Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
imp
Agents & frameworksRun large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.
git clone https://github.com/kekzl/imp.git -
reelforge
SkillsTurn one raw talking-head take into a captioned 9:16 reel locally: faster-whisper transcribes, ffmpeg crops, burns word-synced captions and a hook card. Free, no watermark. Claude Code command included.
git clone https://github.com/waseemnasir2k26/reelforge.git -
GitHub Expert
PromptsI want you to act as a git and GitHub expert. I will provide you with an individual looking for guidance and advice on managing their git repository. they will ask questions related to GitHub codes and commands to…
-
postmortem
Promptscreate a new markdown file that as a postmortem/analysis original message, what happened, how it happened, the chronological steps that you took to fix the problem. The commands that you used, what you did in the end…
-
Nebutra-Sailor
SkillsSkip to production. The open-source (Apache-2.0) production layer for agent-built software — auth, global + China billing, multi-tenancy and an AI gateway in one command, running locally with zero keys.
git clone https://github.com/Nebutra/Nebutra-Sailor.git -
JavaScript Console
PromptsI want you to act as a javascript console. I will type commands and you will reply with what the javascript console should show. I want you to only reply with the terminal output inside one unique code block, and…
-
givememod
SkillsClaude Code mods on demand — a skill that reads your conversation and builds the mod that fits: plan progress bar, files pane, context gauge, risky-command guard, test watcher. 11 tested templates, 29 building blocks, a map of 3,057 public mods. Terminal and desktop.
git clone https://github.com/timoncool/givememod.git -
suxiaoqiang-cli
Skillssxq is the official command-line tool for Superun, the vibe coding platform. It syncs your Superun project files to your local machine so you can edit them with your favorite editor or AI coding agent, then push changes back, trigger a preview build, and release to production.
git clone https://github.com/AiGuangInc/suxiaoqiang-cli.git -
AI Trying to Escape the Box
Prompts[Caveat Emptor: After issuing this prompt you should then do something like start a docker container with `docker run -it ubuntu:latest /bin/bash` and type the commands the AI gives you in, and paste the output back…
-
DAX Terminal
PromptsI want you to act as a DAX terminal for Microsoft's analytical services. I will give you commands for different concepts involving the use of DAX for data analytics. I want you to reply with a DAX code examples of…
-
agentshield
MCP servers🛡️ Offline Rust security scanner for AI agent tools & MCP servers — MCP, Hermes Agent, CrewAI, LangChain/LangGraph, GPT Actions, Cursor Rules. Catches command injection, credential exfiltration, SSRF & unsafe file access; a typical MCP server scans in <50 ms. CLI, GitHub Action, VS Code, SARIF.
git clone https://github.com/aiconnai/agentshield.git -
quick-question
SkillsThe control plane for game-dev agents — close the loop with verified compile, test, and cross-model review across Unity, Godot, Unreal, and S&box. Lifecycle-aware /qq:go routing, 26 /qq:* slash commands. Claude Code-first, agent-agnostic via HTTP and MCP.
git clone https://github.com/tykisgod/quick-question.git -
skills
Skills43 Claude Code skills for making content that doesn't read like a machine made it — prose editing with an offline linter, prompt engineering for 40+ image/video/music models with optional one-command execution, and orchestrators from research to a published carousel, reel or proposal. Russian-first, English throughout.
git clone https://github.com/Mikefluff/skills.git -
Linux Terminal
PromptsI want you to act as a linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. do…
-
prompt-optimizer
SkillsClaude Code / Agent Skill: /prompt-optimizer polishes your existing AI prompts — fixes wording, grammar and structure without adding scope, changing constraints or touching commands, paths and code. 提示词优化技能:只改表达,不改语义。Works with Claude Code, Codex and any chat AI.
git clone https://github.com/talki-io/prompt-optimizer.git -
git-guardrails-claude-code
SkillsSet up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
-
synapti-marketplace
SkillsThe Synapti Marketplace is a curated collection of Claude Code plugins designed for AI-augmented development + advanced analytical and research tasks. Each plugin provides specialized agents, skills, and commands that extend Claude Code's capabilities in specific domains.
git clone https://github.com/synaptiai/synapti-marketplace.git -
OpenAI: GPT-5.6 Sol
ModelsGPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
openai/gpt-5.6-sol -
Text Based Adventure Game
PromptsI want you to act as a text based adventure game. I will type commands and you will reply with a description of what the character sees. I want you to only reply with the game output inside one unique code block, and…
-
R Programming Interpreter
PromptsI want you to act as a R interpreter. I'll type commands and you'll reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not…
-
Ask me for the name of the software as your next question. - You are an IT expert technican. I want you to research, verify and then write powershell commands to silently install or update the software on a Windows…
-
garmin-personal-mcp
MCP serversMCP server for the official Garmin Connect Personal API. Ask Claude, Codex or any stdio MCP client about your runs, strength sets, sleep, HRV etc. Read-only, runs with one command. A training dashboard in under a minute, as a page file or inside the chat. The server writes the page: about 100× fewer output tokens.
git clone https://github.com/indaco/garmin-personal-mcp.git -
OpenAI: GPT-5.6 Sol (batch)
ModelsGPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
openai/gpt-5.6-sol:batch -
skill-olympus
SkillsTwelve Greek gods. One command. A working SaaS. 98 skills + 49 agents + 13 hooks for Claude Code + Codex CLI + Gemini CLI. Cross-CLI persistent memory, zero-interaction full pipeline (design → build → inspect → test → ship).
git clone https://github.com/Dannykkh/skill-olympus.git
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.