Agent Skills
Agent Skills are a simple, open format for giving agents new capabilities and expertise.
Skills are folders of instructions, scripts, and resources that agents can discover and use to perform better at specific tasks. Write once, use everywhere.
Installation
pip install skills-ref
Or using uv:
uv add skills-ref
Quick Start
CLI Usage
# Validate a skill
agentskills validate path/to/skill
# Read skill properties (outputs JSON)
agentskills read-properties path/to/skill
# Generate <available_skills> XML for agent prompts
agentskills to-prompt path/to/skill-a path/to/skill-b
Python API
from pathlib import Path
from skills_ref import validate, read_properties, to_prompt
# Validate a skill directory
errors = validate(Path("my-skill"))
if errors:
print("Validation errors:", errors)
else:
print("Valid skill!")
# Read skill properties
props = read_properties(Path("my-skill"))
print(f"Skill: {props.name}")
print(f"Description: {props.description}")
# Generate prompt XML for agent integration
prompt = to_prompt([Path("skill-a"), Path("skill-b")])
print(prompt)
Features
- Validation: Check skills for proper format and required fields
- Parsing: Extract skill metadata from SKILL.md frontmatter
- Prompt Generation: Create XML blocks for agent system prompts
- i18n Support: Full Unicode support for international skill names
- CLI Tools: Command-line utilities for skill management
Documentation
- Full Documentation - Guides and tutorials
- Specification - Format details
- Example Skills - See what's possible
About
Agent Skills is an open format maintained by Anthropic and open to contributions from the community.
License
Apache 2.0
Metadata
Release files for skills-ref 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| skills_ref-0.1.1.tar.gz | 93.5 kB | Without provenance | Details for skills_ref-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| skills_ref-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for skills_ref-0.1.1-py3-none-any.whl |
Total release size: 106.4 kB
Release files / skills_ref-0.1.1.tar.gz
| Download URL | skills_ref-0.1.1.tar.gz |
|---|---|
| Size | 93.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6b400ca6e0049be62dca0167ff943ba2745fd67efb37fbba4d0ee341fccd2695
|
|
BLAKE2b-256 checksum How to use checksums |
2342943d3ba8b097af7068b7178563a5062ad8a977982f4a7b4f67facfc575e9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.22
|
Release files / skills_ref-0.1.1-py3-none-any.whl
| Download URL | skills_ref-0.1.1-py3-none-any.whl |
|---|---|
| Size | 12.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d35db5bb8de71ae301daf5ca9cb71f8a555e8c6f83a6d40e46a5bc09f8f461b5
|
|
BLAKE2b-256 checksum How to use checksums |
af2536a43c3a61fb6cc3984e6ad5e556929b8ae71c95eba615dae4cf2f427964
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.8.22
|
Security for skills-ref 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.