发现 documentation llm ai 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
This skill provides guidance for tasks involving merging git branches that contain different implementations of ARC-AGI pattern recognition algorithms, and then implementing a working solution that generalizes...
Guidance for deploying HuggingFace models as inference APIs/services. This skill applies when tasks involve downloading pre-trained models from HuggingFace Hub, creating REST APIs for model inference, building...
This skill provides guidance for semantic similarity retrieval tasks using embedding models (e.g., MTEB benchmarks, document ranking). It should be used when computing embeddings for documents/queries, ranking...
Guidance for implementing batching schedulers for LLM inference systems with compilation-based accelerators. This skill applies when optimizing request batching to minimize cost while meeting latency thresholds...
Integration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDK
Guidance for training FastText text classification models with constraints on model size and accuracy. This skill should be used when training FastText models, optimizing hyperparameters, or balancing trade-off...
Guide for reverse-engineering and recreating programmatically-generated ray-traced images. This skill should be used when tasks involve analyzing a target image to determine rendering parameters, implementing p...
Guidance for optimizing LLM inference request batching and scheduling problems. This skill applies when designing batch schedulers that minimize cost while meeting latency and padding constraints, involving tra...
Guidance for querying ML model leaderboards and benchmarks (MTEB, HuggingFace, embedding benchmarks). This skill applies when tasks involve finding top-performing models on specific benchmarks, comparing model...
Guidance for text embedding retrieval tasks using sentence transformers or similar embedding models. This skill should be used when the task involves loading documents, encoding text with embedding models, comp...
Guidance for implementing neural network inference (like GPT-2) under extreme code size constraints. This skill should be used when tasks require implementing ML model inference in minimal code (code golf), par...
This skill provides guidance for implementing headless terminal interfaces that programmatically control interactive shell sessions. Use this skill when tasks involve creating terminal emulators, implementing p...
Guidance for building Caffe from source and training CIFAR-10 models. This skill applies when tasks involve compiling Caffe deep learning framework, configuring Makefile.config, preparing CIFAR-10 dataset, or t...
SDK/API patterns for configuring LLM models on Letta agents. Use when setting model handles, adjusting temperature/tokens, configuring provider-specific settings (reasoning, extended thinking), or setting up cu...
Guidance for SAM-based cell segmentation and mask conversion tasks involving MobileSAM, mask-to-polygon conversion, CSV processing, and command-line interface design. This skill applies when working with Segmen...
This skill provides guidance for training FastText text classification models with constraints on accuracy and model size. It should be used when training fastText supervised models, optimizing model size while...
Guide for using the Letta Conversations API to manage isolated message threads on agents. Use when building multi-user chat applications, session management, or any scenario requiring separate conversation cont...
Guidance for setting up HuggingFace model inference services with Flask APIs. This skill applies when downloading HuggingFace models, creating inference endpoints, or building ML model serving APIs. Use for tas...
Guidance for counting tokens in datasets, particularly from HuggingFace or similar sources. This skill should be used when tasks involve counting tokens in datasets, understanding dataset schemas, filtering by...
Meta-skill for recognizing learnings, validating improvements, and contributing back to the collective knowledge base. Use when agents discover better patterns, find gaps in existing skills, or want to improve...
AI-DLC workflow execution that loads and follows external aidlc-workflows rules to plan, design, and generate code with approval gates and aidlc-docs artifacts. Use when a user wants to run AI-DLC, needs adapti...
Command-line tools that delegate analysis tasks to AI models. Includes image description, screenshot comparison, essay generation from text, and boolean condition evaluation. Use for describing images, comparin...
New agent startup checklist for Agent Mail and Beads. Use when starting a new agent session, when the user says "prime" or "startup", or when beginning work on a multi-agent project.
Retrieve context from past sessions before implementing. Use for learned patterns, past solutions, anti-patterns, session history, or when the user mentions "recall", "memory", "history", "cass", "cm", or "what...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。