable 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.firecrawl/ai-research-skills
- Ray TrainDistributed 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.firecrawl/ai-research-skills
- Rwkv ArchitectureRNN+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.firecrawl/ai-research-skills
- SagElevenLabs text-to-speech with mac-style say UX.firecrawl/openclaw
- Segment Anything ModelFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.firecrawl/ai-research-skills
- Sentence TransformersFramework 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.firecrawl/ai-research-skills
- SentencepieceLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.firecrawl/ai-research-skills
- Serving Llms VllmServes 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.firecrawl/ai-research-skills
- Session LogsSearch and analyze your own session logs (older/parent conversations) using jq.firecrawl/openclaw
- SglangFast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.firecrawl/ai-research-skills
- Sherpa Onnx TtsLocal text-to-speech via sherpa-onnx (offline, no cloud)firecrawl/openclaw
- Simpo TrainingSimple 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.firecrawl/ai-research-skills
- Skill CreatorCreate or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.firecrawl/openclaw
- Skypilot Multi Cloud OrchestrationMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.firecrawl/ai-research-skills
- SlackUse when you need to control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.firecrawl/openclaw
- Slime Rl TrainingProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.firecrawl/ai-research-skills
- SongseeGenerate spectrograms and feature-panel visualizations from audio with the songsee CLI.firecrawl/openclaw
- SonoscliControl Sonos speakers (discover/status/play/volume/group).firecrawl/openclaw
- Sparse Autoencoder TrainingProvides 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.firecrawl/ai-research-skills
- Speculative DecodingAccelerate 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.firecrawl/ai-research-skills
- Spotify PlayerTerminal Spotify playback/search via spogo (preferred) or spotify_player.firecrawl/openclaw
- Stable Diffusion Image GenerationState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.firecrawl/ai-research-skills
- SummarizeSummarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).firecrawl/openclaw
- TensorboardVisualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkitfirecrawl/ai-research-skills
- Tensorrt LlmOptimizes 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.firecrawl/ai-research-skills
- Things MacManage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.firecrawl/openclaw
- TmuxRemote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.firecrawl/openclaw
- Torchforge Rl TrainingProvides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.firecrawl/ai-research-skills
- Training Llms MegatronTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.firecrawl/ai-research-skills
- Transformer Lens InterpretabilityProvides 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.firecrawl/ai-research-skills
- TrelloManage Trello boards, lists, and cards via the Trello REST API.firecrawl/openclaw
- UnslothExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimizationfirecrawl/ai-research-skills
- Verl Rl TrainingProvides 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.firecrawl/ai-research-skills
- Video FramesExtract frames or short clips from videos using ffmpeg.firecrawl/openclaw
- Voice CallStart voice calls via the OpenClaw voice-call plugin.firecrawl/openclaw
- WacliSend WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).firecrawl/openclaw
- WeatherGet current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.firecrawl/openclaw
- Weights And BiasesTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platformfirecrawl/ai-research-skills
- WhisperOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.firecrawl/ai-research-skills
- XurlA CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.firecrawl/openclaw