Agentic AI Foundation (Linux Foundation) · install guide
Goose skills. Where they live and how to install them.
Where Goose loads skills
- In a project
.agents/skills/.goose/skills/.claude/skills/- For all projects
~/.agents/skills/~/.claude/skills/- Docs
- goose-docs.ai
- Website
- goose-docs.ai
- Skills run through the built-in Skills platform extension, which is enabled by default.
- Recommended folders: ~/.agents/skills/ (global) and .agents/skills/ (project). Goose also reads .goose/skills/, .claude/skills/, ~/.claude/skills/ and platform-specific config folders.
- goose skills list shows discovered skills; in the CLI, /skills name1 name2 loads skills by name. You can also just ask Goose to use a skill.
- A built-in web-search skill ships with Goose. Skills from installed plugins are namespaced, for example my-plugin:review.
- Documented frontmatter: name and description (both required).
How to install a skill
npx skills add {owner}/{repo} --skill {skill} -a gooseGoose documents no install command of its own. This writes to .goose/skills/ (or ~/.config/goose/skills/ with -g); Goose lists .goose/skills/ and platform-specific config folders as backward-compatible locations.
npx skills add anthropics/skills --skill mcp-builder -a gooseExample with MCP Server Builder.
gh skill install {owner}/{repo} {skill} --agent gooseProject scope by default; add --scope user for a personal install.
gh skill install anthropics/skills mcp-builder --agent gooseExample with MCP Server Builder.
git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && mkdir -p .agents/skills && cp -r skills-src/{path} .agents/skills/{skill} && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a global install (the location Goose recommends).
git clone --depth 1 https://github.com/anthropics/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mcp-builder .agents/skills/mcp-builder && rm -rf skills-srcExample with MCP Server Builder.
Guide
How to install agent skills in Goose
What skills are in Goose
Goose is an open-source agent that now sits under the Agentic AI Foundation at the Linux Foundation. Its documentation describes skills as reusable sets of instructions and resources that teach Goose how to perform specific tasks, from a simple checklist to a detailed workflow with scripts or templates. Skills run through a built-in Skills platform extension, which is enabled by default.
When a session starts, Goose adds the names and descriptions of the skills it finds to its instructions. It loads a skill's full content when your request clearly matches, or when you ask for it by name, for example "Use the code-review skill to review this PR." Goose says its skills are compatible with Claude Desktop and other agents that support the Agent Skills standard.
Where Goose looks for skills
| Scope | Location |
|---|---|
| Global | ~/.agents/skills/ |
| Project | .agents/skills/ |
| Plugins | ~/.agents/plugins/<plugin-name>/ |
Each skill is a subdirectory with a SKILL.md, for example ~/.agents/skills/code-review/SKILL.md. For backward compatibility Goose also discovers skills in .goose/skills/, .claude/skills/, ~/.claude/skills/ and platform-specific config folders, but it recommends .agents/skills/ as the standard.
Install a skill
Goose's documentation describes creating or placing skill folders, not a command that fetches them from GitHub. The examples use frontend-design from anthropics/skills, located at skills/frontend-design.
Option 1: copy the folder
git clone --depth 1 https://github.com/anthropics/skills.git skills-src
mkdir -p ~/.agents/skills
cp -r skills-src/skills/frontend-design ~/.agents/skills/frontend-design
rm -rf skills-src
Use .agents/skills inside a repository for a project skill instead.
Option 2: the skills CLI
npx skills add anthropics/skills --skill frontend-design -a goose
This writes to .goose/skills/ in the current project, or ~/.config/goose/skills/ with -g. Goose lists .goose/skills/ and platform-specific config folders as backward-compatible locations, so these installs should be picked up. If a skill does not appear, copy it into .agents/skills/ or ~/.agents/skills/ instead.
Option 3: GitHub CLI
gh skill install anthropics/skills frontend-design --agent goose
gh skill install anthropics/skills frontend-design --agent goose --scope user
Needs GitHub CLI 2.90.0 or later, where gh skill is a public preview.
Check that it loaded
Run goose skills list in your shell. In the Goose CLI, the /skills command lists available skills and can load one or more by name:
/skills frontend-design
You can also just ask Goose what skills are available. Skills from installed plugins are namespaced with the plugin name, such as my-plugin:review, so use the full name when loading one explicitly.
Update and remove
- Remove: delete the skill folder, or run
npx skills remove frontend-design. - Update: copy a newer version of the folder over the old one, or use
npx skills updateorgh skill updatefor skills those tools installed. - Goose ships a built-in
web-searchskill that needs no installation. The documentation points to a separatebrowser-use skill installcommand for browser automation; that is for the upstream browser-use skill, not a general installer.
Troubleshooting
- The skill does not list: confirm the folder has a file named
SKILL.mdand that its frontmatter includes bothnameanddescription, which Goose requires. - It was installed by another tool: check which folder the tool wrote to. If it is not one of the locations above, move the skill to
~/.agents/skills/. - A skill from a plugin does not load by its short name: use the namespaced name, for example
my-plugin:review. - Skills are not picked up in a running session: skills are discovered when a session starts, so begin a new session after adding files.
- Goose does not follow the skill: make the description specific about when it applies, or name the skill in your request.
Safety
A skill can include scripts and setup commands that Goose runs with your account's access, using its developer tools to read the supporting files. Review SKILL.md and everything bundled with it before installing anything you did not write, and keep third-party skills in a project folder until you trust them rather than in your global folder where they apply to every session.
Top skills to try in Goose
| # | 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 | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | 3 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 | 3 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 | 41 repos | ~769 | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 4 | React composition patterns that scale. An agent skill from supabase/supabase. | supabase/ | 111k | 59 repos | ~726 | Automated safety check: Pass | MIT | today |
| 5 | 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 |
| 6 | 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 | 10 days ago |
| 7 | Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources. | PleasePrompto/ | 7.8k | 14 repos | ~2.4k | Automated safety check: Notes | MIT | 28 days ago |
| 8 | Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it. | makeplane/ | 61k | 12 repos | ~657 | Automated safety check: Pass | AGPL-3.0 | today |
| 9 | 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 |
| 10 | Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart. | anthropics/ | 38k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | today |
| 11 | 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 | 6 days ago |
| 12 | 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/ | 103k | 6 repos | ~2k | Automated safety check: Pass | MIT | 5 days ago |
| 13 | 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 |
| 14 | 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 | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | 4 days ago |
| 15 | 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 | 35 repos | ~1.4k | Automated safety check: Pass | MIT | 16 days ago |
| 16 | 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 |
| 17 | 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 |
| 18 | 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 | 38 repos | ~4.9k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 19 | 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 | yesterday |
| 20 | 20.Matplotlib Low-level plotting library for full customization. An agent skill from zLanqing/codex-claude-academic-skills. | zLanqing/ | 4.6k | 18 repos | ~2.9k | Automated safety check: Pass | MIT | 4 mo ago |
| 21 | Reformats plain text or Markdown articles with frontmatter, a title, a summary, headings, bold, lists and code blocks, and saves a separate formatted copy. | JimLiu/ | 26k | 7 repos | ~3.5k | Automated safety check: Pass | MIT | 28 days ago |
| 22 | 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 | yesterday |
| 23 | 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 | 6 days ago |
| 24 | 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 | yesterday |
Questions, answered from the data.
Where does Goose look for skills?
Goose loads skill folders (each with a SKILL.md file) inside a project from .agents/skills/, .goose/skills/ and .claude/skills/ and for every project from ~/.agents/skills/ and ~/.claude/skills/.
How do I install a skill in Goose?
skills CLI: npx skills add {owner}/{repo} --skill {skill} -a goose. GitHub CLI: gh skill install {owner}/{repo} {skill} --agent goose. Manual copy: git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && mkdir -p .agents/skills && cp -r skills-src/{path} .agents/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 Goose?
Agent skills are portable SKILL.md folders, so the catalogue's top skills work in Goose too. The highest-ranked right now are MCP Server Builder (anthropics/skills), PDF Processing (anthropics/skills) and Web Artifacts Builder (anthropics/skills).
Sources
- https://goose-docs.ai/docs/guides/context-engineering/using-skills
- https://raw.githubusercontent.com/block/goose/main/documentation/docs/guides/context-engineering/using-skills.md
- https://github.com/vercel-labs/skills
- https://cli.github.com/manual/gh_skill_install
Checked October 7, 2026