CtrlK
BlogDocsLog inGet started
Tessl Logo

api-test-generator

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

36

0.99x

Quality

3%

Does it follow best practices?

Impact

99%

0.99x

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/api-test-generator/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

Payment Processor API Test Suite

Python API testing with pytest and mocking

Criteria
Without context
With context

Uses pytest framework

100%

100%

HTTP gateway mocked

100%

100%

Database mocked

100%

100%

Tests create_charge success path

100%

100%

Tests process_refund

100%

100%

Tests get_charge_status

100%

100%

Tests validation / error paths

100%

100%

Runnable configuration

100%

100%

Descriptive test names

100%

100%

AAA structure

100%

100%

conftest or fixtures used

100%

100%

Without context: $0.6187 · 2m 16s · 29 turns · 28 in / 9,972 out tokens

With context: $1.0138 · 3m 25s · 44 turns · 1,842 in / 14,356 out tokens

100%

Inventory Service Test Coverage

JavaScript API testing with Jest and mocking

Criteria
Without context
With context

Uses Jest framework

100%

100%

axios mocked

100%

100%

Redis client mocked

100%

100%

npm test script defined

100%

100%

Tests reserveStock logic

100%

100%

Tests releaseReservation

100%

100%

Tests syncStockFromWarehouse

100%

100%

Tests validation / error cases

100%

100%

Descriptive test names

100%

100%

Jest devDependency listed

100%

100%

Tests grouped with describe

100%

100%

beforeEach / afterEach cleanup

100%

100%

Without context: $0.6216 · 2m 53s · 26 turns · 68 in / 10,242 out tokens

With context: $0.8493 · 3m 24s · 32 turns · 112 in / 13,386 out tokens

97%

-3%

Notification Service: Build a Test Suite from Scratch

Unit vs integration test separation and framework configuration

Criteria
Without context
With context

Uses pytest

100%

100%

Unit tests exist

100%

100%

Integration tests exist

100%

100%

SendGrid client mocked

100%

100%

Twilio client mocked

100%

100%

Database isolation

100%

100%

Tests send_bulk orchestration

100%

100%

Tests validation errors

100%

100%

requirements.txt includes pytest

100%

100%

Test strategy README

100%

100%

Fixtures or conftest used

100%

57%

Without context: $0.8989 · 3m 15s · 38 turns · 35 in / 14,785 out tokens

With context: $1.0558 · 3m 46s · 48 turns · 331 in / 15,071 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.