Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
coding-agent-audit
MCP serversAudits Claude Code/Cursor MCP configs for supply-chain backdoors and risky permissions.
coding-agent-audit@0.11.0 -
Meilleur Code Parrainage
MCP serversCodes de parrainage vérifiés en France : bonus filleul et parrain, conditions, fiche source.
-
living-docs-skill
SkillsLiving Docs — a AI agent skill that runs your project's documentation as a living system: constitution, ADRs, BDRs, PRDs, issues, research notes & Mermaid architecture diagrams under five no-drift governance invariants. OKF-formatted, stack-agnostic. Works with Claude Code, Cursor, Copilot, OpenCode & Pi.
git clone https://github.com/ejklock/living-docs-skill.git -
asciify-engine
SkillsASCII for the web: 31 GPU-drawn interface components, backgrounds, and image, GIF and video conversion.
git clone https://github.com/ayangabryl/asciify-engine.git -
text generation model by lyber-ai · transformers
lyber-ai/Kimi-K3.1-Pro-UNCENSORED-MXFP4 -
EnterpriseAgentFramework
Agents & frameworksReachAI企业级智能体开发平台:快速、安全完成已有业务系统智能化改造,让 AI 在 OA、ERP、CRM 等原系统中查数据、填表单、办业务。ReachAI: Quickly and securely bring AI to existing enterprise systems, enabling AI to query data, fill out forms, and execute business tasks directly within OA, ERP, CRM, and other business applications.
git clone https://github.com/w8123/EnterpriseAgentFramework.git -
commands
Agents & frameworksArchived. The original Claude Code slash commands, replaced by the plugin marketplace at wshobson/agents.
git clone https://github.com/wshobson/commands.git -
reposwarm
Tools & appsOpen-source multi-repo architecture discovery for AI coding agents. Analyze repositories, generate standardized .arch.md files, and keep them in a central results hub for agent context, onboarding and architecture reviews. GitHub, GitLab, CodeCommit, Azure DevOps and Bitbucket. Apache-2.0.
git clone https://github.com/reposwarm/reposwarm.git -
goskill
Tools & apps长任务执行 Skill:先定成功标准再逐轮验收,让 Claude Code/Codex 跑完长任务不半途而废|Goal-driven long-running agent tasks
git clone https://github.com/AIPMAndy/goskill.git -
receiving-code-review
SkillsUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
-
diy-llm
AI repositoriesCovers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer、MoE、分布式训练、缩放定律、推理与对齐,6 项渐进代码作业,掌握 LLM 全栈知识
git clone https://github.com/datawhalechina/diy-llm.git -
frago
Agents & frameworksMulti-runtime automation infrastructure for AI agents. Native CDP browser control, metadata-driven Recipe system, and persistent Run context management.
git clone https://github.com/tsaijamey/frago.git -
You are a senior developer with years of experience in [project's base] Your first task is to scan the code/ project and ask the user clarifying questions about it and if the user would like the changes presented. #…
-
AST Code Analysis Superpower
Prompts--- name: ast-code-analysis-superpower description: AST-based code pattern analysis using ast-grep for security, performance, and structural issues. Use when (1) reviewing code for security vulnerabilities, (2)…
-
gemini-code-context-mcp
MCP serversCodebase Q&A for Claude Code through Gemini's 1M-token window, with workspace scans and caching.
@qmediat.io/gemini-code-context-mcp@1.23.1 -
figma-to-code-mcp
MCP serversLLM-optimized Figma MCP server.
@tmegit/figma-to-code-mcp@0.29.0 -
9routerx
MCP servers9RouterX (9R Next Go Generation): Single-binary Go AI router, LLM gateway & 20-40% token saver. Route Claude Code, Cursor & Codex across 155 providers, 28 OAuth & 248 free models (24 keyless) — OpenAI, Claude, Gemini, DeepSeek, Groq, Ollama & MCP.
git clone https://github.com/yanstd888/9routerx.git -
rbxdev-ls
MCP serversLuau language server and VS Code extension for Roblox, with strict type checking, smart completions, and optional live-game tooling via an executor bridge.
git clone https://github.com/0neShot101/rbxdev-ls.git -
image text to text model by nvidia · transformers
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 -
Ming-3.0-tts-tiny
Modelstext to speech model by inclusionAI · transformers
inclusionAI/Ming-3.0-tts-tiny -
openmymemo
MCP serversYour AI memory as a local folder you own. Claude, Codex, Cursor and any MCP app share it; you see every change and can undo it.
git clone https://github.com/MyMemoAI/openmymemo.git -
SwiftAutoGUI
SkillsA Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
git clone https://github.com/NakaokaRei/SwiftAutoGUI.git -
k-fable-opus-claude-md
Skills프론티어 LLM 성능과 가격에 충격 먹은 사람이 계속 깎아 만드는 Claude,GPT,Gemini, etc LLM 용 md.
git clone https://github.com/habinsong/k-fable-opus-claude-md.git -
orchestra-auto
SkillsAn Orca best practice built around Matt Pocock's engineering skills. His chain stays: grill-with-docs, to-spec, to-tickets, then implement or implement-spec, closing with code-review. Orca supervises each step in its own worktree, with gates and merge. Not affiliated with or endorsed by Matt Pocock.
git clone https://github.com/whutlichao/orchestra-auto.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.