agent-tdd-london-swarm

Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm

1.01x

Quality

Does it follow best practices?

Impact

93%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-tdd-london-swarm/SKILL.md

Evaluation results

92%

-1%

Subscription Billing Service Tests

Outside-in mock-first TDD

Criteria

Without context

With context

Acceptance test first

30%

Mocks defined before SUT

100%

jest.fn() used for all mocks

100%

Collaborators injected via constructor

100%

Payment gateway call verified

100%

Repository save verified

100%

Email service call verified

100%

No state assertions as primary checks

100%

90%

Mocks are minimal

100%

Clear collaborator interface revealed

100%

Tests pass

100%

88%

Order Fulfillment Workflow Tests

Interaction sequence verification

Criteria

Without context

With context

Order-enforcing assertion present

100%

Payment-before-shipping assertion

100%

toHaveBeenCalledBefore usage

getAllMockCalls snapshot OR call-order check

66%

100%

jest.fn() mocks for all three collaborators

100%

Behavior verification focus

100%

Mocks injected via constructor

100%

Mocks are focused

100%

Tests pass

100%

Authentication Service Contract Design

Contract design via mock expectations

Criteria

Without context

With context

UserRepository mock is minimal

100%

TokenStore mock is minimal

100%

jest.fn() used for all mock methods

100%

Interface revealed by mock setup

100%

Authenticate interaction verified

100%

Revoke interaction verified

100%

No state assertions as primary checks

100%

Contracts are cohesive

100%

Mocks drive design

100%

Tests pass

100%

Repository: ruvnet/claude-flow
Commit: f547cec

Evaluated: 26 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Subscription Billing Service Tests Order Fulfillment Workflow Tests Authentication Service Contract Design

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.