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

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/python-packaging/SKILL.md

Quality

Content

36%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.

The content is well-structured but shallow: it defers all concrete guidance to a referenced playbook file that is missing from the bundle, leaving the Instructions as generic process advice with no executable steps or validation for a publish-to-PyPI workflow.

Suggestions

Replace the abstract Instructions ('Apply relevant best practices and validate outcomes') with a concrete sequenced workflow, e.g. configure pyproject.toml -> build sdist/wheel (`python -m build`) -> check (`twine check dist/*`) -> upload (`twine upload dist/*`), with a validation checkpoint before upload.

Either add the missing resources/implementation-playbook.md bundle file or remove the references to it so progressive disclosure points to real material.

Trim the redundant 9-item 'Use this skill when' list and the opening sentence that repeats the frontmatter description to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, but the opening sentence restates the frontmatter description and the 9-item 'Use this skill when' list contains overlapping entries that could be tightened.	3 / 5
Actionability	The Instructions are abstract meta-advice ('Apply relevant best practices and validate outcomes', 'Provide actionable steps and verification') with no concrete code or commands, and the only concrete pointer (resources/implementation-playbook.md) references a file that does not exist.	2 / 5
Workflow Clarity	Packaging and publishing to PyPI is a multi-step, hard-to-reverse process, but no sequenced steps or validation checkpoints are provided; the Instructions section gives only generic high-level hints.	2 / 5
Progressive Disclosure	Sections are well-organized and the reference is clearly signaled at one level deep, but it points to resources/implementation-playbook.md which is absent from the bundle, leaving the body as a trigger list with no real detailed material behind it.	3 / 5
	Total	10 / 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.

The description is strong: it clearly states capabilities and explicit use-when triggers in third person, with good keyword coverage. Minor gaps in specificity (missing wheel/sdist terms) keep it just below the top anchor on two dimensions.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('proper project structure, setup.py/pyproject.toml, and publishing to PyPI'), but omits specifics like wheels, sdists, and classifiers that appear only in the body, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly states both what it does ('Create distributable Python packages with proper project structure...') and when to use it ('Use when packaging Python libraries, creating CLI tools, or distributing Python code') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('packaging Python libraries', 'creating CLI tools', 'publishing to PyPI') plus file artifacts (setup.py/pyproject.toml), but misses common synonyms like 'wheel', 'sdist', or '.whl'.	4 / 5
Distinctiveness Conflict Risk	Python packaging is a fairly distinct niche with PyPI-specific triggers, but 'distributing Python code' is broad enough to risk minor overlap with a general Python development skill.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/python-packaging/SKILL.md
Commit: 3eff4af

Reviewed: 22 days ago

Table of Contents

Discovery Implementation Validation

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.