Skip to content
Back to search

skillz

SkillWorks with Claude CodeGitHub

An MCP server for loading skills (shim for non-claude clients).

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/intellectronica--skillz/badge.svg)](/listings/intellectronica--skillz)

HTML

<a href="/listings/intellectronica--skillz"><img src="/api/listings/intellectronica--skillz/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

To run the MCP server in your agent, use the following config (or equivalent):

{
  "skillz": {
    "command": "uvx",
    "args": ["skillz@latest"]
  }
}

with the skills residing at `~/.skillz`

_or_

{
  "skillz": {
    "command": "uvx",
    "args": ["skillz@latest", "/path/to/skills/direcotry"]
  }
}

or Docker

You can run Skillz using Docker for isolation. The image is available on Docker Hub at `intellectronica/skillz`.

To run the Skillz MCP server with your skills directory mounted using Docker, configure your agent as follows:

Replace `/path/to/skills` with the path to your actual skills directory. Any arguments after `intellectronica/skillz` in the array are passed directly to the Skillz CLI.

{
  "skillz": {
    "command": "docker",
    "args": [
      "run",
      "-i",
      "--rm",
      "-v",
      "/path/to/skills:/skillz",
      "intellectronica/skillz",
      "/skillz"
    ]
  }
}

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 169 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Skillz
  2. ## 👌 **Use _skills_ in any agent** _(Codex, Copilot, Cursor, etc...)_
  3. [![PyPI version](https://img.shields.io/pypi/v/skillz.svg)](https://pypi.org/project/skillz/)
  4. [![PyPI downloads](https://img.shields.io/pypi/dm/skillz.svg)](https://pypi.org/project/skillz/)
  5. > ⚠️ **Experimental proof‑of‑concept. Potentially unsafe. Treat skills like untrusted code and run in sandboxes/containers. Use at your own risk.**
  6. **Skillz** is an MCP server that turns [Claude-style skills](https://github.com/anthropics/skills) _(`SKILL.md` plus optional resources)_ into callable tools for any MCP client. It discovers each skill, exposes the authored instructions and resources, and can run bundled helper scripts.
  7. > 💡 You can find skills to install at the **[Skills Supermarket](http://skills.intellectronica.net/)** directory.
  8. ## Quick Start
  9. To run the MCP server in your agent, use the following config (or equivalent):
  10. ```json
  11. {
  12. "skillz": {
  13. "command": "uvx",
  14. "args": ["skillz@latest"]
  15. }
  16. }
  17. ```
  18. with the skills residing at `~/.skillz`
  19. _or_
  20. ```json
  21. {
  22. "skillz": {
  23. "command": "uvx",
  24. "args": ["skillz@latest", "/path/to/skills/direcotry"]
  25. }
  26. }
  27. ```
  28. or Docker
  29. You can run Skillz using Docker for isolation. The image is available on Docker Hub at `intellectronica/skillz`.
  30. To run the Skillz MCP server with your skills directory mounted using Docker, configure your agent as follows:
  31. Replace `/path/to/skills` with the path to your actual skills directory. Any arguments after `intellectronica/skillz` in the array are passed directly to the Skillz CLI.
  32. ```json
  33. {
  34. "skillz": {
  35. "command": "docker",
  36. "args": [
  37. "run",
  38. "-i",
  39. "--rm",
  40. "-v",
  41. "/path/to/skills:/skillz",
  42. "intellectronica/skillz",
  43. "/skillz"
  44. ]
  45. }
  46. }
  47. ```
  48. ## Gemini CLI Extension
  49. A Gemini CLI extension is available at [intellectronica/gemini-cli-skillz](https://github.com/intellectronica/gemini-cli-skillz).
  50. Install it with:
  51. ```bash
  52. gemini extensions install https://github.com/intellectronica/gemini-cli-skillz
  53. ```
  54. This extension enables Anthropic-style Agent Skills in Gemini CLI using the skillz MCP server.
  55. ## Usage
  56. Skillz looks for skills inside the root directory you provide (defaults to
  57. `~/.skillz`). Each skill lives in its own folder or zip archive (`.zip` or `.skill`)
  58. that includes a `SKILL.md` file with YAML front matter describing the skill. Any
  59. other files in the skill become downloadable resources for your agent (scripts,
  60. datasets, examples, etc.).
  61. An example directory might look like this:
  62. ```text
  63. ~/.skillz/
  64. ├── summarize-docs/
  65. │ ├── SKILL.md
  66. │ ├── summarize.py
  67. │ └── prompts/example.txt
  68. ├── translate.zip
  69. ├── analyzer.skill
  70. └── web-search/
  71. └── SKILL.md
  72. ```
  73. When packaging skills as zip archives (`.zip` or `.skill`), include the `SKILL.md`
  74. either at the root of the archive or inside a single top-level directory:
  75. ```text
  76. translate.zip
  77. ├── SKILL.md
  78. └── helpers/
  79. └── translate.js
  80. ```
  81. ```text
  82. data-cleaner.zip
  83. └── data-cleaner/
  84. ├── SKILL.md
  85. └── clean.py
  86. ```
  87. ### Directory Structure: Skillz vs Claude Code
  88. Skillz supports a more flexible skills directory than Claude Code. In addition to a flat layout, you can organize skills in nested subdirectories and include skills packaged as `.zip` or `.skill` files (as shown in the examples above).
  89. Claude Code, on the other hand, expects a flat skills directory: every immediate subdirectory is a single skill. Nested directories are not discovered, and `.zip` or `.skill` files are not supported.
  90. If you want your skills directory to be compatible with Claude Code (for example, so you can symlink one skills directory between the two tools), you must use the flat layout.
  91. **Claude Code–compatible layout:**
  92. ```text
  93. skills/
  94. ├── hello-world/
  95. │ ├── SKILL.md
  96. │ └── run.sh
  97. └── summarize-text/
  98. ├── SKILL.md
  99. └── run.py
  100. ```
  101. **Skillz-only layout examples** (not compatible with Claude Code):
  102. ```text
  103. skills/
  104. ├── text-tools/
  105. │ └── summarize-text/
  106. │ ├── SKILL.md
  107. │ └── run.py
  108. ├── image-processing.zip
  109. └── data-analyzer.skill
  110. ```
  111. You can use `skillz --list-skills` (optionally pointing at another skills root)
  112. to verify which skills the server will expose before connecting it to your
  113. agent.
  114. ## CLI Reference
  115. `skillz [skills_root] [options]`
  116. | Flag / Option | Description |
  117. | --- | --- |
  118. | positional `skills_root` | Optional skills directory (defaults to `~/.skillz`). |
  119. | `--transport {stdio,http,sse}` | Choose the FastMCP transport (default `stdio`). |
  120. | `--host HOST` | Bind address for HTTP/SSE transports. |
  121. | `--port PORT` | Port for HTTP/SSE transports. |
  122. | `--path PATH` | URL path when using the HTTP transport. |
  123. | `--list-skills` | List discovered skills and exit. |
  124. | `--verbose` | Emit debug logging to the console. |
  125. | `--log` | Mirror verbose logs to `/tmp/skillz.log`. |
  126. ---
  127. > Made with 🫶 by [`@intellectronica`](https://intellectronica.net)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.