AI & LLM Engineering · For data scientists

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

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

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

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

R6410418/Jackrong-llm-finetuning-guide

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

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

A skill your agent uses when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies…

Optim-Agent/optim-agent

Operates the Inspire ML platform through its local `inspire` CLI: picking account, workspace and resources, launching notebooks, jobs and services, then cleaning up.

realZillionX/InspireSkill

Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.

stas00/the-art-of-debugging

Builds agent evaluations in stages: inspect the repository and traces, agree a Task Spec with you, then build, audit and run a Harbor task with an independent verifier.

langchain-ai/langchain-skills

Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost.

luongnv89/asm

Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus

ruvnet/agentic-flow

Shows how to load, train and use fast Hugging Face tokenizers, with BPE, WordPiece and Unigram models, padding, truncation and alignment tracking.

Orchestra-Research/AI-Research-SKILLs

Adds a new publication page to the RLinf Sphinx docs (EN + ZH) and wires it into the Publications index/toctree.

RLinf/RLinf

逸尘自用的互联网研究总入口。用于跨平台且跨阶段、用户尚未确定工具，或明确要求对公司、产品、人物、技术、行业和领域做横纵分析、发展史加现状对比或有来源约束的系统深度研究；先生成有截止日期和证据闸门的计划，再把搜索发现、候选核验、有限归档、按需转写和证据综合路由到…

mcncarl/yichen-skills

Guide for adding a new dataset loader to AReaL. An agent skill from areal-project/AReaL.

areal-project/AReaL

Integrate a benchmark or custom environment into SAfactory using fixed adapter templates and local contract tests, optionally run Docker/RJob evaluation, or prepare GRPO/RL training.

AI45Lab/SAfactory

Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g.

google-gemma/gemma-skills

Search the public web through Serper instead of the built-in WebSearch tool.

agentscope-ai/ReMe

Evaluate and improve GenAI models and agents using the Google GenAI Evaluation SDK.

GoogleCloudPlatform/vertex-ai-samples

Indexes research papers on the Hugging Face Hub from arXiv, links them to models and datasets, claims authorship and generates markdown research articles from templates.

huggingface/skills

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

cloudnative-co/claude-code-starter-kit

Runs the anomalib benchmarking pipeline to train/evaluate a grid of model + dataset (+ category) combinations and collect metrics into a results CSV.

open-edge-platform/anomalib

Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

digoal/blog

Query AI Safety HOT news, research papers, incidents, hot topics, and daily/weekly/monthly reports through its public read-only MCP service.

wuyoscar/AISafetyHot-Hub

Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.

maslennikov-ig/claude-code-orchestrator-kit

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

KartikLabhshetwar/mind-mentor

Apply a Claude Fable 5 inspired operating style inside Codex.

baskduf/FableCodex

Onboard a new model family (Nemotron or third-party) into skills/ — paper chunks, recipe summaries, context packs, and model card.

NVIDIA-NeMo/Nemotron

A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

MigoXLab/dingo

Searches, saves, and maintains a local document index through a local RAG MCP server.

shinpr/mcp-local-rag

Benchmark and compare LLM models for SUB/WAVE's on-air calls — track picks, segments, listener requests, DJ scripts, banter, and programme beats — in both candidate-pool and agent modes, using…

perminder-klair/subwave

AI-assisted dataset annotation with COCO export — bbox, SAM2, DINOv3 methods

SharpAI/DeepCamera

Adapt AutoRound to support a new diffusion model architecture (DiT, UNet, hybrid AR+DiT).

intel/auto-round

Optimizes the performance of existing Liger Kernel Triton kernels.

linkedin/Liger-Kernel

Guide to LLaVA for image chat, visual question answering and captioning, with model sizes, CLI and Gradio usage and multi-turn conversation code.

Orchestra-Research/AI-Research-SKILLs

Create a new custom agent from scratch. An agent skill from gnekt/My-Brain-Is-Full-Crew.

gnekt/My-Brain-Is-Full-Crew

Fills in a model card for an OpenMed clinical NER or de-identification model from its evaluation reports: intended use, metrics, subgroups and limitations.

maziyarpanahi/openmed

Drives persistent Claude Code, Codex, or OpenCode agent sessions through a Dynamo OpenAI/Anthropic-compatible endpoint over Agent Client Protocol (ACP).

ai-dynamo/dynamo

Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.

huggingface/skills

Comprehensive guide for building Agentic RAG systems using Microsoft Agent Framework in C.

shuyu-labs/WebCode

Grow or shrink the EBS volume that holds the app host's data directory (/var/www/blot/data), with config/host/data-volume/resize.sh (grow in place; shrink by live rsync passes, a brief read-only…

blotcms/blot