The open agent skills tool - npx skills
skills
The CLI for the open agent skills ecosystem.
Supports OpenCode, Claude Code, Codex, Cursor, and 72 more.
Install a Skill Use a Skill Without Installing
Generate a prompt for one skill, or start a supported coding agent interactively:
skills use resolves sources the same way as skills add, writes the selected skill files to a temporary directory, and prints only the generated prompt to stdout unless --agent is provided. With --agent, it starts one supported agent interactively with the generated prompt.
Source Formats
Private Repositories
Use the same command for public and private repositories. The CLI uses the authentication already configured for the repository URL:
For GitHub HTTPS and shorthand sources, skills first uses normal Git credentials. If that fails and GitHub CLI is authenticated, it tries gh repo clone, followed by SSH. It does not execute gh auth token or copy the stored GitHub CLI credential into the Node.js process.
For GitHub tree lookups, skills first tries the API anonymously, then an explicitly supplied environment token, then gh api. GitHub CLI applies its own stored authentication and returns only the API response; the credential is never printed to or read by skills. If API access still fails, update checks fall back to an authenticated Git clone.
GITHUB_TOKEN or GH_TOKEN can be set explicitly for GitHub API access, including private repository downloads and update checks. They are optional for installs when Git, GitHub CLI, or SSH authentication is already configured.
Options
| Option | Description |
|---|---|
-g, --global |
Install to user directory instead of project |
-a, --agent <agents...> |
Target specific agents (e.g., claude-code, codex). See Supported Agents |
-s, --skill <skills...> |
Install specific skills by name (use '*' for all skills) |
-l, --list |
List available skills without installing |
--copy |
Copy files instead of symlinking to agent directories |
-y, --yes |
Skip all confirmation prompts |
--all |
Install all skills to all agents without prompts |
| Examples |
Direct download URLs are tried after well-known discovery. They may point to a single valid SKILL.md file or a .zip, .tar, .tar.gz, or .tgz archive; the URL does not need to include a file extension. Downloads are limited to 10 MiB, extracted content to 25 MiB, and archives to 1000 files by default. Override with SKILLS_DOWNLOAD_MAX_BYTES, SKILLS_EXTRACT_MAX_BYTES, and SKILLS_EXTRACT_MAX_FILES when you trust the source.
Installation Scope
| Scope | Flag | Location | Use Case |
|---|---|---|---|
| Project | (default) | ./<agent>/skills/ |
Committed with your project, shared with team |
| Global | -g |
~/<agent>/skills/ |
Available across all projects |
| Installation Methods |
When installing interactively, you can choose:
| Method | Description |
|---|---|
| Symlink (Recommended) | Creates symlinks from each agent to a canonical copy. Single source |
Listing: request indexing for spsDrop/doordash-ddcli-skill
[skills.sh] Re-index and re-audit dariorapisardi/parlor.sh: snapshot and audits stuck after one reinstall
Re-index and re-audit KalarisLabs/research-agent-skills after collection security update
[Listing]: Request indexing for mauinion/hydratrader-x402-catalog
Installer etiquette: always offer scope (global vs project), link mode (symlink vs copy), and target agents
[Feature]: `skills install` / `skills sync` command to install skills from lock file
[Feature]: Add `files` field to SKILL.md frontmatter for include/exclude control
Listing: Request reindexing for kensaurus/cursor-kenji to kensaurus/skills
Stale Socket audit for ahaomar/un-editorial-check: projectIgnorePaths already present at audit time did not suppress the fixture alert
Request indexing: inacior/writing-for-computer-science