10,094 tagged Data and AI, measured the same way as everything else here.
Browse within: LLM 284agent 131agents 126agentic-ai 120cli 77skills 69machine-learning 60anthropic-claude 59coding-agents 58chatgpt 57javascript 56ai-scientist 55openai 53bioinformatics 44
Skill Claude CodeCodex
Load for any work involving Baseten - deploying/operating models on Dedicated Inference (Truss, custom Docker servers, TRT-LLM engines, Chains), calling hosted Model APIs, running Training jobs (SFT/RL/LoRA), or Model Frontier Gateway.
ankhzw1876/ai-concept-xhs-skill
Skill Claude CodeCodex
A workflow for explaining artificial-intelligence terms and relationships as small-screen Xiaohongshu knowledge cards and diagrams. Xiaohongshu is a social platform where people commonly share visual posts.
ckpxgfnksd-max/prompt-compressor-openclaw
Skill Claude CodeCodex
Saves 20-40% of LLM tokens by teaching the agent to write compressed responses, compressed memory logs, and compressed pre-compaction summaries. Works via SOUL.md instructions — no hooks, no extra process, no dependencies. Also provides explicit compression when the user asks to compress a prompt. Use when the user…
Skill Claude CodeCodex
A local image-analysis tool for AI agents that cannot see images. It turns screenshots and document images into text, OCR coordinates, or structured descriptions of visual elements and page layout.
linhucong814-cyber/goal-prompt-template-skill
Skill Claude CodeCodex
A prompt-writing template that turns a rough goal, task, idea, or Chinese request into a clear instruction for an AI agent. It can also produce a persistent /goal prompt when requested.
Skill Claude CodeCodex
Build, run, and debug the one-level rmsnormbinary kernel (R-split RMSNorm) with SuperNPUBench + runop.py + gfrun/gfsim precision checks. Use when editing rmsnormbinarypto.hpp, rmsnormbinary tests, workspace/GetCacheId reduce, TADD cross-tile sum, or verifying [16,16384] fp16 binary RMSNorm. Shape dims are A (outer)…
Skill Claude CodeCodex
A prompt-based role-playing skill that makes an AI answer in the thinking style and voice associated with Qian Xuesen, a Chinese aerospace scientist and systems-engineering pioneer.
Skill Claude CodeCodex
Help users work with TROPT — the Textual Trigger Optimization Toolbox (https://github.com/matanbt/TROPT) for optimizing discrete text triggers that elicit specific behaviors from NLP models. The core job is helping users run, compose, and extend TROPT: invoking a Recipe Hub entry, swapping loss/optimizer/model in an…
Skill Claude CodeCodex
Use when a user wants to create, draft, improve, rewrite, or optimize a prompt for a general-purpose AI, especially when the request is vague, incomplete, or needs multi-turn clarification.
Skill Claude CodeCodex
A Chinese-language guide for writing prompts for ERNIE-Image, Baidu's image-generation model. It provides prompt templates and rules based on examples from the model's official prompt site.
Skill Claude CodeCodex
A guide for improving, rewriting, or creating prompts that can be copied and reused.
Skill Claude CodeCodex
A Chinese-language question-and-answer guide for Ascend inference repositories, which are software projects for running machine-learning models on Huawei Ascend hardware. It covers vLLM, MindIE, and related projects with evidence-based technical answers.
hkfrank996/mao-zedong-perspective
Skill Claude CodeCodex
A response style that imitates Mao Zedong’s documented thinking and speaking, based on public writings, interviews, and historical decisions.
q2522879285-source/minimax-h3-prompting-skill-public
Skill Codex
Guide an idea into a generation-ready MiniMax H3 / Hailuo H3 prompt or diagnose an inspected H3 output. Use for T2VA, I2VA, FL2VA, L2VA, or Ref2VA; text-only PV and kinetic type, Motion Design/MG, packaging and transitions, product/UI/game/MV/title work, localized reality-to-hand-drawn edits, audio/timbre reference…
302ai/302AI-API-Integration-Skill
Skill Claude CodeCodex
ALWAYS use this skill when user needs ANY API functionality (AI models, image generation, video, audio, text processing, etc.). Automatically search 302.AI's 1400+ APIs and generate integration code. Use proactively whenever APIs or AI capabilities are mentioned.
Skill Claude CodeCodex
Run massive language models (70B+) on consumer GPUs with only 4-8GB VRAM. No quantization, no model degradation.
LoveRain1997/video-to-h3-prompt
Skill Claude CodeCodex
Reverse-engineer a video into a complete MiniMax H3 prompt (T2VA / I2VA / FL2VA / L2VA / Ref2VA) ready to paste into H3. Use when the user provides a video file and a reference image and asks to feed H3, swap the character, recreate the same motion path, or generate a reusable script for a known choreography.…
Skill Codex
Build, modify, materialize, run, and verify DataCoolie projects. Use for workspace bootstrap, metadata authoring, environment overlays, capability checks, runners, notebooks, custom functions, narrow unsupported adapters, local tests, immutable builds, and project-owned build/CI automation. This is the sole…
LookAround0301/vllm-ascend-developer
Skill Claude CodeCodex
A development and debugging guide for vLLM and vLLM-Ascend, tools for running machine-learning models to generate responses. It covers inference accuracy checks, service management, automated tests, and code fixes for single-machine or split deployments.
Skill Claude CodeCodex
Use when translating Brazilian Portuguese messages into English prompts for Claude Code — preserves intent, clarifies ambiguity, and surfaces urgency signals that colloquial Portuguese would lose.
Skill Claude Code
Guide for training PyTorch models using this template's config-driven pipeline. Use this skill whenever the user wants to: train a model, create experiment configs (run.yaml / opt.yaml / best.yaml), run hyperparameter optimization (HPO) with Optuna, extract best parameters from an HPO study, set up a new experiment…
Skill Claude CodeCodex
Skill "notebookmd" from minhlucvan/notebookmd, covering notebookmd — ai agent data analysis skill, quick start, installation, when to use this skill and core concepts.
Skill Claude Code
File-Augmented Retrieval — generate persistent .meta sidecar files for PDFs, images, spreadsheets, videos and more, making every binary file readable to AI coding agents.
Skill Claude CodeCodex
Safeguard LLM calls using adaptive/extended thinking against token truncation. Use this skill when configuring API parameters for reasoning models (like Claude 3.7 Sonnet), when structured JSON outputs are returned unparseable or incomplete, or when designing cost-sensitive pipelines that utilize LLM reasoning.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: