Zed Industries · install guide
Zed skills. Where they live and how to install them.
Where Zed loads skills
- Zed loads only ~/.agents/skills/ (global) and <worktree>/.agents/skills/ (project). Nested folders such as group/my-skill are not discovered, and custom search paths are not supported (use a symlink).
- Project-local skills load only from trusted worktrees.
- Frontmatter documented: name (lowercase letters, numbers, hyphens; max 64), description (keep under 1,024 characters), disable-model-invocation. Other spec fields are planned.
- Adding, removing or editing a SKILL.md takes effect immediately without restarting; the total size of all names and descriptions is capped at 50KB.
- Zed asks you to allow or deny a user-created skill when the agent invokes it. The agent cannot edit SKILL.md files without your authorisation.
- Skills apply to the Zed Agent only; External Agents and Terminal Threads use their own skill systems.
- Manage skills under Settings > AI > Skills (agent.skills), and invoke with / or @skill in the message editor.
How to install a skill
agent: create skill from url (https://github.com/{owner}/{repo}/blob/main/{path}/SKILL.md)Command palette action. Imports a single GitHub Markdown file, so bundled scripts and references are not fetched; copy those separately.
agent: create skill from url (https://github.com/anthropics/skills/blob/main/skills/mcp-builder/SKILL.md)Example with MCP Server Builder.
npx skills add {owner}/{repo} --skill {skill} -a zedProject install goes to .agents/skills/; add -g for ~/.agents/skills/.
npx skills add anthropics/skills --skill mcp-builder -a zedExample 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/ inside the project for a project-local install. Each skill must be a direct child of the skills folder.
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 Zed
What skills are in Zed
Zed's documentation describes skills as reusable instruction packages that give the agent specialised knowledge, such as test-driven development workflows, document processing, database integrations or your team's internal standards. The agent sees a catalogue of installed skills and can load one on demand through a skill tool, or you can invoke any skill from the message editor with a slash command or an @skill mention.
A skill is a folder containing a SKILL.md. Zed documents three frontmatter fields: name (lowercase letters, numbers and hyphens, up to 64 characters, ideally matching the folder name), description (keep it to 1,024 characters or fewer; longer ones still load with a warning) and disable-model-invocation. Zed says it plans to support the other fields in the Agent Skills specification later.
Zed Skills apply to the built-in Zed Agent. External Agents and Terminal Threads may have their own skill systems, which you configure in that agent or CLI.
Where Zed looks for skills
| Scope | Path |
|---|---|
| Global | ~/.agents/skills/ |
| Project | <worktree>/.agents/skills/ |
Each skill must be a direct child of the skills folder. Nesting skills in subfolders, such as ~/.agents/skills/group/my-skill/, is not supported. Zed does not support custom search paths and does not load skills from remote locations at runtime, so use a symlink if a skill lives elsewhere. A project-local skill overrides a global one with the same name. Project skills load only from trusted worktrees, so a freshly cloned or untrusted project's skills stay out of the catalogue until you grant trust.
Install a skill
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
For a project-local skill, copy into .agents/skills/ in the repository instead. Zed's own page describes installing a registry skill the same way: copy the folder into ~/.agents/skills/ for global use, or into the project's .agents/skills/ for project use.
Option 2: the skills CLI
npx skills add anthropics/skills --skill frontend-design -a zed
This installs into .agents/skills/ in the project. Add -g for ~/.agents/skills/.
Option 3: import from a GitHub Markdown file
Open the command palette and run agent: create skill from url. If your clipboard holds a supported GitHub .md URL, Zed pre-fills and fetches it. For example:
https://github.com/anthropics/skills/blob/main/skills/frontend-design/SKILL.md
This imports a single Markdown file, so bundled scripts and reference files are not fetched. Copy those separately, or use option 1 for skills that rely on them.
Other ways to add a skill
Zed includes a built-in create-skill skill, which you invoke with /create-skill. You can also open the Skills Manager from the Agent Panel, or use the Create Skill button on the AI > Skills settings page. A skill can be shared with a zed://skill link that embeds the full SKILL.md. Opening the link shows a Create Skill page, and nothing is written to disk until you save.
Check that it loaded
Open the Settings Editor and go to AI > Skills (or agent.skills). The User tab lists global skills and each Project tab lists that project's skills, with actions to copy a share link, open the file or delete the folder. In the message editor, type / and select the skill, or type @skill and choose it from the menu. Adding, removing or editing a SKILL.md takes effect immediately, so no restart is needed.
Update and remove
- Remove: use Delete on the skill's row in Settings, or delete the folder, or run
npx skills remove frontend-design. - Update: copy a newer version of the folder over the old one. Changing a skill's name or description invalidates the model's prompt cache for the current session.
Troubleshooting
- A skill is missing from the list: confirm it is a direct child of
~/.agents/skills/or.agents/skills/, and that the folder containsSKILL.md. - A project skill does not load: the worktree may not be trusted. Grant trust, then check again.
- A skill with an invalid name fails to load and shows an error in the UI. Names cannot start or end with a hyphen or contain consecutive hyphens.
- The catalogue is full: the combined size of all skill names and descriptions is capped at 50KB, and skills that do not fit are dropped with a warning. Shorten descriptions.
- The agent pauses before using a skill: Zed asks you to allow or deny a skill you created or installed when the agent invokes it, so look for the permission prompt, or set per-skill defaults in Tool Permissions.
Safety
Zed documents several guards. Project skills load only from trusted worktrees, shared links write nothing until you save, and the agent cannot edit SKILL.md files or their resources without your explicit authorisation. You still decide what to install, so read SKILL.md and any scripts first, and be careful granting trust to a repository you have just cloned.
Top skills to try in Zed
| # | 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 | 5 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 | 4 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 | yesterday |
| 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 | yesterday |
| 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 | 2 days ago |
Questions, answered from the data.
Where does Zed look for skills?
Zed loads skill folders (each with a SKILL.md file) inside a project from .agents/skills/ and for every project from ~/.agents/skills/.
How do I install a skill in Zed?
Create skill from URL: agent: create skill from url (https://github.com/{owner}/{repo}/blob/main/{path}/SKILL.md). skills CLI: npx skills add {owner}/{repo} --skill {skill} -a zed. 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 Zed?
Agent skills are portable SKILL.md folders, so the catalogue's top skills work in Zed too. The highest-ranked right now are MCP Server Builder (anthropics/skills), PDF Processing (anthropics/skills) and Web Artifacts Builder (anthropics/skills).
Sources
- https://zed.dev/docs/ai/skills
- https://github.com/vercel-labs/skills
- https://agentskills.io/specification
Checked October 7, 2026