python-testing

pytest、TDD手法、フィクスチャ、モック、パラメータ化、カバレッジ要件を使用したPythonテスト戦略。

Quality

56%

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 ./docs/ja-JP/skills/python-testing/SKILL.md

Quality

Content

53%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 skill is highly actionable with comprehensive executable pytest examples, but it is severely over-long, re-teaching concepts Claude already knows and inlining reference material that should be split into bundled files. Workflow clarity is moderate: TDD sequencing exists but validation/feedback loops for risky operations are absent.

Suggestions

Trim or remove sections that re-explain basics Claude already knows (basic assertions, simple fixtures, tmp_path) to reclaim token budget.

Move the large reference catalogs (assertion patterns, mock variants, marker/ini config) into bundled reference files and link to them one level deep from SKILL.md.

Add explicit validation/feedback checkpoints where risk applies, e.g. 'run pytest --cov and confirm coverage meets the 80% threshold before committing'.

Dimension	Reasoning	Score
Conciseness	At ~810 lines the body extensively documents concepts Claude already knows (basic asserts, fixture scopes, simple mocks, tmp_path) with many redundant near-duplicate examples, which is noticeably verbose and padded.	2 / 5
Actionability	The content is almost entirely concrete, executable, copy-paste-ready code and commands covering fixtures, parametrization, mocking, async testing, and pytest invocation, spanning the common cases thoroughly.	5 / 5
Workflow Clarity	The TDD red/green/refactor section gives a clear sequence, but there are no validation checkpoints or feedback loops for risky/batch operations (e.g. running suites, coverage gating), and the rest is reference material rather than a sequenced workflow.	3 / 5
Progressive Disclosure	No bundle files exist, yet ~810 lines of reference material (assertion catalog, fixture variants, mock patterns, config snippets) that clearly belongs in separate reference files is inlined into SKILL.md with no external navigation.	2 / 5
	Total	12 / 20 Passed

Description

58%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 third-person and enumerates several concrete capabilities, giving it solid specificity and distinctiveness. Its main weakness is the absence of any explicit 'Use when...' trigger clause, which caps completeness, and the keyword set lacks the natural user phrasings.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when writing Python tests, designing a test suite, or reviewing test coverage.'

Include natural user phrases and synonyms such as 'write tests', 'test my Python code', and 'pytest' alongside the existing capability terms.

Convert the comma-separated keyword list into full action verbs (e.g. 'write', 'mock', 'parametrize', 'measure coverage') for stronger specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — "TDD手法、フィクスチャ、モック、パラメータ化、カバレッジ要件" — naming the domain with multiple specific actions, though the coverage is a keyword list rather than fully enumerated actions.	4 / 5
Completeness	It clearly states what the skill does (Python testing strategy using pytest/TDD/fixtures/mocks/parametrization/coverage), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains relevant terms (pytest, TDD, フィクスチャ, モック, パラメータ化, カバレッジ) but lacks the natural phrases a user would actually say (e.g. "write tests", "test my code") and common synonyms, so keyword coverage is partial.	3 / 5
Distinctiveness Conflict Risk	The pytest/TDD/fixtures/mocks framing carves a clear niche distinct from generic Python or coding skills, with only minor overlap risk against a broader Python-development skill.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (816 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: docs/ja-JP/skills/python-testing/SKILL.md
Commit: e04ea0b

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.