If you are evaluating Gemini CLI skills on GitHub, this repository is a strong broad starting point: installable skills, large coverage, and clear onboarding for day-one use.
Agentic Awesome Skills supports Gemini CLI through the .gemini/skills/ path and combines general engineering playbooks with specialized skills for AI systems, integrations, infrastructure, testing, product, and growth.
Install into the Gemini skills path, then ask Gemini to apply one skill at a time to a specific task. This works best when you keep the active set small and choose a clear workflow-oriented skill for the job in front of you.
- It installs directly into the expected Gemini skills path.
- It includes both core software engineering skills and deeper agent/LLM-oriented skills.
- It helps new users get started with bundles and workflows rather than forcing a cold start from 2,001+ files.
- It is useful whether you want a broad internal skill library or a single repo to test many workflows quickly.
npx agentic-awesome-skills --geminitest -d .gemini/skills || test -d ~/.gemini/skillsbrainstorming: turn vague goals into clearer implementation specs.prompt-engineering: improve prompting quality and task framing.rag-engineer: build and evaluate retrieval systems.langgraph: design stateful agent workflows.mcp-builder: add tool integrations and external capabilities.
Use @prompt-engineering to improve this system prompt for a coding assistant.
Use @langgraph to design a stateful agent workflow for support triage.
Use @mcp-builder to plan the tools needed for a GitHub + Slack integration.
- Start with
bundles.mdif you want a smaller curated subset by role. - Read
ai-agent-skills.mdif you are comparing general-purpose agent skill libraries. - Use
usage.mdif you want more examples of how to invoke skills in real prompts.