Best AI and LLM engineering skills, page 93

Machine-learning research loop for dataset curation, fine-tuning, evaluation, inference deployment, experiment tracking, and model explainability.

AnastasiyaW/codex-claude-code-config

《聪明的投资者》方法论。把格雷厄姆的价值投资框架转化为可执行规则， 用于：评估一只股票是否值得买入、判断当前情绪是否在被市场牵着走、构建防御型组合。

SpaceZephyr/career.skill

《投资最重要的事》(Howard Marks, Columbia Business School Press, 2011；2013 增注版) 方法论。

SpaceZephyr/career.skill

《穷查理宝典》(Peter Kaufman 编，2005 初版，2020 增订) 方法论。把芒格的多元思维模型格栅、 25 条误判心理学清单、Lollapalooza 识别、逆向思考、too hard pile 判断转化为 可执行的投资与决策框架。每条规则标注原书 Talk 或章节。

SpaceZephyr/career.skill

Search relevance and ranking on OpenSearch/Elasticsearch for a two-sided marketplace — candidate retrieval (hybrid BM25 + kNN, RRF, two-tower EBR), base relevance (BM25F, multimatch, LambdaMART)…

pproenca/dot-skills

Check Anthropic API access and list available Claude models.

Anil-matcha/awesome-muse-connectors

Verify your Hugging Face account and search the model hub. An agent skill from Anil-matcha/awesome-muse-connectors.

Anil-matcha/awesome-muse-connectors

Check OpenAI API access and list the models your key can use.

Anil-matcha/awesome-muse-connectors

Browse OpenRouter's model catalog and check your key usage. An agent skill from Anil-matcha/awesome-muse-connectors.

Anil-matcha/awesome-muse-connectors

Builds a portable, embedding-free knowledgebase from a set of files and delivers it as a self-contained .skill bundle (BM25 index + bundled searcher + query protocol).

oaustegard/claude-skills

Assign items to a CLOSED label vocabulary that is too large to put in a prompt — product taxonomies, category hierarchies, tag vocabularies, routing tables, ICD/SIC-style code lists.

oaustegard/claude-skills

In-process semantic search over text files or in-memory strings, using Gemini embeddings via the CF AI Gateway.

oaustegard/claude-skills

Open-source embedding database for RAG — store embeddings, vector search, metadata filtering.

AlexAI-MCP/hermes-CCC

Facebook AI Similarity Search — ultra-fast vector similarity search for large-scale local embedding retrieval without a database server.

AlexAI-MCP/hermes-CCC

Optimize transformer attention with Flash Attention — 2-4x speedup, 10-20x memory reduction for long sequences on CUDA GPUs.

AlexAI-MCP/hermes-CCC

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

AlexAI-MCP/hermes-CCC

HuggingFace Hub — download models/datasets, upload artifacts, search, and manage tokens via CLI and Python API.

AlexAI-MCP/hermes-CCC

Structured LLM outputs with Instructor — Pydantic models as response schemas for OpenAI, Anthropic, and any OpenAI-compatible API.

AlexAI-MCP/hermes-CCC

Run quantized LLMs locally with llama.cpp — CPU+GPU inference, GGUF format, OpenAI-compatible server, and Python bindings.

AlexAI-MCP/hermes-CCC

Managed vector database for production RAG — serverless and pod-based deployment, hybrid search, namespaces, and metadata filtering.

AlexAI-MCP/hermes-CCC

High-performance vector search engine for production RAG — Rust-powered, horizontal scaling, hybrid dense+sparse search, metadata filtering.

AlexAI-MCP/hermes-CCC

Run Stable Diffusion locally with diffusers — text-to-image, img2img, inpainting, ControlNet, and SDXL.

AlexAI-MCP/hermes-CCC

Deploy and serve LLMs with vLLM — OpenAI-compatible inference server with PagedAttention, continuous batching, and quantization support.

AlexAI-MCP/hermes-CCC

OpenAI Whisper for speech recognition and transcription — local inference, multiple model sizes, language detection, and subtitle generation.

AlexAI-MCP/hermes-CCC

A skill your agent uses when the user wants the current date and time written to a file via the bundled script inside the sandbox.

langchain-ai/docs

Takes aggregated ambiguity insights from the LLM synthesis stage and produces ≤5 ranked questions to surface to the user.

digipulse-engineering/GAAI-framework

Optimize gpu resource optimizer operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Collect Langfuse debug evidence for support tickets and troubleshooting.

jeremylongshore/tons-of-skills-marketplace

Create a minimal working Langfuse trace example. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Install and configure Langfuse SDK authentication for LLM observability.

jeremylongshore/tons-of-skills-marketplace

Build model quantization tool operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Build pytorch model trainer operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Build tensorflow model trainer operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Debug complex Claude API issues including context window overflow, tool use failures, streaming corruption, and response quality problems.

jeremylongshore/tons-of-skills-marketplace

Configure CI/CD pipelines for Anthropic Claude API integrations.

jeremylongshore/tons-of-skills-marketplace

Build Claude tool use (function calling) workflows with the Messages API.

jeremylongshore/tons-of-skills-marketplace

Build Claude streaming and Message Batches API workflows. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Optimize Anthropic Claude API costs with model routing, prompt caching, batching, and spend monitoring.

jeremylongshore/tons-of-skills-marketplace

Create a minimal working Anthropic Claude Messages API example.

jeremylongshore/tons-of-skills-marketplace

Install and configure Anthropic Claude SDK authentication for Python and TypeScript.

jeremylongshore/tons-of-skills-marketplace

Identify and avoid common Claude API anti-patterns and integration mistakes.

jeremylongshore/tons-of-skills-marketplace

Implement load testing, auto-scaling, and capacity planning for Claude API.

jeremylongshore/tons-of-skills-marketplace

Configure a local development workflow for Anthropic Claude API projects.

jeremylongshore/tons-of-skills-marketplace

Migrate to Claude API from OpenAI, Gemini, or other LLM providers.

jeremylongshore/tons-of-skills-marketplace

Configure Claude API across dev, staging, and production environments with isolated keys, model routing, and spend controls per environment.

jeremylongshore/tons-of-skills-marketplace

Optimize Claude API performance with prompt caching, model selection, streaming, and latency reduction techniques.

jeremylongshore/tons-of-skills-marketplace

Implement content policy guardrails, input/output validation, and usage governance for Claude API integrations.

jeremylongshore/tons-of-skills-marketplace

Execute production deployment checklist for Claude API integrations.

jeremylongshore/tons-of-skills-marketplace