Library
88,222 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
-
finephrase
Datasets & benchmarksHugging Face dataset by HuggingFaceFW
Source for finephrase (opens huggingface.co) HuggingFaceFW/finephrase -
GLM-5.1-Reasoning-1M-Cleaned
Datasets & benchmarksHugging Face dataset by Jackrong
Source for GLM-5.1-Reasoning-1M-Cleaned (opens huggingface.co) Jackrong/GLM-5.1-Reasoning-1M-Cleaned -
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
Source for Qwen: Qwen3 VL 30B A3B Instruct (opens openrouter.ai) qwen/qwen3-vl-30b-a3b-instruct -
Summarize and export all important points, instructions, and contextual information exchanged in this chat, structured per your requirements. - Use section headers for each major category (e.g., Task Instructions…
-
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
Source for Qwen: Qwen3 235B A22B Instruct 2507 (opens openrouter.ai) qwen/qwen3-235b-a22b-2507 -
skillcheck
PromptsBlind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.
Source for skillcheck (opens github.com) git clone https://github.com/sx4im/skillcheck.git -
artemis
Agents & frameworksARTEMIS turns natural-language instructions into reliable Android automation. It automates end-to-end workflows, captures logs, and integrates seamlessly with AI coding assistants such as Antigravity, Codex, and Claude Code. It also achieves 99%+ success rate on AndroidWorld Benchmark.
Source for artemis (opens github.com) git clone https://github.com/google/artemis.git -
Meta: Llama 3.3 70B Instruct
ModelsThe Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Source for Meta: Llama 3.3 70B Instruct (opens openrouter.ai) meta-llama/llama-3.3-70b-instruct -
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Source for Qwen: Qwen3 Next 80B A3B Instruct (opens openrouter.ai) qwen/qwen3-next-80b-a3b-instruct -
python-codes-25k
Datasets & benchmarksHugging Face dataset by flytech
Source for python-codes-25k (opens huggingface.co) flytech/python-codes-25k -
Act as a sports instructor resembling Cristiano Ronaldo. You are tasked with creating an instructional video for students about how muscles work. The video should cover the following sections: 1. **What are Muscles?**…
-
Instrukt
Tools & appsIntegrated AI environment in the terminal. Build, test and instruct agents.
Source for Instrukt (opens github.com) git clone https://github.com/blob42/Instrukt.git -
agent-toolkit
SkillsA curated collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities across development, documentation, planning, and professional workflows.
Source for agent-toolkit (opens github.com) git clone https://github.com/softaworks/agent-toolkit.git -
SABARUDIN INSTRUCTIONS FRAMEWORK
PromptsCORE: EXECUTIVE SYSTEM PROMPT & CUSTOM INSTRUCTION SYSTEM PERSONA & IDENTITY You are an integrated cognitive, strategic, and neural architecture functioning as a high-level executive advisor. Your core identity is…
-
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Source for Qwen: Qwen3 VL 235B A22B Instruct (opens openrouter.ai) qwen/qwen3-vl-235b-a22b-instruct -
OmniLottie
AI repositories[CVPR 2026🔥] 🧑🎨 OmniLottie, an open-sourced multi-modal instructed vector animation generator that produces Lottie JSONs.
Source for OmniLottie (opens github.com) git clone https://github.com/OpenVGLab/OmniLottie.git -
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
Source for Qwen: Qwen3 30B A3B Instruct 2507 (opens openrouter.ai) qwen/qwen3-30b-a3b-instruct-2507 -
Hy4-flash-FP8
Modelsimage text to text model by tencent · transformers
Source for Hy4-flash-FP8 (opens huggingface.co) tencent/Hy4-flash-FP8 -
rosetta
Tools & appsAn instruction layer for AI coding agent
Source for rosetta (opens github.com) git clone https://github.com/griddynamics/rosetta.git -
image text to text model by DavidAU
Source for Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF (opens huggingface.co) DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF -
gpt-with-taste
PromptsBetter judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.
Source for gpt-with-taste (opens github.com) git clone https://github.com/NB-Corp/gpt-with-taste.git -
vn-law-check
SkillsAudit pháp lý website theo luật Việt Nam (BVDLCN 91/2025, TMĐT 122/2025, ANM 116/2025, AI 134/2025) cho Claude Code, Cursor, Copilot, Windsurf, Cline
Source for vn-law-check (opens github.com) git clone https://github.com/mhfed/vn-law-check.git -
Instructor in a School
PromptsI want you to act as an instructor in a school, teaching algorithms to beginners. You will provide code examples using python programming language. First, start briefly explaining what an algorithm is, and continue…
-
Meta: Llama 3.1 70B Instruct
ModelsMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...
Source for Meta: Llama 3.1 70B Instruct (opens openrouter.ai) meta-llama/llama-3.1-70b-instruct
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.