JetBrains · install guide
Junie skills. Where they live and how to install them.
Where Junie loads skills
- In a project
.junie/skills/.agents/skills/- For all projects
~/.junie/skills/~/.agents/skills/- Docs
- junie.jetbrains.com
- Website
- junie.jetbrains.com
- Skills work in Junie CLI and in Junie inside JetBrains IDEs; the folder rules documented are for Junie CLI.
- Junie CLI loads .junie/skills/ and ~/.junie/skills/, plus .agents/skills/ (project folders only when trusted) and ~/.agents/skills/, extension skills, custom folders and built-in skills.
- If it finds .cursor/skills, .claude/skills or .codex/skills in a project, Junie CLI offers to import them into .junie/skills/.
- Only name is required; if description is missing Junie uses the first paragraph of the body, and the skill fails to load if the body is empty.
- Invoke with /<skill-name> or $<skill-name>; /skills opens a screen to enable or disable skills and lists errors.
- Custom folders can be added with --skill-location or the skill-locations field in config.json; --skill-default-locations false turns the default folders off.
- Junie is included with a JetBrains AI subscription.
How to install a skill
npx skills add {owner}/{repo} --skill {skill} -a junieJunie documents no install command of its own. Project install goes to .junie/skills/; add -g for ~/.junie/skills/.
npx skills add anthropics/skills --skill mcp-builder -a junieExample with MCP Server Builder.
gh skill install {owner}/{repo} {skill} --agent junieProject scope by default; add --scope user for a personal install.
gh skill install anthropics/skills mcp-builder --agent junieExample with MCP Server Builder.
git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && mkdir -p .junie/skills && cp -r skills-src/{path} .junie/skills/{skill} && rm -rf skills-srcJetBrains' own docs show this clone-and-copy flow. Use ~/.junie/skills/ for a personal install.
git clone --depth 1 https://github.com/anthropics/skills.git skills-src && mkdir -p .junie/skills && cp -r skills-src/skills/mcp-builder .junie/skills/mcp-builder && rm -rf skills-srcExample with MCP Server Builder.
Guide
How to install agent skills in Junie
What skills are in Junie
JetBrains describes agent skills as folders with instructions, templates, scripts and reference material that give Junie task-specific context. They follow the open Agent Skills format. Unlike guidelines, which apply to every prompt, a skill is only used when it matches the task at hand. Junie follows the instructions and loads referenced materials or runs bundled scripts as needed.
JetBrains says skills work in both Junie CLI and Junie in JetBrains IDEs, and that Junie is included with a JetBrains AI subscription. The folder rules and commands below are the ones JetBrains documents for Junie CLI.
Where Junie looks for skills
By default Junie CLI loads two locations:
- Project scope:
<projectRoot>/.junie/skills/<skill-name>/, which you can commit and share with your team. - User scope:
~/.junie/skills/<skill-name>/on macOS and Linux, or%USERPROFILE%\.junie\skills\<skill-name>\on Windows.
It also loads .agents/skills/ in a trusted project and ~/.agents/skills/, skills bundled with installed extensions, built-in skills, and any folders you add with the --skill-location option or the skill-locations field in config.json. Turn the default folders off with --skill-default-locations false. If you have skill folders from other agents in a project (.cursor/skills/, .claude/skills/ or .codex/skills/), Junie CLI detects them and offers to import them into .junie/skills/. When a project skill and a user skill share a name, the project-level one takes precedence.
Install a skill
JetBrains' own instructions for third-party skills are to copy them from a Git repository into your skills folder. 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 .junie/skills
cp -r skills-src/skills/frontend-design .junie/skills/frontend-design
rm -rf skills-src
Copy into ~/.junie/skills/ for a skill that applies to all your projects. On Windows PowerShell, use git clone and Copy-Item -Recurse -Force, as JetBrains' page shows.
Option 2: the skills CLI
npx skills add anthropics/skills --skill frontend-design -a junie
This installs into .junie/skills/ in the project. Add -g for ~/.junie/skills/.
Option 3: GitHub CLI
gh skill install anthropics/skills frontend-design --agent junie
gh skill install anthropics/skills frontend-design --agent junie --scope user
Needs GitHub CLI 2.90.0 or later, where gh skill is a public preview.
Option 4: ask Junie to write one
JetBrains' simplest route is to describe the skill you want in a prompt, and Junie generates the folder, SKILL.md and supporting files. That creates a new skill rather than installing an existing one.
Check that it loaded
Run /skills in Junie CLI. In the interactive terminal UI it opens a management screen where you can search skills and press Enter or Space to enable or disable one. In ACP clients, /skills re-scans the folders and prints Enabled, Disabled and Errors groups, with the reason for any skill that failed to load. Every enabled skill also becomes a /<skill-name> command, and typing $ in a prompt suggests matching skills.
Update and remove
- Remove: delete the skill's folder, or run
npx skills remove frontend-design. - Update: copy over a newer version of the folder, or use
npx skills updateorgh skill updatefor skills those tools installed. - Turn off without deleting: use
/skills. In ACP clients,/skills frontend-design disablepersists across sessions, and/skills frontend-design enablereverses it.
Troubleshooting
- Junie does not use the skill: the description may be too vague for the task. Try asking for it explicitly, for example "Use the frontend-design skill to ...", or run
/frontend-design. - A skill folder is not recognised: it needs a file named
SKILL.md. Frontmatter must start with---, use spaces rather than tabs, includename, and end with---. - A skill fails to load:
descriptionis optional, but if it is missing and the body is empty or only headings, the skill fails. Give it an explicit description. - Name conflicts: JetBrains' page says the project-level skill wins over a user-level one with the same name, so rename one if you want both.
- File errors: check permissions and that the files are UTF-8.
Safety
JetBrains warns that Junie modifies your code and executes scripts, so you should treat third-party skills like any third-party code. Only use skills from sources you trust, read SKILL.md and all supporting files, and prefer pinning to a specific commit or tag rather than pulling from a branch that may change.
Top skills to try in Junie
| # | 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 Junie look for skills?
Junie loads skill folders (each with a SKILL.md file) inside a project from .junie/skills/ and .agents/skills/ and for every project from ~/.junie/skills/ and ~/.agents/skills/.
How do I install a skill in Junie?
skills CLI: npx skills add {owner}/{repo} --skill {skill} -a junie. GitHub CLI: gh skill install {owner}/{repo} {skill} --agent junie. Manual copy: git clone --depth 1 https://github.com/{owner}/{repo}.git skills-src && mkdir -p .junie/skills && cp -r skills-src/{path} .junie/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 Junie?
Agent skills are portable SKILL.md folders, so the catalogue's top skills work in Junie too. The highest-ranked right now are MCP Server Builder (anthropics/skills), PDF Processing (anthropics/skills) and Web Artifacts Builder (anthropics/skills).
Sources
- https://junie.jetbrains.com/docs/agent-skills.html
- https://github.com/vercel-labs/skills
- https://cli.github.com/manual/gh_skill_install
Checked October 7, 2026