Google · install guide
Gemini CLI skills. Where they live and how to install them.
Where Gemini CLI loads skills
- In a project
.gemini/skills/.agents/skills/- For all projects
~/.gemini/skills/~/.agents/skills/- Docs
- geminicli.com
- Website
- geminicli.com
- Precedence, lowest to highest: built-in, extension, user (~/.gemini/skills or ~/.agents/skills), workspace (.gemini/skills or .agents/skills). Within a tier, .agents/skills wins.
- Workspace skills only load when the folder is trusted (run /trust and restart if needed); user-scope skills are not affected.
- SKILL.md is found at the skills root or one folder deep; deeper nesting is not discovered. The skill name comes from the name field, not the folder.
- When a task matches, Gemini calls activate_skill and shows a consent prompt with the skill's name and directory before loading it.
- In a session: /skills list [all], /skills reload, /skills enable|disable <name>, /skills link <path>. From the shell: gemini skills list|install|uninstall.
- Gemini CLI's site carries a notice that unpaid-tier and Google One users were moved from Gemini CLI to Antigravity CLI on June 18, 2026. Check which account type applies to you.
How to install a skill
gemini skills install https://github.com/{owner}/{repo}.git --path {path}--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
gemini skills install https://github.com/anthropics/skills.git --path skills/mcp-builderExample with MCP Server Builder.
npx skills add {owner}/{repo} --skill {skill} -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
npx skills add anthropics/skills --skill mcp-builder -a gemini-cliExample with MCP Server Builder.
gh skill install {owner}/{repo} {skill} --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
gh skill install anthropics/skills mcp-builder --agent gemini-cliExample with MCP Server Builder.
git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/{path} .gemini/skills/{skill} && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
git clone --depth 1 https://github.com/anthropics/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mcp-builder .gemini/skills/mcp-builder && rm -rf skills-srcExample with MCP Server Builder.
Guide
How to install agent skills in Gemini CLI
What skills are in Gemini CLI
Gemini CLI describes Agent Skills as on-demand expertise, as opposed to GEMINI.md, which gives persistent background context. At the start of a session the CLI scans its skill locations and puts the name and description of every enabled skill into the system prompt. When a task matches a description, Gemini calls an activate_skill tool. You then see a confirmation prompt naming the skill and the directory it will be able to read, and only after you approve does the full SKILL.md and the skill's folder get added to the conversation.
A skill is a directory containing SKILL.md with name and description frontmatter, and optionally scripts/, references/ and assets/.
Where Gemini CLI looks for skills
Locations are listed from lowest to highest precedence:
- Built-in skills
- Extension skills, bundled inside installed extensions
- User skills:
~/.gemini/skills/or the alias~/.agents/skills/ - Workspace skills:
.gemini/skills/or the alias.agents/skills/
When two skills share a name, the higher tier wins, and within a tier the .agents/skills/ folder beats .gemini/skills/. Workspace skills only load when the folder is marked as trusted. SKILL.md must be at the root of a skills folder or one directory below it; deeper nesting is not discovered.
Install a skill
The examples use frontend-design from anthropics/skills, located at skills/frontend-design.
Option 1: gemini skills install
gemini skills install https://github.com/anthropics/skills.git --path skills/frontend-design
--path names the sub-directory of the repository that holds the skill. The default scope is user; add --scope workspace to install into the current project. The CLI asks you to confirm the security risks first, and --consent skips that prompt, so use it only for sources you have already reviewed. The command also accepts a local directory.
Option 2: the skills CLI
npx skills add anthropics/skills --skill frontend-design -a gemini-cli
This installs into .agents/skills/ in the current project. Add -g for ~/.gemini/skills/.
Option 3: GitHub CLI
gh skill install anthropics/skills frontend-design --agent gemini-cli
gh skill install anthropics/skills frontend-design --agent gemini-cli --scope user
Needs GitHub CLI 2.90.0 or later, where gh skill is a public preview.
Option 4: copy the folder
git clone --depth 1 https://github.com/anthropics/skills.git skills-src
mkdir -p .gemini/skills
cp -r skills-src/skills/frontend-design .gemini/skills/frontend-design
rm -rf skills-src
Use ~/.gemini/skills/ for a personal install. If Gemini CLI is already running, refresh with /skills reload.
Check that it loaded
Inside a session, run /skills list. Add all to include built-in skills, or nodesc to hide the descriptions. From the shell, gemini skills list --all prints the same information. If you just added files, /skills reload (or /skills refresh) rescans every tier without restarting. Then ask a question that matches the skill's description and watch for the consent prompt.
Update and remove
- Remove:
gemini skills uninstall frontend-design --scope workspace(use--scope userfor a user-level install). - Disable without deleting:
/skills disable frontend-design, and/skills enable frontend-designto turn it back on. These default to user scope; add--scope workspacefor project settings. - Update: the documentation lists install, uninstall and link but no separate update command, so uninstall the skill and install it again to get a newer version. If you use
npx skillsorgh skill, their ownupdatecommands apply to the skills they installed. - Local development:
/skills link <path>links a skill folder you are editing.
Troubleshooting
- A workspace skill does not show up: the folder may not be trusted. Run
/trustand restart the session. User-level skills are not affected by trust. - A skill is silently skipped: it needs both
name:anddescription:, the file must be named exactlySKILL.md, and the opening---must be the first thing in the file with no heading or blank line before it. - The skill appears under a different name: Gemini takes the name from the
name:field, not from the folder name. - It was nested too deep: only the skills root and one folder below it are scanned.
- Account notice: Gemini CLI's site carries a banner saying unpaid-tier and Google One users were moved from Gemini CLI to Antigravity CLI on June 18, 2026. Check that notice for your account type before you set things up.
Safety
Activating a skill gives Gemini access to the skill's whole directory, and bundled scripts run through the shell tool with your permissions. Read SKILL.md and scripts/ before you approve installation or activation. The consent prompts exist for this reason, so read them rather than reflexively approving, and avoid --consent for repositories you have not reviewed.
Top skills to try in Gemini CLI
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation. | anthropics/ | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 2 | Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR. | anthropics/ | 180k | 48 repos | ~2k | Automated safety check: Pass | Proprietary | 2 days ago |
| 3 | Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file. | anthropics/ | 180k | 40 repos | ~769 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 4 | Builds animated HTML slide decks that run in the browser with no dependencies, or converts PowerPoint files to the web, starting from visual style previews. | zarazhangrui/ | 30k | 16 repos | ~7k | Automated safety check: Pass | MIT | 3 mo ago |
| 5 | Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code. | shareAI-lab/ | 78k | 6 repos | ~1.2k | Automated safety check: Pass | MIT | 9 days ago |
| 6 | Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources. | PleasePrompto/ | 7.8k | 13 repos | ~2.4k | Automated safety check: Notes | MIT | 27 days ago |
| 7 | Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it. | makeplane/ | 60k | 12 repos | ~657 | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 8 | Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree. | obra/ | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | today |
| 9 | Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart. | anthropics/ | 37k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | today |
| 10 | Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories. | browser-use/ | 28k | 6 repos | ~3k | Automated safety check: Pass | MIT | 4 days ago |
| 11 | Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions. | addyosmani/ | 102k | 6 repos | ~2k | Automated safety check: Pass | MIT | 3 days ago |
| 12 | Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking… | vercel-labs/ | 44k | 24 repos | ~864 | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. | rolling-scopes/ | 10k | 24 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | 3 days ago |
| 14 | A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions | farm-fe/ | 5.6k | 34 repos | ~1.4k | Automated safety check: Pass | MIT | 15 days ago |
| 15 | Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review. | obra/ | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | today |
| 16 | Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue. | vercel-labs/ | 44k | 8 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters. | anthropics/ | 180k | 37 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 18 | Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. | spacering-net/ | 3.8k | 15 repos | ~3.6k | Automated safety check: Pass | MIT | today |
| 19 | 19.Matplotlib Low-level plotting library for full customization. An agent skill from zLanqing/codex-claude-academic-skills. | zLanqing/ | 4.6k | 17 repos | ~2.9k | Automated safety check: Pass | MIT | 4 mo ago |
| 20 | A skill your agent uses whenever the user mentions Horizon by name in a Laravel context. | coollabsio/ | 63k | 4 repos | ~898 | Automated safety check: Pass | MIT | today |
| 21 | Gives the agent Postgres rules to consult before writing or changing tables, queries, indexes, RLS policies or migrations, and when diagnosing slow queries. | supabase/ | 2.7k | 24 repos | ~808 | Automated safety check: Pass | MIT | 5 days ago |
| 22 | Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way. | openinterpreter/ | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | today |
| 23 | Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design. | anthropics/ | 37k | 8 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | today |
| 24 | Create new skills, modify and improve existing skills, and measure skill performance. | Azure/ | 794 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
Where does Gemini CLI look for skills?
Gemini CLI loads skill folders (each with a SKILL.md file) inside a project from .gemini/skills/ and .agents/skills/ and for every project from ~/.gemini/skills/ and ~/.agents/skills/.
How do I install a skill in Gemini CLI?
gemini skills install: gemini skills install https://github.com/{owner}/{repo}.git --path {path}. skills CLI: npx skills add {owner}/{repo} --skill {skill} -a gemini-cli. GitHub CLI: gh skill install {owner}/{repo} {skill} --agent gemini-cli. Manual copy: git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/{path} .gemini/skills/{skill} && rm -rf skills-src. Replace the placeholders with the skill's GitHub owner, repository and name; every skill page here shows the filled-in command.
What are the best skills for Gemini CLI?
Agent skills are portable SKILL.md folders, so the catalogue's top skills work in Gemini CLI too. The highest-ranked right now are MCP Server Builder (anthropics/skills), PDF Processing (anthropics/skills) and Web Artifacts Builder (anthropics/skills).
Sources
- https://geminicli.com/docs/cli/skills/
- https://geminicli.com/docs/cli/tutorials/skills-getting-started/
- https://geminicli.com/docs/cli/creating-skills/
- https://github.com/vercel-labs/skills
- https://cli.github.com/manual/gh_skill_install
Checked October 7, 2026