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.
63
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/python-development/skills/python-packaging/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates specific capabilities around Python packaging, includes natural trigger terms users would use, and explicitly states both what the skill does and when to use it. The description is concise, uses third person voice, and occupies a distinct niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating distributable packages, proper project structure, setup.py/pyproject.toml configuration, and publishing to PyPI. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create distributable Python packages with proper structure, setup.py/pyproject.toml, publishing to PyPI) and 'when' (explicit 'Use when' clause covering packaging libraries, creating CLI tools, or distributing Python code). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Python packages', 'setup.py', 'pyproject.toml', 'PyPI', 'packaging Python libraries', 'CLI tools', 'distributing Python code'. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly occupies a distinct niche around Python packaging and distribution. Terms like 'PyPI', 'setup.py', 'pyproject.toml', and 'distributable packages' are highly specific and unlikely to conflict with general Python development or other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable examples for Python packaging but is severely bloated with content Claude already knows (PEP references, layout advantages, tool configurations). The workflow for building and publishing lacks explicit validation checkpoints and error recovery. The content would benefit significantly from aggressive trimming and better separation of core vs. reference material.
Suggestions
Cut the 'When to Use This Skill', 'Core Concepts', and layout advantage explanations — Claude knows these. Reduce to Quick Start + key pyproject.toml patterns + build/publish commands.
Move the full-featured pyproject.toml (Pattern 4), CLI patterns, tool configurations, and GitHub Actions workflow into referenced files to keep SKILL.md lean.
Add explicit validation checkpoints to the build/publish workflow: verify twine check passes, test install from TestPyPI works correctly, then publish to production PyPI with a clear error recovery loop.
Remove the argparse CLI pattern entirely (Claude knows argparse) and trim the Click example to just the pyproject.toml entry point registration + a minimal example.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at 400+ lines. It explains concepts Claude already knows (what PyPI is, what source/flat layouts are, advantages of source layout), lists PEP numbers without actionable context, includes full tool configurations (black, ruff, mypy, pytest, coverage) that are tangential to packaging, and provides two complete CLI patterns (click + argparse) that are standard Python knowledge. The 'When to Use This Skill' section with 9 bullet points and 'Core Concepts' section with 4 subsections are largely unnecessary padding. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code throughout: complete pyproject.toml files, working CLI implementations, exact bash commands for building and publishing, a complete GitHub Actions workflow, and proper file structures. All examples are concrete and directly usable. | 3 / 3 |
Workflow Clarity | The build-and-publish workflow (Patterns 8-9) has a reasonable sequence but lacks explicit validation checkpoints and error recovery steps. For example, there's no guidance on what to do if 'twine check' fails, no verification step after TestPyPI upload (e.g., testing the installed package works), and no feedback loop for fixing issues before publishing to production PyPI. | 2 / 3 |
Progressive Disclosure | The skill references 'references/advanced-patterns.md' at the end, which is good progressive disclosure, but the bundle has no files so we can't verify it exists. The main content itself is monolithic — the full-featured pyproject.toml (Pattern 4) with all tool configurations inline could easily be split into a reference file, and the CLI patterns could be separate. The structure has sections but too much detail is inline. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (511 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
112197c
- 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.