CtrlK
BlogDocsLog inGet started
Tessl Logo

tdd-guide

Comprehensive Test Driven Development guide for engineering subagents with multi-framework support, coverage analysis, and intelligent test generation

56

1.03x
Quality

33%

Does it follow best practices?

Impact

95%

1.03x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./generated-skills/tdd-guide/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

4%

Coverage Health Report for E-Commerce Backend

Coverage gap analysis with prioritized recommendations

Criteria
Without context
With context

P0 for critical gap

80%

100%

P1 for moderate gap

75%

100%

80% line threshold applied

100%

100%

Branch coverage checked

100%

100%

70% branch threshold applied

100%

100%

Coverage summary present

100%

100%

P0 listed before P1

100%

100%

Uncovered lines identified

100%

100%

Actionable recommendations

100%

100%

No E2E or performance testing suggested

100%

100%

Summary first

100%

100%

Output file produced

100%

100%

100%

10%

Test Suite for Inventory Management Module

Framework-appropriate test generation with AAA structure

Criteria
Without context
With context

Uses pytest

100%

100%

test_ naming convention

100%

100%

Specification-style names

100%

100%

Arrange-Act-Assert sections

0%

100%

Happy path covered

100%

100%

Error conditions tested

100%

100%

Edge cases covered

100%

100%

Behavior focused

100%

100%

Test isolation

100%

100%

Single behavior per test

100%

100%

No E2E or integration approach

100%

100%

Output test file created

100%

100%

87%

-3%

Implement a TypeScript String Truncation Utility Using TDD

TDD red-green-refactor workflow with correct framework imports

Criteria
Without context
With context

Uses Jest

0%

0%

describe/it structure

100%

100%

RED phase documented

100%

100%

GREEN phase documented

100%

100%

REFACTOR phase documented

100%

62%

Specification-style test names

100%

100%

Assertions use expect()

100%

100%

Behavior focused tests

100%

100%

Error/edge cases tested

100%

100%

TDD log file created

100%

100%

Test and implementation files

100%

100%

Minimal GREEN implementation

100%

100%

Repository
thinmintdev/claude-cooker
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.