SkillFoxx

Type a name, a task or a service

Awesome LLM Apps

A collection of 100+ AI agent and RAG app templates, including a section of skills for coding agents

SkillMedium risk

shubhamsaboo/awesome-llm-appsAuthor: Shubham Saboo

Install

npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/<skill>

Replace <skill> with the skill folder name, for example project-graveyard.

This is third-party code. Review the repository files before installing.

What it does

The repository is primarily a set of ready LLM app templates: starter and advanced agents, multi-agent teams, voice agents and RAG. Its agent_skills section contains coding-agent skills with scripts and eval tests: project-graveyard finds abandoned projects and explains why they died, scope-creep-detector checks whether a diff grew beyond its intent, commit-archaeologist reconstructs why code exists, dependency-doctor audits a dependency manifest, and first-reader simulates readers of a draft.

Who it is for. Developers looking for agent examples to learn from and small standalone skills for their coding agent.

Good fit when

  • You want to check whether a pull request grew beyond its stated goal
  • You need to understand why a piece of code exists
  • You want a working agent or RAG app template to start from

Not a fit when

  • You need a cohesive skill set for one workflow
  • You are not willing to read skill scripts before installing

Example request

Why do I never finish my side projects

Limitations

The agent_skills section is small; most of the repo is apps that need model API keys. advisor-orchestrator-worker is built around several commercial models. The author advises reading SKILL.md and every script before installing any skill.

How to disable. Remove the skill folder from your agent's skills directory, for example ~/.claude/skills or .agents/skills.

Security check

  • Skills ship executable scripts
  • Apps in the repo require model API keys

README in short

Awesome LLM Apps is an open collection of 100+ AI agents, skills and RAG apps under Apache 2.0. Templates work with Claude, Gemini, GPT, DeepSeek, Llama, Qwen and other models. Skills install with npx skills add pointing at a folder; apps run after cloning and installing requirements. Step-by-step tutorials are published on Unwind AI.

FAQ

Do the skills send data over the network?

According to the README, skills are local by default, declare any network use up front and run nothing at install time.

Editors’ pick

A self-improving agent from Nous Research with a TUI, messaging gateway, cron jobs and skills it writes itself

CLIHigh risk245.5K
Editors’ pick

Anthropic's coding agent for the terminal, IDE and GitHub: understands your codebase, runs tasks and handles git

CLIHigh risk145K
Editors’ pick

OpenAI's coding agent that runs locally in your terminal, with IDE and desktop versions

CLIHigh risk124.1K
Editors’ pick

Google's open-source terminal agent on Gemini models: code work, shell, web search and MCP

CLIHigh risk107K