Skip to main content

somm-skill

Onboarding guidance for coding agents working in projects that use somm.

The package ships two markdown resources:

  • SKILL.md — general LLM-call guidance for agents editing Python code.
  • SOMMELIER.md — model-selection guidance for agents using somm-mcp.

Installation

Install the package with the rest of the workspace:

pip install somm-skill

For Claude Code, copy the canonical skill into the local skill folder:

python - <<'PY'
from importlib.resources import files
from pathlib import Path
import shutil

target = Path.home() / ".claude" / "skills" / "somm"
target.mkdir(parents=True, exist_ok=True)
for name in ("SKILL.md", "SOMMELIER.md"):
    shutil.copyfile(files("somm_skill") / name, target / name)
PY

For other agents, use the same two markdown files as the source of truth and adapt only the surrounding packaging format.

Metadata

Release files for somm-skill 0.17.2

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

Source distribution (sdist)

Source distribution for somm-skill 0.17.2
File Size Uploaded
somm_skill-0.17.2.tar.gz 10.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for somm-skill 0.17.2
File Interpreter ABI Platform
somm_skill-0.17.2-py3-none-any.whl Python 3 none any Details

Total release size: 23.0 kB

Release files / somm_skill-0.17.2.tar.gz

Download URL somm_skill-0.17.2.tar.gz
Size 10.9 kB
Tags Source
SHA-256 checksum
How to use checksums
a89f0ce977081f8ba7220d5fd21fe13f9796467acb10b9e9dcca9ffe099c4d33
BLAKE2b-256 checksum
How to use checksums
7cb86c990336d6b58a6d3e089b1077fe353b2ed92d232337730f54746c6ac487
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 12, 2026.

Transparency log

Release files / somm_skill-0.17.2-py3-none-any.whl

Download URL somm_skill-0.17.2-py3-none-any.whl
Size 12.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a661ac6765e2552a2af48fe252ce4b07a708b7ea40b3f8330b3b365082e66283
BLAKE2b-256 checksum
How to use checksums
2572ce10eab984495734491393a75b382c22bf8d5c80fde117f7b6655f82b284
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 12, 2026.

Transparency log

Release history Release notifications | RSS feed

0.19.0

2 release files

0.18.0

2 release files

This release

0.17.2 This release

2 release files

0.17.1

2 release files

0.17.0

2 release files

0.16.0

2 release files

0.15.0

2 release files

0.14.0

2 release files

0.13.0

2 release files

0.12.0

2 release files

0.7.1

2 release files

0.7.0

2 release files

0.6.1

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