fastmcp-python-tests

Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, and async testing.

Quality

75%

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/fastmcp-creator/skills/fastmcp-python-tests/SKILL.md

Quality

Content

67%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.

A practical, highly actionable testing style guide whose project-specific rules (async mode, module imports, in-memory transport, v3 API accessor, inline snapshots) are the real value. Its main cost is token weight from generic pytest best-practice sections that duplicate what Claude already knows.

Suggestions

Trim or cut the generic sections (Fixtures, Mocking, Error Testing, Test Naming) to one-line reminders, keeping the project-specific rules as the bulk of the skill.

Replace placeholder functions like calculate(-1) and connect_to_invalid_host() with realistic fastmcp-based examples so every snippet is copy-paste executable.

Consider moving the checklist and command reference to the top so the highest-frequency guidance is encountered first.

Dimension	Reasoning	Score
Conciseness	The project-specific rules (asyncio_mode auto, module-level imports, in-memory transport, the 'result.data' v3 constraint, uv run commands, inline-snapshot) earn their tokens, but the Fixtures, Mocking, Error Testing, and Test Naming sections largely restate standard pytest knowledge Claude already has.	3 / 5
Actionability	Nearly all guidance is executable copy-paste code with concrete commands ('uv run pytest -n 2 -k', '--inline-snapshot=create'), though a few examples rely on placeholder functions like calculate(-1) and connect_to_invalid_host().	4 / 5
Workflow Clarity	As a guideline skill rather than a sequential process, each action is unambiguous and anchored by a pre-submit checklist and a 'Running Tests' verification section; no validation cap applies since the skill is not destructive or batch-oriented.	4 / 5
Progressive Disclosure	No bundle files exist; the ~230-line body is organized into clean, well-ordered sections with a clearly cited external reference. Structure is good, though the single inline file is slightly too large for pure section organization alone to merit a 5.	4 / 5
	Total	15 / 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.

A well-constructed description with an explicit 'Use when...' trigger clause, concrete coverage areas, and a clear pytest/Python niche. Its main weaknesses are the slightly generic headline verbs and a few missing natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Python tests using pytest') plus several concrete coverage areas ('test design, fixtures, parameterization, mocking, and async testing'), but the headline verbs 'write and evaluate' are somewhat generic, keeping it short of comprehensive concrete-action enumeration.	4 / 5
Completeness	Clearly answers both 'what' (write and evaluate effective Python tests using pytest, with enumerated coverage areas) and 'when' via an explicit 'Use when...' clause listing four concrete trigger scenarios.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('writing tests', 'reviewing test code', 'debugging test failures', 'improving test coverage', 'pytest'), but misses common variants like 'unit tests', 'test suite', or 'TDD'.	4 / 5
Distinctiveness Conflict Risk	'Python tests using pytest' carves a clear niche, but 'reviewing test code' and 'improving test coverage' are broad enough to create minor overlap risk with generic code-review and coverage-analysis skills.	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: Jamie-BitFlight/claude_skills
Path: plugins/fastmcp-creator/skills/fastmcp-python-tests/SKILL.md
Commit: 3e0b2af

Reviewed: 3 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.