Best AI and LLM engineering skills, page 7

Auto Review closeout. An agent skill from vincentkoc/tokenjuice.

vincentkoc/tokenjuice

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

Arize-ai/phoenix

Adds a new local feature matching model from a GitHub repository to the image-matching-webui project as a working WebUI option.

Vincentqyw/image-matching-webui

Write LLM evaluation spec files with datasets, tasks, and evaluators using the @kbn/evals Playwright fixture.

elastic/kibana

Reference for designing and tuning production LLM prompts: few-shot examples, chain-of-thought, structured outputs, templates and system prompts.

wshobson/agents

Lets an agent drive DeepChat's bundled CLI for model calls, media generation, transcription, OCR, artifacts, configuration, Skills and MCP operations, within strict command rules.

ThinkInAIXYZ/deepchat

This skill should be used when the user asks to "create a new prompt sample", "add a new prompt sample", "scaffold a new prompt sample", "create a prompt contribution", "add a prompt", or needs to…

pnp/copilot-prompts

Pixel-based motion and UI change analysis from frame sequences or screenshots using computer vision and visual comparison.

edwardsanchez/MotionEyes

Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.

breaking-brake/cc-wf-studio

mlx-serve pre-release validation checklist, CalVer versioning, release steps, and CHANGELOG style.

ddalcu/mlx-serve

Developer guide for the Cortex-M (CMSIS-NN) backend in ExecuTorch: quantization pipeline, pass manager, tests and adding new ops.

pytorch/executorch

Operates the ccproxy inspector MITM system for intercepting, inspecting, and transforming LLM API traffic.

starbaser/ccproxy

Builds a browser-based annotation page for reviewing LLM traces one at a time with pass/fail labels, notes and saved results, tailored to your data.

ai-evals-course/evals-skills

This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe…

evo-hq/evo

Sends one prompt to Claude, GPT through the Codex CLI and Gemini, then tabulates response time, token use and cost, with an optional judged quality score.

garrytan/gstack

High-level guide for integrating a new DiT model into cache-dit: Cache (BlockAdapter/ForwardPattern), Context Parallelism, Tensor Parallelism, Text Encoder Parallelism (TE-P), VAE Parallelism…

vipshop/cache-dit

Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document.

NVIDIA/Megatron-LM

Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design.

rmyndharis/antigravity-skills

Runs and configures the anomalib tiled-ensemble pipeline, which trains/evaluates one model per image tile and merges results (with optional seam smoothing) for high-resolution anomaly detection.

open-edge-platform/anomalib

Syncs or audits ccLoad's CLIProxyAPI protocol-conversion core and registered provider adapters against one pinned upstream commit, then verifies the result.

caidaoli/ccLoad

Meta-research под вопрос или решение: веб-поиск, источники, Q&A отчёт с цитатами по файлам для повторного использования.

Socialpranker/deepdive

Adapts and debugs Hugging Face or local models to run on vLLM with Ascend NPU, validates them by serving, and delivers the result as one signed commit.

vllm-project/vllm-ascend

A skill your agent uses when maintaining or optimizing OpenClaw workspace files — AGENTS.md, TOOLS.md, SOUL.md, USER.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, and related checklists and…

win4r/openclaw-workspace

Router for adding a diffusion or omni pipeline to verl-omni.

verl-project/verl-omni

Create, edit, evaluate, and package agent skills. An agent skill from smixs/skill-conductor.

smixs/skill-conductor

Guide for upgrading Stripe API versions and SDKs. An agent skill from kanchengw/cnllm.

kanchengw/cnllm

Profiles, benchmarks and tunes AI training workloads on Moore Threads MUSA GPUs with a measurement-first process that keeps model behavior unchanged.

open-infra-skills/infra-skills

Manage CI for PyTorch ghstack stacks by running CI where its results are useful now and deferring other PRs with [no-ci].

pytorch/pytorch

Review pull requests and local branches for vllm-project/vllm-omni with a frozen snapshot, module-design ownership, feature-design overlays, targeted validation, and concise evidence-backed findings.

vllm-project/vllm-omni

Process documents with Blockify API to create optimized IdeaBlocks for RAG.

iternal-technologies-partners/blockify-agentic-data-optimization

Run and report repository model or provider-mapping benchmarks.

theopenco/llmgateway

Comprehensive Mastra framework guide. An agent skill from LiorVainer/data-israel.

LiorVainer/data-israel

Diagnose OpenAI-compatible model-serving failures from symptoms, endpoint reports, explicit configuration files, or logs while preserving evidence status and requiring confirm/refute checks.

Blackwellboy/model-serving-minefield

Universal quality bar and final audit rubric for any agent system prompt.

mastra-ai/mastra

Builds a retail product search agent on Google Cloud, from catalog ingestion into BigQuery and Vector Search to ADK scaffolding, evaluation and Cloud Run deployment.

google/adk-recipes

A skill your agent uses when wrapping CLI binaries in JavaScript, automating shell workflows in TypeScript, composing multiple CLIs into scripts, or building agent tool-use.

millionco/cli-to-js

Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

graphsignal/graphsignal

Clean up noisy startup warnings and spurious prints in SGLang server logs.

guqiong96/Lsglang

Edits, updates, rewrites, or adds content on the ComfyUI template site pages.

Comfy-Org/workflow_templates

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails…

RedWoodOG/Hermes-Desktop

Authoring and running behavioral evals for a shopping or merchant agent, covering the case shape, authoring rules, code graders and judges, the run pattern, and poisoned fixtures.

anthropics/commerce-agents

Add or modify an AI chat tool ("Ask Ryo" capability) in ryOS.

ryokun6/ryos

Generate images via OpenAI Images API (GPT Image, DALL-E 3, DALL-E 2).

swarmclawai/swarmclaw

Analyzes and improves prompts using 31 frameworks across 7 intent categories.

ckelsoe/prompt-architect

A skill your agent uses for ANY bug, error, crash, wrong output, loss divergence, gradient explosion, test failure, CUDA error, distributed training hang, checkpoint load failure, or unexpected…

ByteDance-Seed/VeOmni

Installs and configures ktx, the open-source context layer for data agents — runs ktx setup non-interactively with hidden CLI flags, configures database connections and embeddings, installs agent…

Kaelio/ktx

Create a new Langfuse integration page in the langfuse-docs repo.

langfuse/langfuse-docs

Kiln's code conventions and per-area gotchas, plus a diff gate that enforces the mechanical ones.

Kiln-AI/Kiln