CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

python-packaging

Create distributable Python packages with proper project structure, setup.py/pyproject.toml, and publishing to PyPI. Use when packaging Python libraries, creating CLI tools, or distributing Python code.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/ext_conformance/artifacts/agents-wshobson/python-development/skills/python-packaging/SKILL.md

The canonical home for this skill is python-packaging in wshobson/agents

SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable and executable throughout, with complete code, commands, and validation checkpoints for the build-and-publish workflow. However, it is severely overweight: heavy boilerplate and templates Claude can already produce are inlined into a single ~880-line file with no progressive disclosure to reference files.

Suggestions

Split boilerplate templates (README template, .gitignore, MANIFEST.in, CI workflows, full-featured pyproject.toml) into one-level-deep reference files and keep only concise inline examples in SKILL.md.

Trim the ~120 lines of black/ruff/mypy/pytest/coverage tool configuration from the pyproject example — Claude already knows standard tool config and can generate it on demand.

Remove or quarantine time-sensitive version pins (cibuildwheel@v2.16.2, actions/checkout@v3) and add a brief error-recovery note for when `twine check` fails to strengthen the workflow's feedback loop.

DimensionReasoningScore

Conciseness

The ~880-line body inlines extensive boilerplate Claude already knows: ~120 lines of black/ruff/mypy/pytest/coverage config inside the full pyproject example, plus an argparse CLI example, a README template, a .gitignore, and MANIFEST.in. Dated version pins ("cibuildwheel@v2.16.2", "actions/checkout@v3", "setuptools>=61.0") add time-sensitive tokens outside any deprecated section, matching anchor 2's extensive padding rather than anchor 3's occasional tightening opportunities.

2 / 5

Actionability

Every pattern is complete and copy-paste ready: working pyproject.toml files, runnable Click and argparse CLI code, exact commands ("python -m build", "twine check dist/*", "twine upload --repository testpypi dist/*"), and full CI workflows covering the common packaging cases, matching the anchor-5 example.

5 / 5

Workflow Clarity

The publishing flow has a clear sequence with real validation checkpoints ("twine check dist/*", TestPyPI upload, clean-environment install test) plus a 13-item publishing checklist. It falls short of anchor 5 because there are no error-recovery feedback loops — what to do when twine check fails is never stated.

4 / 5

Progressive Disclosure

The body is well-sectioned with clear headers, but it is a monolithic ~880-line file with zero bundle references; content that clearly belongs in separate files (README template, .gitignore, MANIFEST.in, CI workflows, full pyproject examples) is entirely inline. This sits between anchor 2 (minimal structure — not the case, structure is good) and anchor 4 (nothing is split out), landing on anchor 3.

3 / 5

Total

14

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly and explicitly states both capabilities and use-when triggers in third person. Trigger terms are natural and domain-specific, with only minor gaps in synonym coverage and a small overlap risk from the CLI-tools trigger.

DimensionReasoningScore

Specificity

"Create distributable Python packages", "proper project structure, setup.py/pyproject.toml", and "publishing to PyPI" list several specific actions with concrete artifacts. Coverage has minor gaps (no wheels/sdists, versioning, or private indexes), so it falls at anchor 4 rather than a comprehensive 5.

4 / 5

Completeness

The description explicitly answers both questions: "what" ("Create distributable Python packages with proper project structure... publishing to PyPI") and "when" ("Use when packaging Python libraries, creating CLI tools, or distributing Python code") with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Natural phrases like "packaging Python libraries", "creating CLI tools", "distributing Python code", and "PyPI" match what users would actually say. Common variations such as "publish a package", "wheel", or "pip installable" are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

Python packaging is a clear niche with distinct triggers (PyPI, pyproject.toml, setup.py), so it is mostly distinct. The "creating CLI tools" trigger carries minor overlap risk with CLI-building skills, preventing a 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (889 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository

Dicklesworthstone/pi_agent_rust

Path

tests/ext_conformance/artifacts/agents-wshobson/python-development/skills/python-packaging/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.