AI & LLM Engineering

Transcribe local audio or video with Volcengine Doubao file ASR, including BigASR 1.0 Turbo direct upload and asynchronous 1.0 standard, 1.0 idle, or 2.0 standard jobs through TOS.

ysyecust/lecture-to-notes

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

Comfy-Org/workflow_templates

Benchmark a third-party coding-agent harness against FrontierHarness Eval using Runta runtimes.

frontier-harness-eval/eval

Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval.

iflytek/skillhub

Diagnose broken Hugging Face Gradio Spaces from their actual logs and pinned source, then prepare a minimal verified source fix as candidate files.

huggingface/hf-mcp-server

Add a cross-cutting decision pattern under src/nemotron/steps/patterns/.

NVIDIA-NeMo/Nemotron

Explain the IM+Agent framework: create+send as minimal primitives, IM system vs agent loop separation, message vs llmHistory, and the recursive property.

chmod777john/swarm-ide

Coaches a token-efficient Claude Code or Codex setup from the user's own usage data.

alexgreensh/token-optimizer

A skill your agent uses when installing, verifying or configuring OMNI, when command output carries an [OMNI: ...] marker, or when output looks shorter than expected.

fajarhide/omni

Helps an agent write ComfyUI custom nodes in Python, including wrapping an existing script, mapping data types and handling image batches.

ConstantineB6/comfy-pilot

CUDA kernel development, debugging, and performance optimization for Claude Code.

technillogue/ptx-isa-markdown

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration.

MoizIbnYousaf/ai-agent-skills

Review RAG designs or accessible implementations for extraction failures, deterministic facts, evidence routing, source versioning, code retrieval, and memory boundaries.

FinanceFlash/unvibecode

A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…

Mesh-LLM/mesh-llm

Migrate Python Agno applications to Pydantic AI and, only when needed, Pydantic AI Harness.

pydantic/pydantic-ai

Real-time depth map privacy transforms using Depth Anything v2 (CoreML + PyTorch)

SharpAI/DeepCamera

Read Tessera satellite embeddings with the geotessera Python library.

ucam-eo/geotessera

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

LLM provider initialization for bridgic projects. An agent skill from bitsky-tech/bridgic.

bitsky-tech/bridgic

Scaffold a brand-new Comet example in this repo from the canonical template under templates/integration-example/.

comet-ml/comet-examples

Adapt AutoRound to support a new LLM architecture that doesn't work out-of-the-box.

intel/auto-round

Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity.

zscole/model-hierarchy-skill

Create, track and update team goals in Hivemind via the hivemind CLI.

activeloopai/hivemind

A skill your agent uses when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval.

andrea9293/mcp-documentation-server

Cross-harness orchestrator for AI coding work. An agent skill from alexgreensh/outsourcerer.

alexgreensh/outsourcerer

Iteratively optimize a CUDA/CUTLASS/Triton kernel only when strict on-device compilation, correctness, timing, and NCU evidence gates pass.

KernelFlow-ops/cuda-optimized-skill

Interact with Langfuse and access its documentation: tracing, monitoring, creating datasets, running experiments, and evaluating AI applications.

langfuse/skills

Capture and organize general facts about the user by topic. An agent skill from memodb-io/Acontext.

memodb-io/Acontext

Generate a fact-checked academic personal homepage from a CV, optionally augmented by an existing manual homepage and an assets directory.

wanshuiyin/ARIS-in-AI-Offer

Create or operate a portable, auditable Chinese book-review short-video workflow from a clean local workspace.

jaxxchen003/book-video-factory

Look up what a Biohub ESM-C sparse-autoencoder (SAE) feature means — its label, description, top-activating proteins, decoder neighbours, and activation statistics — by querying the Biohub…

softnanolab/bagel

驱动 One-Eval 对 API 或本地模型做端到端评测，覆盖纯文本、多模态、代码生成、函数调用和 Agent benchmark。当用户想评测模型在一个或多个 benchmark 上的表现、比较分数、补充 metric，或生成图文评测报告时使用本 skill。

OpenDCAI/One-Eval

Runs LLM-based rubric judging on agent output and loops revise-and-rejudge rounds until a quality threshold is met.

greyhaven-ai/autocontext

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods.

Orchestra-Research/AI-Research-SKILLs

Trigger the bot-cherry-pick workflow for a batch of merged PRs onto a release branch and monitor each run to completion.

sgl-project/sglang

Search local documents, files, notes, and knowledge bases. An agent skill from gmickel/gno.

gmickel/gno

Search and recall relevant memories from past sessions via memsearch.

zilliztech/memsearch

Diagnose failed, hung, slow, OOM, NaN, illegal-memory-access, NCCL, compilation, rollout, or training runs in AReno.

inclusionAI/AReno

在 Paddle 代码库中定位问题并输出高质量调试报告的专用技能。当遇到以下场景时优先使用：(1) Paddle 框架 bug 调试，(2) 算子实现问题排查，(3) 训练脚本异常诊断，(4) 分布式训练故障定位，(5) CUDA/GPU 相关错误处理，(6) 需要生成结构化调试报告。

PaddlePaddle/Paddle

Cross-check RLinf documentation against code, natural explanation flow, and other docs, including English-Chinese parity.

RLinf/RLinf

Port a PyTorch model to use pyrefly's tensor shape type system (Tensor[[B, C, H, W]], Int[T]).

facebook/pyrefly

在发布前评估 Agent Skill bundle 的结构完整性、触发质量、产物改进、脚本正确性、安全性、已安装目录树完整性和目标宿主可移植性。

fancyboi999/ai-engineering-from-scratch-zh

Write and run custom Pi prompt templates (slash commands) for this extension.

nicobailon/pi-prompt-template-model

Helps design and build AI agents for any domain around a minimal loop of capabilities, knowledge and context, adding planning or subagents only when needed.

shareAI-lab/lab-skills

Drives a self-hosted Open Notebook instance to organize sources into notebooks, chat with documents, generate notes and multi-speaker podcasts, and search across material.

agent-skills-hub/agent-skills-hub

Benchmark and profile the Dynamo frontend (dynamo.frontend HTTP + tokenizer + KV router) against mock workers (dynamo.mocker).

ai-dynamo/dynamo

Finds llama.cpp-compatible GGUF models on the Hugging Face Hub, picks a quantization for your hardware and launches them with llama-cli or llama-server.

huggingface/skills

Trains and fine-tunes object detection, image classification and SAM or SAM2 segmentation models on Hugging Face Jobs cloud GPUs and saves the results to the Hub.

huggingface/skills