agent-tdd-london-swarm
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-tdd-london-swarm48
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 93%
↑ 1.01xAgent success when using this skill
Validation for skill structure
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It functions only as an invocation reference rather than a functional description, providing no information about capabilities, use cases, or trigger conditions. Claude would have no basis for selecting this skill appropriately from a list of available skills.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Implements Test-Driven Development using London/mockist style with outside-in design, creating tests with mocks and stubs before implementation code.'
Include a 'Use when...' clause with natural trigger terms like 'TDD', 'test-driven', 'London style testing', 'mockist TDD', 'outside-in testing', or 'write tests first'.
Remove the invocation instruction from the description field - this belongs elsewhere. The description should focus entirely on capabilities and selection criteria.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for tdd-london-swarm' is completely abstract and doesn't describe what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command, not functional information. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'tdd-london-swarm' which is technical jargon. No natural keywords a user would say like 'test', 'TDD', 'test-driven development', or 'London style' are present. | 1 / 3 |
Distinctiveness Conflict Risk | While the name 'tdd-london-swarm' is unique, the description provides no context about what makes this skill distinct. Without knowing what it does, it's impossible to distinguish it from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable introduction to London School TDD concepts with TypeScript examples, but suffers from being overly verbose and conceptual rather than actionable. The 'swarm coordination' features reference undefined utilities making them non-executable, and the lack of progressive disclosure results in a lengthy document that could benefit from splitting into focused reference files.
Suggestions
Extract the swarm coordination patterns, contract testing, and best practices into separate reference files (e.g., SWARM_PATTERNS.md, CONTRACTS.md) and link to them from a concise overview
Provide actual implementations or installation instructions for the swarm utilities (swarmCoordinator, createSwarmMock, SwarmContractMonitor) or remove them if they're conceptual
Add a clear numbered workflow showing the exact sequence of steps to follow when applying London School TDD, including validation checkpoints
Remove explanatory text that restates what the code examples already demonstrate (e.g., 'Focus on HOW objects collaborate' when the code shows this)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes some unnecessary verbosity. The 'Core Responsibilities' section lists concepts Claude already understands, and some explanations like 'Focus on HOW objects collaborate' are redundant given the code examples already demonstrate this. | 2 / 3 |
Actionability | Provides TypeScript code examples that appear executable, but many rely on undefined utilities (swarmCoordinator, createSwarmMock, extendSwarmMock, SwarmContractMonitor) without showing their implementation. The 'swarm coordination' patterns are conceptual rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | The outside-in development flow is mentioned but lacks explicit step-by-step sequencing with validation checkpoints. The document describes patterns but doesn't provide a clear workflow for when/how to apply each pattern or verify correctness. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files for detailed information. All patterns, examples, and best practices are inline despite the document being quite long. No navigation structure or links to separate reference materials. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
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.