Best AI and LLM engineering skills, page 6

Adding a Community Agent Skill: a Markdown attack-workflow file that users import from the catalog, which then competes in the Intent Router and is injected into the agent's system prompt.

samugit83/redamon

设置 Claude Code hooks，在危险 git commands（push、reset --hard、clean、branch -D 等）执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks，或在 Claude Code 中阻止 git push/reset 时。

vinvcn/mattpocock-skills-zh-CN

Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.

maslennikov-ig/claude-code-orchestrator-kit

Measure whether a change makes Chat's styling replies better, with yarn eval:chat — it runs styling requests on recorded real pages for two versions of Stylebot and measures on the page whether each…

ankit/stylebot

A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search.

luochang212/dive-into-langgraph

Sets up an isolated per-worktree Python environment for attention-gym development using nightly PyTorch and the CI-mirroring uv flow.

meta-pytorch/attention-gym

Checks that ReasoningConfig fields are serialized into the right provider-specific JSON for OpenRouter, Anthropic, GitHub Copilot and Codex requests.

tailcallhq/forgecode

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

KartikLabhshetwar/mind-mentor

Investigate AI traces, observations, exceptions, latency, sessions, prompts, datasets, annotation queues, and scores through Langfuse MCP.

avivsinai/langfuse-mcp

Know what every AI call really costs — floe-guard meters STT + TTS + LLM + telephony per call (Pipecat, LiveKit — Python & TypeScript), keeps a live ledger of real spend, and hard-stops the next…

Floe-Labs/floe-guard

A skill your agent uses when a user wants to search archived VSS video or ingest or delete a source for search.

NVIDIA-AI-Blueprints/video-search-and-summarization

Apply a Claude Fable 5 inspired operating style inside Codex.

baskduf/FableCodex

Defines the nestia product contract, workspace layout, package boundaries, the Go plugin composition model, and canonical commands.

samchon/nestia

DyNote: systematically and efficiently extract raw Douyin/DY video data and analyze videos, comments, accounts, hashtags, and short-video scenes into evidence-graded learning notes, summaries…

Rimagination/dy-note

Onboard a new model family (Nemotron or third-party) into skills/ — paper chunks, recipe summaries, context packs, and model card.

NVIDIA-NeMo/Nemotron

A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

MigoXLab/dingo

Integrate Databuddy analytics using the SDK, REST API, or MCP.

databuddy-analytics/Databuddy

Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.

dstackai/dstack

Retrieve real Taiwan court judgments with verifiable citations before answering any question about Taiwan law or case law.

aa0101181514/tw-legal-rag

Searches, saves, and maintains a local document index through a local RAG MCP server.

shinpr/mcp-local-rag

Plan a token-efficient Claude Code or Codex setup, or get a quick health check.

alexgreensh/token-optimizer

Query AI Safety HOT news, research papers, incidents, hot topics, and daily/weekly/monthly reports through its public read-only MCP service.

wuyoscar/AISafetyHot-Hub

Read and search GitHub repository documentation via gitmcp.io MCP service.

AgentTeam-TaichuAI/ScienceClaw

Benchmark and compare LLM models for SUB/WAVE's on-air calls — track picks, segments, listener requests, DJ scripts, banter, and programme beats — in both candidate-pool and agent modes, using…

perminder-klair/subwave

Run the repository commit workflow when the user explicitly asks to commit changes or create a save-point commit.

Julian-adv/OpenMMO

AI-assisted dataset annotation with COCO export — bbox, SAM2, DINOv3 methods

SharpAI/DeepCamera

A skill your agent uses when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos.

aws-samples/sample-kolya-br-proxy

Turn 2+ user reference images into a high-fidelity animated Codex companion using PocketMen's own local stack.

six-nut/PocketMen-with-you

Adapt AutoRound to support a new diffusion model architecture (DiT, UNet, hybrid AR+DiT).

intel/auto-round

Workflow for porting an existing Triton kernel in fla/ops/ to Gluon (triton.experimental.gluon) to gain explicit control over tensor layouts, shared memory, async data movement (cp.async / TMA), MMA…

fla-org/flash-linear-attention

Trains and evaluates several WiFi-signal-based pose and sensing models, from unsupervised pose estimation to domain adaptation and publishing.

ruvnet/RuView

Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/.

activeloopai/hivemind

Optimizes the performance of existing Liger Kernel Triton kernels.

linkedin/Liger-Kernel

Build, debug, and interpret vLLM GPU kernel microbenchmarks for CUDA, Triton, and CuteDSL, including CUPTI timing, correctness checks, generated-code inspection, multi-GPU measurements, and SOL…

guqiong96/Lvllm

Guide to LLaVA for image chat, visual question answering and captioning, with model sizes, CLI and Gradio usage and multi-turn conversation code.

Orchestra-Research/AI-Research-SKILLs

Create a new custom agent from scratch. An agent skill from gnekt/My-Brain-Is-Full-Crew.

gnekt/My-Brain-Is-Full-Crew

Fills in a model card for an OpenMed clinical NER or de-identification model from its evaluation reports: intended use, metrics, subgroups and limitations.

maziyarpanahi/openmed

Audit local AI coding-agent sessions with agenttrace. An agent skill from luoyuctl/agenttrace.

luoyuctl/agenttrace

Drives persistent Claude Code, Codex, or OpenCode agent sessions through a Dynamo OpenAI/Anthropic-compatible endpoint over Agent Client Protocol (ACP).

ai-dynamo/dynamo

Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM.

NVIDIA/OpenShell

Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.

huggingface/skills

Comprehensive guide for building Agentic RAG systems using Microsoft Agent Framework in C.

shuyu-labs/WebCode

URL search param and hash state management. An agent skill from promptfoo/promptfoo.

promptfoo/promptfoo

Quick reference for wdoc, a command-line and Python tool that summarizes, searches and answers questions over documents of many file types.

thiswillbeyourgithub/wdoc

This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token…

guanyang/open-agent-hub

Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking.

nkapila6/mcp-local-rag

Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates.

lllllllama/RigorPilot-Skills

Write efficient GraphQL queries against the Phoenix API. An agent skill from Arize-ai/phoenix.

Arize-ai/phoenix