python-best-practices

Provides Python patterns for type-first development with dataclasses, discriminated unions, NewType, and Protocol. Must use when reading or writing Python files.

1.66x

Quality

—

Does it follow best practices?

Impact

88%

1.66x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is highly actionable with complete executable code and a clear sequenced type-first workflow, but it is long and monolithic with some redundant examples and lacks progressive disclosure via separate reference files.

Suggestions

Trim redundant examples (the Examples section repeats NotImplementedError, raise-from, and exhaustive match already illustrated) to improve token efficiency.

Move the optional ty tooling guide and/or the configuration deep-dive into a separate reference file referenced from SKILL.md for better progressive disclosure.

Add a concrete validation checkpoint to the type-first workflow (e.g. "run ty check / mypy and fix reported errors before proceeding") to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly lean code-with-brief-notes that assumes Python competence, but the length (~270 lines) and the duplicated Examples plus optional ty/Configuration sections could be tightened.	2 / 3
Actionability	Provides many complete, executable, copy-paste-ready examples with imports and full class/match definitions rather than pseudocode.	3 / 3
Workflow Clarity	The Type-First Development workflow is a clear 4-step sequence including a "Validate at boundaries" step, but validation is conceptual rather than a concrete checkpoint and no feedback loops are shown.	2 / 3
Progressive Disclosure	Well-organized into clearly headed sections, but it is a monolithic single-file skill (~270 lines) with no bundle references; the ty tooling and detailed examples could be split out.	2 / 3
	Total	9 / 12 Passed

Description

77%

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 specific about the patterns covered and clearly pairs a what-clause with an explicit when-trigger, but its trigger terms are somewhat narrow and the broad Python-files trigger creates overlap risk with general Python skills.

Suggestions

Broaden trigger terms to natural phrasings users actually say, e.g. "writing or refactoring Python code", "adding type hints", or "reviewing Python best practices".

Narrow the trigger to reduce conflict risk, e.g. "Use when designing or refactoring Python types and data models" rather than any Python file read/write.

Dimension	Reasoning	Score
Specificity	Names multiple concrete patterns ("dataclasses, discriminated unions, NewType, and Protocol"), comparable to listing several specific actions rather than vague domain references.	3 / 3
Completeness	Explicitly states what ("Provides Python patterns for type-first development with...") and when ("Must use when reading or writing Python files"), with an explicit trigger clause.	3 / 3
Trigger Term Quality	"Must use when reading or writing Python files" supplies a couple of natural terms but misses common variations like "Python code", "writing Python", "refactoring", or "type hints".	2 / 3
Distinctiveness Conflict Risk	The what is niche (type-first development), but the trigger "reading or writing Python files" is broad and would fire for almost any Python task, risking overlap with other Python skills.	2 / 3
	Total	10 / 12 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: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 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.