python-packaging

Comprehensive guide to creating, structuring, and distributing Python packages using modern packaging tools, pyproject.toml, and publishing to PyPI.

Quality

41%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/python-packaging/SKILL.md

The canonical home for this skill is python-packaging in rmyndharis/antigravity-skills

Quality

Content

22%Scale 1-5

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

This skill is essentially a stub that delegates all real content to a referenced resource file that wasn't provided. The SKILL.md body contains no concrete guidance—no pyproject.toml examples, no build commands, no publishing workflow, no validation steps. The instructions are generic boilerplate that could apply to any domain, making this skill nearly useless as standalone content.

Suggestions

Add a concrete quick-start workflow with actual commands: e.g., creating pyproject.toml, running `python -m build`, and `twine upload`.

Include at least a minimal pyproject.toml template as an executable, copy-paste-ready example.

Define a clear sequenced workflow with validation steps (e.g., build → check with `twine check dist/*` → upload → verify installation).

Replace the generic instruction bullets ('Clarify goals', 'Apply best practices') with Python-packaging-specific guidance that Claude wouldn't already know.

Dimension	Reasoning	Score
Conciseness	The 'Use this skill when' and 'Do not use this skill when' sections are somewhat verbose and list many scenarios Claude could infer. The instructions section is generic and doesn't add Python-packaging-specific value. However, it's not excessively padded.	3 / 5
Actionability	The skill provides zero concrete code, commands, or specific guidance. Instructions like 'Clarify goals, constraints, and required inputs' and 'Apply relevant best practices' are entirely vague and non-actionable. There are no executable examples, no pyproject.toml templates, no build commands, nothing copy-paste ready.	1 / 5
Workflow Clarity	There is no defined workflow, no sequenced steps, and no validation checkpoints. The four bullet points in Instructions are generic platitudes that could apply to any skill, not a clear process for Python packaging.	1 / 5
Progressive Disclosure	The skill references `resources/implementation-playbook.md` for detailed patterns, which is a reasonable one-level-deep reference. However, no bundle files were provided to verify the reference exists, and the SKILL.md itself contains almost no substantive overview content to serve as a useful entry point before directing to the resource.	3 / 5
	Total	8 / 20 Passed

Description

61%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 identifies a clear domain (Python packaging) and mentions specific tools and targets (pyproject.toml, PyPI), giving it reasonable specificity and distinctiveness. However, it lacks an explicit 'Use when...' clause, which is critical for Claude's skill selection, and the actions described are high-level rather than enumerating concrete tasks.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about publishing to PyPI, setting up pyproject.toml, creating a Python package, or distributing Python libraries.'

Include additional trigger terms and synonyms such as 'setup.py', 'pip', 'wheel', 'sdist', 'package distribution', and 'build system' to improve keyword coverage.

List more specific concrete actions such as 'configure build backends, define package metadata, manage dependencies, build wheels and sdists, upload to PyPI' to improve specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (Python packaging) and mentions a few concrete elements like 'pyproject.toml' and 'publishing to PyPI', but the actions are described at a high level ('creating, structuring, distributing') rather than listing specific concrete tasks like setting up build systems, configuring dependencies, or managing versioning.	3 / 5
Completeness	The 'what' is reasonably clear (guide to creating, structuring, and distributing Python packages), but there is no explicit 'when' clause. There's no 'Use when...' guidance telling Claude when to select this skill, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes several natural keywords users would say: 'Python packages', 'pyproject.toml', 'PyPI', 'packaging tools'. Missing some common variations like 'pip install', 'setup.py', 'wheel', 'sdist', 'publish a package', or 'package distribution'.	4 / 5
Distinctiveness Conflict Risk	Fairly distinct due to the specific mention of Python packaging, pyproject.toml, and PyPI. Minor overlap risk with general Python development skills or dependency management skills, but the packaging focus is clear enough to differentiate in most cases.	4 / 5
	Total	14 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/python-packaging/SKILL.md
Commit: 57c135b

Reviewed: 2 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.