Best AI and LLM engineering skills, page 96

Guide to Transformer architectures for NLP and computer vision

wentorai/research-plugins

Vectorized multi-agent reinforcement learning simulator. An agent skill from wentorai/research-plugins.

wentorai/research-plugins

Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation.

borghei/Claude-Skills

Build AI agents with the Strands Agents SDK - the open-source framework (the agent "brain") for writing agent logic, tools, and multi-agent systems in Python.

hoodini/ai-agents-skills

Build LLM applications with LangChain and LangGraph. An agent skill from hoodini/ai-agents-skills.

hoodini/ai-agents-skills

Route AI coding queries to local LLMs in air-gapped networks.

hoodini/ai-agents-skills

Call POST /chat/completions on Venice. An agent skill from veniceai/skills.

veniceai/skills

LLM and multimodal serving systems. An agent skill from uw-syfi/vibesys.

uw-syfi/vibesys

Reuse lower-level SIL libraries before writing custom helpers in FieldWorks.

sillsdev/FieldWorks

Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling…

artokun/comfyui-mcp

On-demand GPU cloud instances for ML training. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Use the skill-hub CLI to search, install, update, and publish agent skills from skill-hub.com.

CoWork-OS/CoWork-OS

Turn a network topology into one stylized, AI-generated still image via a self-hosted ComfyUI instance — reuses the same topology model as threejs-network-viz (any of 8 topology-source integrations…

automateyournetwork/netclaw

Human-in-the-loop escalation via HumanRail — route low-confidence agent decisions, pre-destructive operation approvals, and ambiguous incident tickets to real human engineers.

automateyournetwork/netclaw

Ingest user-selected documents and retrieve cited procedures, standards, and design evidence from the local RAG knowledge base.

automateyournetwork/netclaw

Draft and publish user-requested Twitter content through content checks and approval.

automateyournetwork/netclaw

Install the repository-wide Agent Skills compatibility view for Claude Code

tetherto/qvac

This skill should be used when the user asks about "EMA", "CHMP opinion", "NICE", "G-BA", "AMNOG", "HAS", "European launch", "HTA", "EU pricing", "reimbursement in Europe", or wants ex-US launch…

hh-health-AI/healthcare-equity

This skill should be used when the user asks about "hospital margins", "cost reports", "HCRIS", "payer mix", "occupancy", "uncompensated care", "hospital capex capacity", "will hospitals buy", or…

hh-health-AI/healthcare-equity

This skill should be used when the user asks about "Medicare Advantage margins", "MLR", "Star Ratings", "MA enrolment", "risk adjustment", "MedPAC benchmark", "payor margin normalisation"…

hh-health-AI/healthcare-equity

This skill should be used when the user asks for an "open TRx proxy", "SDUD", "Medicaid utilisation", "script trend without IQVIA", "is the launch tracking", "prescription volume for [brand]", or…

hh-health-AI/healthcare-equity

Engineer effective LLM prompts using zero-shot, few-shot, chain-of-thought, and structured output techniques.

ancoleman/ai-design-components

Create and setup a new OpenAI Agents SDK application with interactive guidance for language choice, agent type selection (Basic, Voice, Realtime), project setup, and automatic verification.

sandgardenhq/sgai

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning.

coco-research/coco

A skill your agent uses when building AI features into a product: LLM integration, RAG pipelines, guardrails, streaming, AI UX, prompt engineering, or AI cost control.

coco-research/coco

Wrap any command-line tool into a JSON-emitting agent skill.

coco-research/coco

A skill your agent uses when the user sends or generates an image, screenshot, video, audio or file and wants it saved, or asks to find past media (that diagram, the mockup from last week).

coco-research/coco

Your AI research and engineering brain trust. An agent skill from coco-research/coco.

coco-research/coco

Speech-to-text transcription via OpenAI Whisper. An agent skill from coco-research/coco.

coco-research/coco

Earnings sentiment analysis, analyst estimates vs guidance, earnings surprise history, consensus sentiment, earnings revision trends, analyst rating changes, earnings beat miss track record…

agentii-ai/agentii-investment-intelligence

Build OCR pipelines in MATLAB using the ocr() function. An agent skill from matlab/matlab-agentic-toolkit.

matlab/matlab-agentic-toolkit

Compresses artifacts for judge evaluation. An agent skill from closedloop-ai/claude-plugins.

closedloop-ai/claude-plugins

Gemini画像生成APIでテキストから画像生成、既存画像の編集を行うスキル. An agent skill from minicoohei/ai-agent-camp.

minicoohei/ai-agent-camp

TikTok/YouTube動画を分析してテンプレート化するスキル. An agent skill from minicoohei/ai-agent-camp.

minicoohei/ai-agent-camp

Create a new custom agent for the workspace. An agent skill from evolution-foundation/evo-nexus.

evolution-foundation/evo-nexus

Tri-model orchestration — run the same task through Claude + Codex + Gemini in parallel and synthesize the best answer.

evolution-foundation/evo-nexus

Hybrid search (vector + BM25 via RRF + metadata boost) against the pgvector Knowledge base, with optional RAG synthesis.

evolution-foundation/evo-nexus

Direct a three-phase MiniMax H3 fireworks FPV flight: launch near ground in P1, complete one translated 360-degree orbit around P1's primary scene subject, then follow verified P2 bends to its…

karuvanan/MiniMax-H3-Director-Cut-Studio

Builds and edits a model-driven Power Apps app from a natural-language intent — tables, columns, relationships, adaptive forms with sub-grids, views, Choice-column charts, business rules, business…

microsoft/power-platform-skills

Guided workflow for building custom AI agents using the OpenHands Software Agent SDK.

OpenHands/extensions

A skill your agent uses when the user wants to estimate or predict the cost, token usage, or time of a task BEFORE it runs — "how much will this feature cost to build", "estimate the tokens for this…

Habitat-Thinking/ai-literacy-superpowers

Analyze videos with Google Gemini API (summaries, Q&A, transcription with timestamps + visual context, scene/timeline detection, video clipping, FPS control, multi-video comparison, and YouTube URL…

benchflow-ai/skillsbench

Analyze images and multi-frame sequences using OpenAI GPT vision models

benchflow-ai/skillsbench

Local self-check of instructions and mask outputs (format/range/consistency) without using GT.

benchflow-ai/skillsbench

High-performance numerical computing and machine learning workflows using JAX.

benchflow-ai/skillsbench

A skill your agent uses to review voice, visual, legal, and partner requirements before publishing social content.

gtmagents/gtm-agents

A skill your agent uses when reallocating spend across channels/ad sets or setting guardrails to stay on plan.

gtmagents/gtm-agents

A skill your agent uses to run pricing elasticity experiments with consistent assumptions and guardrails.

gtmagents/gtm-agents