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

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a concept-heavy, example-laden overview of London School TDD that explains familiar ideas and relies on non-existent swarm helpers. It offers some concrete patterns but lacks an executable workflow or external reference structure.

Suggestions

Cut explanations of well-known concepts (what mocking is, outside-in TDD) and keep only the non-obvious swarm-coordination specifics to improve conciseness.

Replace undefined helpers (swarmCoordinator, createSwarmMock, extendSwarmMock, SwarmContractMonitor) with real, executable code or document where they come from so examples are runnable.

Add an explicit sequenced TDD workflow with validation checkpoints (write failing test -> run -> implement to green -> refactor -> re-run) rather than descriptive strategy lists.

Dimension	Reasoning	Score
Conciseness	The ~240-line body explains TDD/mocking concepts Claude already knows and pads with illustrative examples using undefined helpers (swarmCoordinator, createSwarmMock), matching the verbose/explains-known-concepts anchor.	1 / 3
Actionability	Code examples are present but rely on undefined functions/objects (createSwarmMock, extendSwarmMock, SwarmContractMonitor, toSatisfyContract), so they are illustrative rather than copy-paste executable, matching the incomplete/pseudocode anchor.	2 / 3
Workflow Clarity	Sections list responsibilities and strategies but provide no sequenced TDD workflow (red/green/refactor) and no validation checkpoints, matching steps-present-but-checkpoints-missing; it stays above 1 because content is organized into sections.	2 / 3
Progressive Disclosure	No bundle files exist and all examples are inline in a single ~240-line document with no external references or navigation, matching the structure-present-but-content-that-could-be-separate-is-inline anchor.	2 / 3
	Total	7 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The frontmatter description is boilerplate that names the skill but describes no capabilities or use conditions. It would not help a user or Claude know when to invoke it.

Suggestions

Replace the description with concrete actions the skill performs, e.g. 'Drives outside-in TDD with mocks, defines collaborator contracts, and coordinates test coverage across agents.'

Add an explicit 'Use when...' clause stating natural trigger conditions, e.g. 'Use when writing mockist/London School tests, defining object contracts, or coordinating test coverage across agents.'

Include natural trigger terms users would say (mocks, stubs, behavior verification, test contracts) rather than the internal invocation syntax.

Dimension	Reasoning	Score
Specificity	The description only states 'Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm', naming no concrete actions, matching the vague/abstract anchor.	1 / 3
Completeness	It answers neither 'what does this do' (no actions) nor 'when should Claude use it' (no trigger clause), matching the missing what-AND-when anchor.	1 / 3
Trigger Term Quality	It contains only the internal name and invocation syntax ($agent-tdd-london-swarm), no natural keywords a user would say, matching the no-natural-keywords/jargon anchor.	1 / 3
Distinctiveness Conflict Risk	'Agent skill for tdd-london-swarm' is generic boilerplate with no niche or distinct triggers, so it is not distinguishable from other skills.	1 / 3
	Total	4 / 12 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: ruvnet/claude-flow
Commit: 8ae8752

Reviewed: 2 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.