Name: agent-tdd-london-swarm
Rating: 59.4 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-tdd-london-swarm

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

1.01x

Quality

39%

Does it follow best practices?

Impact

93%

1.01x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-tdd-london-swarm/SKILL.md

The canonical home for this skill is agent-tdd-london-swarm in ruvnet/claude-flow

Quality

Content

50%Weight 40%Scale 1-5

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

The content is a well-sectioned tour of London School TDD with illustrative Jest examples, but it leans on fictional swarm APIs, carries an out-of-place YAML config block, and never gives a concrete, validated workflow. It reads more like a concept overview than executable skill guidance.

Suggestions

Replace or remove references to non-existent APIs (swarmCoordinator, createSwarmMock, extendSwarmMock, SwarmContractMonitor, jest.getAllMockCalls) with real, runnable Jest code or clearly label them as illustrative.

Add a concrete sequenced workflow (e.g. write failing acceptance test -> define collaborator mocks -> implement to green -> verify interactions) with an explicit validation checkpoint before refactoring.

Move the YAML agent-config block and the contract/API reference material into reference files under references/ and link to them from the body, keeping SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly code and sectioned, but it includes an extraneous YAML config block, restates TDD concepts Claude already knows, and repeats known London School principles in the closing "Remember" paragraph.	3 / 5
Actionability	Real Jest primitives (jest.fn().mockResolvedValue) appear, but many examples call fictional APIs (swarmCoordinator, createSwarmMock, extendSwarmMock, SwarmContractMonitor, jest.getAllMockCalls), making them pseudocode rather than executable.	3 / 5
Workflow Clarity	Methodology subsections imply an outside-in sequence but there is no explicit step ordering or validation/feedback loop, and the test-run workflow lacks verify-then-proceed checkpoints.	3 / 5
Progressive Disclosure	No bundle files exist and the entire ~245-line body is inline with section headers; structure is present but nothing is split out or referenced, which for a skill this long leaves it heavier than the overview-only ideal.	3 / 5
	Total	12 / 20 Passed

Description

28%Weight 40%Scale 1-5

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 description is a placeholder-style line that names the skill slug and how to invoke it, but tells neither what the skill concretely does nor when to use it. It reads as generated metadata rather than useful trigger guidance.

Suggestions

Rewrite the description to state concrete capabilities, e.g. "Drives outside-in TDD using mocks to define collaborator contracts and verify object interactions."

Add an explicit "Use when..." trigger clause naming natural phrases like "writing tests", "mockist TDD", "London School TDD", or "defining collaborator contracts".

Drop the "invoke with $agent-tdd-london-swarm" boilerplate; it is invocation metadata, not a capability or trigger.

Dimension	Reasoning	Score
Specificity	The description "Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm" names the domain but lists no concrete actions, only an invocation hint.	2 / 5
Completeness	It gives a vague "what" ("Agent skill for tdd-london-swarm") and no "when"/"Use when..." clause, matching the vague-what-plus-no-when anchor.	2 / 5
Trigger Term Quality	The only keyword is the internal slug "tdd-london-swarm"; there are no natural trigger phrases a user would actually say, just technical jargon.	2 / 5
Distinctiveness Conflict Risk	The London School TDD niche is fairly specific, but the description provides no trigger context so it could still overlap with other testing/TDD skills.	3 / 5
	Total	9 / 20 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/ruflo
Path: .agents/skills/agent-tdd-london-swarm/SKILL.md
Commit: fa13ee4

Reviewed: about 8 hours 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.