Best AI and LLM engineering skills, page 14

Critic layer for the inference optimizer. An agent skill from AMD-AGI/Hyperloom.

AMD-AGI/Hyperloom

Evaluate and score agent behavior against a golden reference.

agentevals-dev/agentevals

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models).

MadAppGang/claudish

Update the libs/ SDK submodules (openai-go, anthropic-sdk-go, go-genai) to new upstream/fork versions, adapt tingly-box to API changes, and verify with build + vet + tests.

tingly-dev/tingly-box

Track, retrieve, screen, and synthesize research frontiers for geospatial AI, remote sensing big data, and transferable computer vision methods.

limi124/remote-sensing-research-radar

Run local black-box voice tests against the physical Dotty robot by playing a TTS prompt through the workstation speakers while the C920 records video and room audio.

BrettKinny/dotty-stackchan

End-to-end GECX/CXAS/CES conversational agent lifecycle -- build agents from requirements (PRD-to-agent), create and run evals (goldens, simulations, tool tests, callback tests), debug failures, and…

GoogleCloudPlatform/cxas-scrapi

Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink.

JayPokale/Chisle

Create agent company packages that conform to agentcompanies/v1.

paperclipai/paperclip

Migrates Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness while preserving the application's observed behavior.

pydantic/pydantic-ai

Build the standalone ZenDNN native library (zendnnl) from source with the alternate compute backends OFF (no oneDNN, libxsmm, parlooper, fbgemm), keeping AOCL DLP, which is the GEMM backend zendnnl…

amd/ZenDNN

YOLO 2026 — state-of-the-art real-time object detection. An agent skill from SharpAI/DeepCamera.

SharpAI/DeepCamera

Reference for the Opik SDK — tracing, span types, framework integrations, threads, and the prompt library (Python, TypeScript, REST).

comet-ml/opik-mcp

Inspect and compare PyTorch models with TorchScan reports, operator FLOPs, and peak-memory workloads.

frgfm/torch-scan

A skill your agent uses for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or…

theowenyoung/home

Anthropic Claude API patterns for Python and TypeScript. An agent skill from loulanyue/awesome-claude-notes.

loulanyue/awesome-claude-notes

中文 AI Agent 实习冲刺导师。用于生成 8 周 AI Agent 学习路线的每周大纲、每日 6 小时学习内容、基于反馈的后续调整，以及 Obsidian 双链知识点维护。适用于用户提出“生成 Week N 大纲”“生成 Day N”“根据反馈继续”“补全双链/生成知识点笔记”等请求时。输出必须为中文，围绕 AI-Interview 主项目，包含固定 5…

Marcos-wu/ai-agent-daily-mentor

Use FieldFlow to inspect and reduce noisy JSON CLI output before it reaches model context.

guillaumegay13/fieldflow

Embed proteins with Meta AI's ESM-2 (fair-esm package). An agent skill from JimLiu/science-skills.

JimLiu/science-skills

把一段中文（或任意 Whisper 支持语言）的会议/面试录音用本地 Whisper large-v3 转成文本，再清洗成带说话人标签、修过 ASR 错字、分好章节的 markdown 文档（可选再转成 docx）。跨平台（macOS Apple Silicon 用 mlx-whisper，Windows/Linux/Intel Mac 用…

xiaopengde/murmur

Add a new hardware inference backend to AutoRound for deploying quantized models (e.g., CUDA/Marlin, Triton, CPU, HPU, ARK).

intel/auto-round

Updates the docs website after a change to the SDK or CLI. An agent skill from tetherto/qvac.

tetherto/qvac

Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/.

activeloopai/hivemind

Prepare, publish, refresh, or validate the TraceLab public dataset on Hugging Face under UW-SyFI/TraceLab.

uw-syfi/TraceLab

Integrate new evaluation datasets into FlagEvalMM as benchmark tasks.

flageval-baai/FlagEvalMM

Check model compatibility with xinfer before loading. An agent skill from guoqingbao/xinfer.

guoqingbao/xinfer

Human handoff, Linear branch names, reviewable (non-draft) PRs, the cursor GitHub label, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and…

langfuse/langfuse

Create or edit a live-rules instruction in the project's atomic rule set.

Eigenwise/eigenwise-toolshed

Configure and launch SparkDiffusion sparse finetuning for Wan 2.1 or Wan 2.2.

AlibabaResearch/SparkDiffusion

Propose an improved version of a prompt registered in a self-hosted AgentX (AgentX-trace-eval) instance, using real low-rated evaluation results as evidence, then publish it as a new version once…

AgentX-ai/AgentX-Trace-Eval

Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading.

wanshuiyin/ARIS-in-AI-Offer

Teaches an agent to build LM pipelines, RAG systems and agents in DSPy using signatures, modules and optimizers instead of hand-tuned prompts.

Orchestra-Research/AI-Research-SKILLs

Guides an agent through tracking ML experiments with W&B: run logging, config capture, hyperparameter sweeps, artifacts and a model registry.

Orchestra-Research/AI-Research-SKILLs

Uses the Outlines library to constrain model output to a JSON schema, Pydantic model, regex or fixed set of choices when running local models.

Orchestra-Research/AI-Research-SKILLs

Set up or repair Entrix guardrail specs in the current repository by discovering real quality signals, generating docs/fitness, and iterating with entrix validation until the result is executable.

phodal/entrix

A skill your agent uses when creating, improving, or troubleshooting Claude Code subagents.

NangoHQ/nango

A skill your agent uses when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on /v1/listen - summarize, topics, intents, sentiment, diarize…

deepgram/deepgram-js-sdk

This skill should be used when finding, tracing, or understanding code in a repository with SymDex available.

husnainpk/SymDex

Skill for compiling and writing release notes for langchain-azure packages.

langchain-ai/langchain-azure

Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR.

PackmindHub/packmind

Shows how to replace unsafe hasattr and setattr loops over user-controlled kwargs with an explicit allowlist when configuring ONNX Runtime option objects.

microsoft/onnxruntime

Search 2500+ curated ChatGPT and LLM open-source repositories.

taishi-i/awesome-ChatGPT-repositories

Add, move, rename, or delete a page on the LangChain docs site.

langchain-ai/docs

Runs the `autoctx` CLI to improve an approach to a task over several generations, score or refine a single output and inspect what a run produced.

greyhaven-ai/autocontext

Used to invoke the PXMeter tool for rigorous quality assessment of biomolecular structure prediction models (e.g., proteins, nucleic acids, small molecules).

bytedance/PXMeter

A skill your agent uses whenever the user asks to generate, collect, inspect, or prepare early-experience training data (Implicit World Modeling or Self-Reflection, in the sense of arXiv:2510.08558)…

OSU-NLP-Group/EarlyExperience

Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares).

zhongkaifu/TensorSharp

A skill your agent uses when quantizing a diffusion DiT with NVIDIA ModelOpt and making the resulting FP8 or NVFP4 checkpoint loadable, verifiable, and benchmarkable in SGLang Diffusion.

sgl-project/sglang