Library
87,169 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
BloomTutor
SkillsOpen-source AI tutor for personalized learning: Socratic, adaptive lessons to learn anything. Claude Code skill + self-hosted web app. Bloom 2 Sigma · 开源 AI 家教
git clone https://github.com/Li-Evan/BloomTutor.git -
Codex-Prompt
PromptsRational engineering system prompt for Codex and LLMs — focused on accuracy, software engineering, AI, security research, bug bounty, and reverse engineering. | 面向 Codex 与 LLM 的理性工程系统提示词:强调准确性、软件工程、AI、网络安全、漏洞研究与逆向工程。
git clone https://github.com/Mai-xiyu/Codex-Prompt.git -
platypus
Agents & frameworksSelf-hosted AI Agents for your whole team — on your infrastructure, your models, around the clock.
git clone https://github.com/willdady/platypus.git -
sno-station
SkillsWhen Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.
git clone https://github.com/sno-ai/sno-station.git -
events-rpocket-tracker
Agents & frameworksTeam calendar & tracker for events, talks and forums. Week and month views, forums with nested sessions, statuses and filters. Assign owners, keep the full communication history for every event. A Telegram bot powered by Claude turns forwarded invites, PDFs and posters into events and answers questions about your schedule.
git clone https://github.com/BalthDreadgrid20608/events-rpocket-tracker.git -
LFM3-1.7B-GGUF
Modelstext generation model by AtomicChat · gguf
AtomicChat/LFM3-1.7B-GGUF -
architecture-copilot
Prompts🧭 给 Claude Code / Cursor / Codex 用的『架构副驾』skill —— 开新项目时用持续深度提问引导你在写代码前想清楚架构(产出架构图 / ADR / 演进路线)。知识源自 awesome-architecture。中英双语。
git clone https://github.com/study8677/architecture-copilot.git -
McD-saver
Agents & frameworks🍟 麦麦省钱助手 —— 麦当劳中国官方 MCP 的省钱点餐 Agent Skill:官方 calculate-price 实时核价 + 券组合优化 + 沉默成本体检与多单用券排程,官方券/套餐/团购券/积分四渠道同口径算终局价。免登录在线试算。
git clone https://github.com/yuxinlaile/McD-saver.git -
prismor
Agents & frameworksSelf-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
git clone https://github.com/PrismorSec/prismor.git -
ApiManagementClient
Public APIsUse these REST APIs for performing operations on Property entity associated with your Azure API Management deployment. API Management policies are a powerful capability of the system that allow the publisher to change the behavior of the API through configuration. Policies are a collection of statements that are executed sequentially on the request or response of an API. Policy statements can be…
-
XTRF Home Portal API
Public APIsXTRF Home Portal API enables you to perform operations on Projects, Quotes, Customers, Vendors etc. as a XTRF Home Portal user. The documentation is generated from OpenAPI specification 3.0 available here The API client/consumer code may be easily generated in 60+ programming languages using an open source code generator available at the time of writing this documentation at…
-
security-threat-model
SkillsRepository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.
$skill-installer <skill-name> -
agent-symphony
Agents & frameworksMulti-Agent AI Task Orchestrator 2026
git clone https://github.com/skerry699/agent-symphony.git -
d1-omni-600M-GGUF
Modelsimage text to text model by LiquidAI · gguf
LiquidAI/d1-omni-600M-GGUF -
Ornn
SkillsYour all-in-one skills-as-a-service platform to manage your skills, auto-generate skills and use agent skills as simple as calling an API.
git clone https://github.com/ChronoAIProject/Ornn.git -
Ornith-1.5-122B-NVFP4
Modelstext generation model by ornith-ai · transformers
ornith-ai/Ornith-1.5-122B-NVFP4 -
Qwen3.8-27B-Ultimate
Modelsimage text to text model by DavidAU · transformers
DavidAU/Qwen3.8-27B-Ultimate -
awesome-prompt-engineering
PromptsA curated list of resources, tools, papers, and platforms for prompt engineering in large language models (LLMs) and generative AI.
git clone https://github.com/brandonhimpfen/awesome-prompt-engineering.git -
Socratic
Agents & frameworksSocratic is a framework for building reliable vertical AI agents by letting human experts teach agents interactively, turning tacit domain knowledge into a continuously improving knowledge base.
git clone https://github.com/kevins981/Socratic.git -
Atlas-MultiAsset-Advisor
Agents & frameworksAtlas - a DeepSeek-driven multi-asset investment advisor agent: risk profiling, strategy allocation, factor self-evolution, macro/geopolitics fusion, family-office global basing.
git clone https://github.com/Bruce848647703/Atlas-MultiAsset-Advisor.git -
text generation model by apetersson · mlx
apetersson/DeepSeek-V4.1-Flash-1017-Abliterated-MLX -
mcp-ssh-manager
MCP serversMCP server for SSH: let Claude Code, Codex and any MCP client run commands, transfer files and manage servers over SSH, with human approval, an encrypted vault and a live audit trail. Desktop app and CLI included.
git clone https://github.com/bvisible/mcp-ssh-manager.git -
ultraprompt
SkillsFrontier model solution tracing, then made the prompting skills
git clone https://github.com/rlaope/ultraprompt.git -
fastagent
Agents & frameworksVibe first. Then FastAgent — turn a local agent directory into a live service: in your app, on GitHub, in Telegram, or any channel.
git clone https://github.com/fastagent-sh/fastagent.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.