Best AI and LLM engineering skills, page 16

Adds a new task to the bench-swe pipeline from a real GitHub bug-fix issue or pull request, then checks the generated task file and patch.

ory/lumen

Selects a fine-tuning technique (SFT, DPO, RLVR, or RLAIF) for the user's use case and validates it against the selected model's available recipes.

awslabs/agent-plugins

Builds diverse synthetic test inputs for LLM pipeline evaluation by defining failure-focused dimensions, drafting tuples with you and turning them into realistic queries.

ai-evals-course/evals-skills

Author and run multi-agent workflows with the omegacode CLI — JavaScript files that orchestrate Codex (gpt-5.x) and Claude Code agents deterministically via agent()/parallel()/pipeline()/phase().

SawyerHood/omegacode

AWS Bedrock foundation models for generative AI. An agent skill from itsmostafa/aws-agent-skills.

itsmostafa/aws-agent-skills

Writes Terraform alerting policies for AI agents that emit OpenTelemetry metrics, covering reliability, cost, safety, security and quality signals on Google Cloud.

google/skills

Use this skill working with Phoenix Framework. An agent skill from podlove/radiator.

podlove/radiator

A skill your agent uses when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage

butterbase-ai/butterbase-skills

Guide for using the NeuroLink SDK and CLI. An agent skill from juspay/neurolink.

juspay/neurolink

Quick-reference help for fine-tuning language models with Axolotl, covering YAML configs, FSDP, context parallelism, compressed saves and dataset formats.

Orchestra-Research/AI-Research-SKILLs

OpenVideo skill (v0.1.0): generate high-quality local video with the OpenVideo product (MiniMax H3 backend).

agent-next/video-agent

A skill your agent uses when the user needs academic paper retrieval — searching scientific literature by author/year/journal, finding paper chunks for RAG-style citations, or expanding original…

opendatalab/Sciverse-Agent-Tools

Find which provable-contracts YAML contracts a Hugging Face model needs, create missing contracts, generate Rust artifacts, and implement all stubs.

paiml/aprender

Write, debug, and optimize CUTLASS, CuTe, and CuTeDSL GPU kernels from local upstream source, examples, and headers.

slowlyC/agent-gpu-skills

Refresh RepoPrompt tool guidance when the CLI/MCP surface changes.

w-winter/dot314

Solutions for non-trivial PerforatedAI integration scenarios.

PerforatedAI/PerforatedAI

Write less code and say less about it. An agent skill from Green-PT/honey-for-devs.

Green-PT/honey-for-devs

Run a 5 Persona Advisory Board review, board review, strategic decision stress-test, offer critique, risk check, or pricing/timing/positioning decision review.

harryvondiesel-web/5-persona-advisory-board

The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models.

oxbshw/watch-skill

Train a custom VideoHighlighter action or object model from a few videos the user provides — cut into samples, sort with CLIP, review contact sheets, build, train, install only if better.

Aseiel/VideoHighlighter

Helps show a model provider's usage, balance or quota in PiDeck: checks built-in support, points to the dialog templates, or writes a custom probe entry.

ayuayue/PiDeck

Submit, monitor and benchmark jax-gcm (jcm) simulations on NCAR Derecho's PBS queues.

climate-analytics-lab/jax-gcm

Add or retrofit Tenuo authorization for AI-agent tools and effects.

tenuo-ai/tenuo

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end.

microsoft/GitHub-Copilot-for-Azure

Preflight checks and diagnosis for ten known failure modes of ML training on NVIDIA DGX Spark's GB10, spanning launch errors, memory, thermals, bandwidth and precision.

wshobson/agents

MetaKim executable governance dispatcher. An agent skill from KimYx0207/Meta_Kim.

KimYx0207/Meta_Kim

GPU optimization workflow using uipc.profile, uipc.profile.nsight, and Nsight Compute CLI.

spiriMirror/libuipc

Work on the Nexus LLM eval harness in tests/eval/ — author or fix a scenario fixture, write an eval config, change the executors, assertions or reports, or explain a run that produced nothing…

ProfSynapse/nexus

How to write and run verl-omni CPU tests (testoncpu.py) that exercise adapters, rewards, and configs without a GPU or model weights.

verl-project/verl-omni

Builds an OpenEnv (Hugging Face) variant of an RL environment.

adithya-s-k/FineEnvs

A skill your agent uses when you need documentation for a third-party library, SDK, or API before writing code that uses it — for example, "use the OpenAI API", "call the Stripe API", "use the…

sudomakes/backroad

Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods.

caliber-ai-org/ai-setup

Search papers from top AI/ML conferences. An agent skill from Xiangyue-Zhang/auto-deep-researcher-24x7.

Xiangyue-Zhang/auto-deep-researcher-24x7

This skill should be used when working with DSPy.rb, a Ruby framework for building type-safe, composable LLM applications.

davekilleen/Dex

Guide for writing eval conversation JSONs and running them through policy engines

open-bias/open-bias

Search local videos by meaning, exact words or reference image, analyze scenes, and export clips using the cerul CLI.

cerul-ai/cerul

Shows how to call NEAR AI Cloud through an OpenAI-compatible API and verify that inference ran in a TEE, using attestation checks and signed chat responses.

internet-court/internet-court-skill

Debug PyTorch 2 compiler stack failures including Dynamo graph breaks, Inductor codegen errors, AOTAutograd crashes, and accuracy mismatches.

pytorch/pytorch

A skill your agent uses when adding, debugging, or modifying LLMObs plugins for an LLM library in dd-trace-js.

DataDog/dd-trace-js

Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.

brevdev/workshop-build-an-agent

Measure whether an RT-VLM configuration change altered caption quality — capture paired baseline and candidate captions for a set of videos, score both against a ground truth with an LLM judge, and…

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

Rules for measuring or quoting any benchmark number in this repo.

jgravelle/jcodemunch-mcp

A skill your agent uses when writing, modifying, porting, or optimizing CuTe DSL GPU kernels in Python; reading CuTe DSL API reference material; integrating a CuTe DSL kernel into a project; or…

vipshop/cache-dit

A skill your agent uses when releasing a beta build of this Obsidian plugin for BRAT-based testing (e.g.

joybro/obsidian-similar-notes

Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in…

overmind-core/overmind

Configure and use Duel Agents model routing in Claude Code. An agent skill from 2aronS/Duel-Agents.

2aronS/Duel-Agents

Guides training and analyzing sparse autoencoders with SAELens to break neural network activations into interpretable features, including superposition and monosemanticity studies.

Orchestra-Research/AI-Research-SKILLs

Shows how to use Pinecone, a managed vector database, for production RAG, semantic search and recommendations: indexes, upserts, queries, filters and namespaces.

Orchestra-Research/AI-Research-SKILLs