CtrlK
BlogDocsLog inGet started
Tessl Logo

pytest-test-generator

Pytest Test Generator - Auto-activating skill for Test Automation. Triggers on: pytest test generator, pytest test generator Part of the Test Automation skill category.

34

1.00x

Quality

3%

Does it follow best practices?

Impact

90%

1.00x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/09-test-automation/pytest-test-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

80%

Payment Processor Test Coverage

Parametrized tests with mocking

Criteria
Without context
With context

Test file naming

100%

100%

Test function naming

100%

100%

Uses parametrize decorator

0%

0%

Multiple parametrize cases

0%

0%

Mocking applied

100%

100%

Mock isolates dependency

100%

100%

Meaningful assertions

100%

100%

Edge case coverage

100%

100%

No test interdependence

100%

100%

Imports correct

100%

100%

Tests runnable

100%

100%

Without context: $0.5527 · 2m · 28 turns · 29 in / 6,731 out tokens

With context: $0.7079 · 2m 29s · 36 turns · 293 in / 8,973 out tokens

92%

Test Infrastructure for Inventory Service

Test suite setup with fixtures and configuration

Criteria
Without context
With context

conftest.py created

100%

100%

Fixture decorator used

100%

100%

Fixture used in test

100%

100%

pytest config file

100%

100%

Test file naming

100%

100%

Test function naming

100%

100%

Unit tests present

100%

100%

Step-by-step run instructions

100%

100%

Meaningful assertions

100%

100%

Tests deterministic

100%

100%

requirements or deps listed

0%

0%

Without context: $0.6104 · 2m 22s · 32 turns · 31 in / 8,386 out tokens

With context: $0.8333 · 2m 42s · 42 turns · 42 in / 10,595 out tokens

100%

Order Pipeline Integration Tests

Integration tests with isolation and edge cases

Criteria
Without context
With context

Integration test scope

100%

100%

Fixture for shared setup

100%

100%

Fixture injected correctly

100%

100%

Test file naming

100%

100%

Test function naming

100%

100%

Error path tested

100%

100%

Edge case covered

100%

100%

Tests deterministic

100%

100%

No shared mutable state

100%

100%

Meaningful assertions

100%

100%

Mocking of external I/O

100%

100%

Without context: $0.4185 · 1m 54s · 25 turns · 26 in / 6,740 out tokens

With context: $0.7180 · 2m 28s · 35 turns · 68 in / 9,031 out tokens

Repository
jeremylongshore/claude-code-plugins-plus-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.