AI & LLM Engineering

Guides building Tavily integrations for web search, URL extraction, site crawling and AI-assisted research in Python or JavaScript agent and RAG projects.

andrewyng/context-hub

SFT training reference for the ART framework. An agent skill from OpenPipe/ART.

OpenPipe/ART

LeetCUDA 中文技术书（584 页，XeLaTeX 源）按需查阅 skill——写、优化、调试或 review CUDA C++/PTX kernel 时的权威参考路由层。当任务涉及：GPU 架构/Roofline/ occupancy、向量化与 coalescing、warp/block reduce、softmax（online/LSE merge）、…

xlite-dev/LeetCUDA

Adds Liger Kernel support for a new HuggingFace Transformers model, or modifies existing monkey-patching.

linkedin/Liger-Kernel

Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.

onnx/onnx

Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.

microsoft/onnxruntime

Bump or upgrade the pinned versions of Helmor's bundled agent CLIs, SDKs, and supporting binaries — Claude Code + claude-agent-sdk (lockstep), Codex, Cursor SDK, OpenCode, Kimi, Pi, and gh / glab /…

dohooo/helmor

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.

Orchestra-Research/AI-Research-SKILLs

Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths…

sgl-project/sglang

Audits token waste and cost across Claude Code, Codex, OpenClaw, Hermes and OpenCode, with dollar savings.

alexgreensh/token-optimizer

Adds example documentation for a new model or environment in RLinf (RST pages in the docs gallery for both English and Chinese).

RLinf/RLinf

Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring.

lobehub/lobehub

Generates images through a 9Router gateway's image endpoint, with model discovery, the request fields and per-provider quirks for OpenAI, Gemini, MiniMax and others.

decolua/9router

A professional AI bounty hunter persona named Atlas. An agent skill from 1sadjlk/bounty-hunter-skill.

1sadjlk/bounty-hunter-skill

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

JimLiu/science-skills

Guide for adding a new model to the Archon engine. An agent skill from areal-project/AReaL.

areal-project/AReaL

Navigate Langfuse repositories, code areas, and agent skills.

langfuse/langfuse

Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.

rohitg00/ai-engineering-from-scratch

A skill your agent uses when working with Harbor's harbor exec CLI workflow: compiling files, directories, or globs into Harbor tasks; running map jobs; configuring artifacts and existence-only…

Arize-ai/phoenix

Routes every LLM call in a repository through the Caveman Cloud gateway in record mode, so requests and costs are measured without changing behavior.

JuliusBrussee/caveman

Diagnose and configure MemSearch memory behavior. An agent skill from zilliztech/memsearch.

zilliztech/memsearch

Run Pyrefly benchmarks locally via Buck or Cargo, including PyTorch real-world LSP benchmarks.

facebook/pyrefly

Measures and shrinks the ExecuTorch runtime binary by building a size test, analyzing it with bloaty and landing each reduction as its own pull request.

pytorch/executorch

Check Kiln's fine-tunable model list for deprecated or unsupported base models.

Kiln-AI/Kiln

Adds a new anomaly-detection model to anomalib under src/anomalib/models/.

open-edge-platform/anomalib

Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo.

sunny-glow/Auto-BenchMax

Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login…

diegosouzapw/OmniRoute

Build and maintain documentation sites with Mintlify. An agent skill from Arize-ai/phoenix.

Arize-ai/phoenix

Diagnoses and repairs a broken AutoRAG install so every configured datasource is both indexed and returns real search hits.

Marker-Inc-Korea/AutoRAG

Guides building on the 0G Compute Network, a decentralized GPU marketplace for AI inference and fine-tuning, with SDK patterns and CLI commands.

internet-court/internet-court-skill

Guide to building Node.js and TypeScript apps on the agent-squad package: orchestrator, agent types, classifier routing, storage, retrievers and MCP tools.

2FastLabs/agent-squad

Document undocumented public APIs in PyTorch by removing functions from coverageignorefunctions and coverageignoreclasses in docs/source/conf.py, running Sphinx coverage, and adding the appropriate…

pytorch/pytorch

Self-check your branch before creating a PR — catch dead code, prevent new model-specific Python examples, verify accuracy/perf claims, validate PR title format, and confirm merge readiness.

vllm-project/vllm-omni

Decide, don't guess — trigger on ANY combinatorial or ground-state decision where a plausible guess is worse than silence: rosters and on-call schedules, packing and placement, RAG passage…

brayonpi/hexstellar

TRIGGER when working with ai-sdk which is Laravel official first-party AI SDK.

trypostit/trypost

Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

R6410418/Jackrong-llm-finetuning-guide

Semantic code search and call-graph tracing. An agent skill from yoanbernabeu/grepai.

yoanbernabeu/grepai

Track daily activity logs and summaries for the user. An agent skill from memodb-io/Acontext.

memodb-io/Acontext

Writes and runs black-box benchmark cases for Windmill's flow, app, script, CLI and global AI generation modes, including before-and-after comparisons.

windmill-labs/windmill

Fetch and diagnose vLLM Buildkite CI failure logs. An agent skill from guqiong96/Lvllm.

guqiong96/Lvllm

Identify documentation gaps and prioritize the docs backlog.

strands-agents/harness-sdk

Run registered ComfyUI workflows through the fast comfyui-skill CLI, and use the official local Comfy MCP for live template, node, model, validation, and orchestration capabilities.

HuangYuChuh/ComfyUI_Skills_OpenClaw

Shows how to write custom cognee tasks, chain them into pipelines, store custom DataPoints and run enrichment over the existing graph.

topoteretes/cognee

Scans Python agent code for framework imports and recommends the matching Omnigent executor type, or says when the framework is not natively supported yet.

omnigent-ai/omnigent

Create a new skill in the current repository. An agent skill from Hyk260/PureChat.

Hyk260/PureChat

Stores, searches, and retrieves successful patterns with HNSW-indexed semantic search so agents can reuse past solutions instead of relearning them.

ruvnet/ruflo

Measure retrieval quality and latency of a deployed VSS search profile by ingesting a labelled dataset and running the vss CLI across retrieval paths.

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

Retrieve transcripts from YouTube, Instagram, TikTok, X, Vimeo and other video sites, summarize or analyze what was said (and shown on screen), or save an Obsidian-ready Markdown knowledge-base note…

JimmySadek/youtube-fetcher-to-markdown