Skip to main content

SkillLite

A lightweight Skills secure execution engine. One package: full CLI + sandbox API.

pip install skilllite

CLI (full capability)

skilllite chat              # Interactive chat with LLM
skilllite add owner/repo    # Add skills from GitHub
skilllite list              # List installed skills
skilllite mcp               # Start MCP server (for Cursor/Claude)
skilllite run/exec/bash     # Execute skills
skilllite init-cursor       # Initialize Cursor IDE integration
# ... and more

API (Python ↔ binary bridge)

from skilllite import scan_code, execute_code, chat, run_skill

# Sandbox: security scan + execute (IDE/MCP integration)
result = scan_code("python", "print(1+1)")
result = execute_code("python", "print(sum(range(101)))")

# Direct skill execution
result = run_skill("./.skills/calculator", '{"operation": "add", "a": 15, "b": 27}')

# Agent chat (single-shot, hides binary CLI)
result = chat("帮我分析这个项目", skills_dir=".skills", stream=True)
# result["success"], result["exit_code"]

Artifacts (run-scoped blobs over HTTP)

Use the same API as docs/openapi/artifact-store-http-v1.yaml. No extra pip dependencies (stdlib urllib).

from skilllite import artifact_put, artifact_get

artifact_put("http://127.0.0.1:8080", "my-run-id", "outputs/result.json", b'{"ok": true}')
data = artifact_get("http://127.0.0.1:8080", "my-run-id", "outputs/result.json")

Serve locally with the main CLI (subcommand is in the default binary; must allow bind explicitly):

cargo build -p skilllite --bin skilllite
SKILLLITE_ARTIFACT_SERVE_ALLOW=1 ./target/debug/skilllite artifact-serve --dir /tmp/art --bind 127.0.0.1:8080

Build from source

./scripts/build_wheels.sh

Release files for skilllite 0.1.29

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for skilllite 0.1.29
File Size Uploaded
skilllite-0.1.29.tar.gz 15.1 kB Details

Built distributions (wheels)

Table of built distributions (wheels) for skilllite 0.1.29
File
skilllite-0.1.29-py3-none-win_amd64.whl Python 3 none Windows x86-64 Details
skilllite-0.1.29-py3-none-manylinux_2_17_x86_64.whl Python 3 none Linux glibc 2.17+ x86-64 Details
skilllite-0.1.29-py3-none-macosx_11_0_x86_64.whl Python 3 none macOS 11.0+ x86-64 Details
skilllite-0.1.29-py3-none-macosx_11_0_arm64.whl Python 3 none macOS 11.0+ ARM64 Details

Total release size: 23.8 MB

Release files / skilllite-0.1.29.tar.gz

Download URL skilllite-0.1.29.tar.gz
Size 15.1 kB
Tags Source
SHA-256 checksum
How to use checksums
35576df3bbc8ff382baf199e5dbc5c64eefb1b18ef2145669ee744a150c7a6d1
BLAKE2b-256 checksum
How to use checksums
154f6d9ca3083ba83cbf5aff0e1560d7a778cb7578428e40cfe86a5e744ee7da
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.15

Release files / skilllite-0.1.29-py3-none-win_amd64.whl

Download URL skilllite-0.1.29-py3-none-win_amd64.whl
Size 6.3 MB
Tags Python 3 Windows x86-64
SHA-256 checksum
How to use checksums
c5f477cf6190e6ab777a9cb85d9f6cb028001f583f99e5c9e8cf77b485726373
BLAKE2b-256 checksum
How to use checksums
c0e49ac2d71b714434be74fdd915d8c1b2e1dbe19a5b34b9caf3497ce762f366
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.15

Release files / skilllite-0.1.29-py3-none-manylinux_2_17_x86_64.whl

Download URL skilllite-0.1.29-py3-none-manylinux_2_17_x86_64.whl
Size 6.3 MB
Tags Linux glibc 2.17+ x86-64 Python 3
SHA-256 checksum
How to use checksums
fc1bcd68a18af85da2420427f5a1f3c73122e694bbe5feee29e1a51ccafdbf6c
BLAKE2b-256 checksum
How to use checksums
1238b5f7d38c3f87d43cf9ca13045af80c835d2bf79c03ec8730c0938bdbcabf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.15

Release files / skilllite-0.1.29-py3-none-macosx_11_0_x86_64.whl

Download URL skilllite-0.1.29-py3-none-macosx_11_0_x86_64.whl
Size 5.9 MB
Tags Python 3 macOS 11.0+ x86-64
SHA-256 checksum
How to use checksums
451bfa2ee294254b9c3a4fbfb2c7b25635d8d2843626785c94503a7c88b5bf4a
BLAKE2b-256 checksum
How to use checksums
126d141f5f8aa33c9dc5e510ba32859f85f6619fd83f2660281a479b4006f17e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.15

Release files / skilllite-0.1.29-py3-none-macosx_11_0_arm64.whl

Download URL skilllite-0.1.29-py3-none-macosx_11_0_arm64.whl
Size 5.3 MB
Tags Python 3 macOS 11.0+ ARM64
SHA-256 checksum
How to use checksums
18450811dcf32a9e18d6b3a81228a337d7e468f7b15a875691e5b3a210d78850
BLAKE2b-256 checksum
How to use checksums
c2a20b02af6ba04bf86a7e790a63792352ba36504967016cdde06e40762d9680
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.15

Release history Release notifications | RSS feed

This release

0.1.29 This release

5 release files

0.1.28

5 release files

0.1.27

5 release files

0.1.26

5 release files

0.1.25

5 release files

0.1.24

5 release files

0.1.23

5 release files

0.1.18

5 release files

0.1.17

5 release files

0.1.16

5 release files

0.1.15

5 release files

0.1.14

2 release files

0.1.12

2 release files

0.1.9

2 release files

0.1.8

2 release files

0.1.4

2 release files

0.1.3

2 release files

0.1.2

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page