Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Find PDF documents on your computer, extract and summarize their content, and read the summary aloud using text-to-speech. Use this skill when the user asks to read a PDF summary out loud, speak a doc…
Extract and analyze key clauses from construction contracts. Identify payment terms, change order procedures, dispute resolution, warranties, and risk allocation provisions.
Super-resolución de la foto del documento para mejorar calidad del face match cuando la foto es de baja resolución
State-of-the-art facial recognition with ArcFace R100 to compare selfie with document photo
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, N…
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, …
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (…
User Guide for the Talon Multi-Model Fusion Data Engine. It is triggered when users need to develop using the Talon database: including SQL queries, KV storage, vector search, time-series data, messag…
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
Clasificador de deepfakes y face swaps entrenado en el dataset FaceForensics++
Advanced image processing algorithms for document analysis
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source …
Fast 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 infe…
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering mo…
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melod…
Build RAG systems for construction knowledge bases. Create searchable AI-powered construction document systems
AI-powered contractor matching and selection for construction projects. Analyze contractor capabilities, past performance, certifications, and project requirements to recommend optimal matches.
Quantization of ML models to FP16/INT8 to reduce memory and accelerate inference in the KYC pipeline
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal supp…
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 a…
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.…
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange interven…
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, vi…