Design and implement AI copilots that analyze structured data and propose mutations for human approval (draft → apply), not direct writes. Covers prompting, multistep compound requests (remove + add in one turn), FIFO client queuing for long agent loops, validation, session memory, optimistic versioning UX, copilot…
★not rated 176 3d agoASkillSpector: warn141 tokens
originalMIT
Leverage Retrieval Augmented Generation to retrieve relevant information from a a LlamaCloud Index. Requires the llamacloudservices package and LLAMACLOUDAPIKEY as an environment variable.
Use inside RSIBench-Data when testing whether an automation agent can improve a target model on a configured benchmark through synthetic Tinker SFT data, Tinker sampling, and E2B-based Harbor evaluation.
LLM tarafından sürekli inşa edilen ve güncellenen kalıcı, birikimli bir bilgi arşivi (persistent wiki) deseni. Standart RAG'ın aksine her sorguda bilgi yeniden keşfedilmez — ajan yeni kaynakları okur, mevcut wiki'ye entegre eder, varlık/kavram sayfalarını günceller, çelişkileri işaretler, çapraz-referansları korur.…
Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.
Write a high-quality prompt for any LLM or AI assistant — Claude, Claude Code, ChatGPT, Gemini, Cursor, Windsurf, Copilot, or any coding / chat agent. Use this skill whenever the user asks to write, improve, refine, shorten, or rewrite a prompt; asks "how should I phrase this for [model]" or "what's a good prompt for…
Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images. Use when you need to understand screenshots, UI layouts, diagrams, or any image content. Supports png/jpg/webp/gif.
ANDREJ KARPATHY — SKILL COMPLETA v2.0 workflow skill. Use this skill when the user needs Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo and the operator should preserve the upstream workflow, copied support…
A tool that breaks down a reference or original video into its shots, timing, camera work, composition, actions, transitions, captions, sound, and visual elements, then writes reusable prompts.
A research workflow that reuses verified GraphRAG research trails. GraphRAG combines graph-based connections between information with search to investigate questions and produce cited reports.
Register, update, or re-sync data sources for MFS so they become searchable — postgres / mysql / mongo / snowflake / bigquery, github / jira / linear / notion / hubspot / zendesk, slack / discord / gmail / feishu, s3 / gdrive / web / file. Use whenever the user wants to ADD a new data source to MFS, change an existing…
Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.
A skill for writing prompts for Seedance 2.0, a video-generation model. It creates 15-second, single-shot product-animation prompts in Apple, Microsoft, Bauhaus, or Vercel-inspired visual styles, with support for reference images.
Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 model to a new downstream dataset. Supports fine-tuning from a self-trained DPA3 model (.pt checkpoint), from a multi-task pre-trained model, or from a built-in pretrained model downloaded via dp…
Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions KeiRouter, KEIROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant…
Judges whether a user's input suits the Vibe Creating style of video-prompt writing, and when it does, distills single-scene prompts, multi-shot descriptions, emotional imagery, or mixed input into prompts that are easier for a video model to generate from — while preserving any user-specified dialogue, voiceover…
A workflow that turns a local short video into a structured Chinese prompt for AI video-generation tools. It examines the visuals, movement, camera work, and audio rhythm, while avoiding invented details when frames are unclear.
Write prompts, system instructions, agent directives, slash commands, and skill descriptions using two stacked layers — outcome-first (define the destination, success criteria, stopping condition) plus directional language (every sentence names the path with positive verbs). Triggers when writing or reviewing any…
A tool for running Python code in an isolated environment. Python is a programming language often used for calculations, data processing, file-format conversion, and preparing chart data.
Analyze, benchmark, diagnose, and optimize large-model inference deployments from hardware inventory, model details, workload traces, and latency or throughput SLOs. Use when Codex needs to tune SGLang launch parameters, run bounded single-host GPU experiments, plan deployment topology, inspect GPU or CPU profiles…
Advanced image prompt engineering assistant for Chinese-first users. Turns any input into high-quality image-generation prompts: reverse-engineers prompts from images, expands rough prompts into structured prompts, translates/transwrites prompts, extracts reusable variables, suggests phrase banks, supports minimal…
★not rated 141▲
+2 5mo agoA63 tokens
originalMIT
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: