Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Best Gemini CLI skills
Google’s Gemini CLI supports Agent Skills in the shared SKILL.md format. It discovers skills from your home directory and workspace, uses each skill’s description to decide when to activate it, and grants the agent access to the skill’s bundled scripts and references once it does.
The skills below either name Gemini CLI in their SKILL.md or were tagged for it by their authors. Most skills written for other agents also load in Gemini CLI once placed in a skills folder it reads.
How to install Gemini CLI skills
~/.gemini/skills/<skill-name>/SKILL.md.gemini/skills/<skill-name>/SKILL.md- Copy the skill folder into ~/.gemini/skills/ for all projects, or .gemini/skills/ in your workspace. The ~/.agents/skills and .agents/skills aliases also work.
- Run /skills list in a Gemini CLI session (or gemini skills from your shell) to confirm it was discovered.
- When a skill activates, Gemini CLI adds its instructions to the conversation and lets the agent read files bundled with it.
Source: Google’s official documentation ↗. Each skill page shows the exact install command from its repository.
Popular Gemini CLI skills
Ranked by quality and GitHub popularity.
Extract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing /understand knowledge graph.
Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.
Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships
🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen & 20+ CLIs via BYOK.
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
Runs Gemini CLI headlessly for repository analysis and coding tasks. Use when the user asks to delegate work to Gemini CLI or compare its result with another coding agent.
Arquitecto de Soluciones Principal y Consultor Tecnológico de Andru.ia. Diagnostica y traza la hoja de ruta óptima para proyectos de IA en español.
Trending Gemini CLI skills
Gaining the most GitHub stars since we started tracking them.
Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks
Use when you need a deep-dive explanation of a specific file, function, or module in the codebase
Use when you need to ask questions about a codebase or understand code using a knowledge graph
Use when you need to generate an onboarding guide for new team members joining a project
Launch the interactive web dashboard to visualize a codebase's knowledge graph
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
New Gemini CLI skills
Instrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging.
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.
Conduct periodic access reviews and certifications. Implement access governance and recertification workflows. Use when managing access compliance.
PPT 视觉增强工具,支持多种风格渲染、交互式播放器生成和视频合成。可与 ppt-generator Skill 协同工作,实现从内容规划到视觉呈现的完整流程。
模拟多个AI智能体协作开会并进行决策讨论的场景。适用于需要从多个专业角度分析问题、进行辩论和达成共识的场景,如项目决策、技术方案评审、商业策略制定等。
提供基于 FFmpeg 和 ImageMagick 的多媒体处理能力,支持视频和图像的格式转换、分辨率调整、压缩等操作
Gemini CLI skills by category
Guides
Custom skills
Need a Gemini CLI skill for your own workflow?
Tell us what you want your AI agent to do. We’ll help turn your workflow, standards or internal tools into a production-ready skill for Claude Code, Codex, Cursor or Gemini.
Frequently asked questions
- Where are Gemini CLI skills stored?
- User skills live in ~/.gemini/skills/ (or ~/.agents/skills/). Workspace skills live in .gemini/skills/ (or .agents/skills/) in the current project.
- How do I see which skills Gemini CLI has loaded?
- Use the /skills list command in an interactive session, or the gemini skills command from your terminal.
- How many Gemini CLI skills are there?
- AISkillsify lists 270 skills with evidence of Gemini CLI support: the skill’s SKILL.md names Gemini CLI or the author tagged the repository for it. The count is refreshed weekly from GitHub.