Awesome LLM apps skill
Awesome LLM Apps
A collection of over 100 AI agent and RAG app templates, including a section of skills for coding agents
- 143,362 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- Skills contain executable scripts
- Repository applications require model API keys
Install
- Works in
Manual 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.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Skills contain executable scripts
- Repository applications require model API keys
This is third-party code. Review the repository files before installing.
What it does
The repository primarily contains ready-made templates for LLM applications: starter and advanced agents, multi-agent teams, voice agents, RAG. The agent_skills section includes skills for coding agents with scripts and eval tests: project-graveyard finds abandoned projects and analyzes causes, scope-creep-detector checks if a diff exceeds the task scope, commit-archaeologist reconstructs code history, dependency-doctor verifies dependency manifests, first-reader simulates draft readers.
Who it is for. For developers looking for agent examples to study and small individual skills for coding agents.
Good fit when
- You want to check if a pull request has grown beyond its stated goal
- You need to understand why a code fragment appeared in the repository
- You are looking for a working agent or RAG app template to start with
Not a fit when
- You need a coherent, unified set of skills for one process
- You are not ready to read skill scripts before installation
Example request
Why do I never finish my pet projectsLimitations
There are few skills in the agent_skills section; most of the repository consists of applications that require model API keys. The advisor-orchestrator-worker skill is designed to link several commercial models. The author recommends reading SKILL.md and all scripts before installing any skill.
How to disable. Delete the skill folder from the agent's skills directory, for example ~/.claude/skills or .agents/skills.
FAQ
Do skills send data over the network?
According to the README, skills in this section are local by default, any network access is declared in advance, and nothing runs during installation.
Discussion
No questions or reviews yet.
Related
SkillsA multi-agent harness that verifies results by artifacts: stop hooks, an independent judge and an event log for Claude Code, Codex, Cursor and more
AI Builder Club Skills
AI Builder Club — Skills
A Claude Code plugin marketplace to make a repo agent-ready and run compounding agent loops
AI Research Skills
AI Research Skills Library
98 skills for ML research, from ideation and model training to inference, evaluation and paper writing
A CLI to run several coding agents: one config, a session console, local memory and a set of engineering skills
A set of CLI tools and a skill that give a text-only agent sight: image analysis, long-screenshot OCR and UI restoration
A LangWatch command-line tool that creates the scaffold of a new AI agent project and hands it to a coding assistant
README in short
Awesome LLM Apps is an open collection of over 100 AI agents, skills, and RAG applications under the Apache 2.0 license. Templates work with Claude, Gemini, GPT, DeepSeek, Llama, Qwen, and other models. Skills are installed via npx skills add using a folder link; applications run after cloning and installing dependencies. Step-by-step guides are available on Unwind AI.