Skip to main content

Add Skills bundles to the LLM CLI tool

Project description

Add Skills bundles to the LLM CLI tool.

A tool for the llm command line that allows loading a Claude Skill.

Usage

Install for use with llm:

# install the plugin:
llm install llm-tools-skill

# see available plugins:
llm plugins

...
  {
    "name": "llm-tools-skill",
    "hooks": [
      "register_tools"
    ],
    "version": "0.1.0"
  },
...

Examples:

# Load my local skills, and use them against some other context (eg, a local repo):
repomix
cat repomix-output.xml | llm -T 'Skills("../my-coding-skills")' "Check this codebase against my own best practice skills"

This plugin supports two kinds of directory structures:

  • A single skill: A directory with a single SKILL.md and supporting files.
  • Multiple skills: A directory with multiple subdirectories, each containing a SKILL.md and supporting files.

Security and Privacy

Warning: This tool has read-access to your entire browser history. You risk sending this highly sensitive personal data to third-party services (like OpenAI).

See the lethal trifecta article for more information about the risks of using tools like this with LLMs.

Dev setup

make setup
make test

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llm_tools_skills-0.1.0.tar.gz (6.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llm_tools_skills-0.1.0-py3-none-any.whl (4.9 kB view details)

Uploaded Python 3

File details

Details for the file llm_tools_skills-0.1.0.tar.gz.

File metadata

  • Download URL: llm_tools_skills-0.1.0.tar.gz
  • Upload date:
  • Size: 6.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.5.24

File hashes

Hashes for llm_tools_skills-0.1.0.tar.gz
Algorithm Hash digest
SHA256 5a546892e1adcf2f856a44e1faf66afa38fb68405169d3fe10abb5c3e14e2867
MD5 8679e85bd9ceac64a1b29d782981b7db
BLAKE2b-256 35dade6f72541eb9c517c315a59a6a02cc6d1461434f31384d91ec1d5b0c483a

See more details on using hashes here.

File details

Details for the file llm_tools_skills-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for llm_tools_skills-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 019302dd0d1c099b7b9d330e71acc076a0ac62d44ebe7bb9a7a3ef7d89272960
MD5 320f949193adda3e01e25a582859c808
BLAKE2b-256 0c059defc6c180528d05bb2dccdf78b27d91d9805e6bf80937c33b38c19f6ba0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page