agent-tester

Agent skill for tester - invoke with $agent-tester

1.14x

Quality

—

Does it follow best practices?

Impact

88%

1.14x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

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 thorough, actionable QA reference with genuinely executable test examples, but it is verbose and monolithic — no content is split into reference files and no validation-gated workflow is provided. It would benefit from trimming boilerplate and extracting detailed examples into separate bundle files.

Suggestions

Trim repetitive boilerplate test scaffolding (e.g. shared beforeEach/mock setup) to reduce token overhead and move from conciseness 2 toward 3.

Add a sequenced testing workflow with explicit validation checkpoints (e.g. run tests -> read failures -> fix -> re-run) to raise workflow clarity, especially for batch/destructive operations.

Extract large code-example blocks (performance, security, MCP integration) into reference files under references/ and link to them from a concise SKILL.md overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The ~290-line body avoids explaining basic concepts Claude already knows, but includes lengthy boilerplate TypeScript test blocks and some repetition across test types that could be tightened, matching the 'Mostly efficient but includes some unnecessary explanation or could be tightened' anchor.	2 / 3
Actionability	It provides real, executable Jest/supertest/Playwright code, concrete coverage thresholds (>80% statements, >75% branches), and specific best-practice lists that are copy-paste ready, matching the 'Fully executable code/commands; specific examples' anchor.	3 / 3
Workflow Clarity	Test types and a test pyramid give some structure, but there is no sequenced multi-step workflow with explicit validation checkpoints or feedback loops for risky operations, matching the 'Steps listed but validation gaps' anchor.	2 / 3
Progressive Disclosure	All content sits inline in a single monolithic SKILL.md with no bundle files or external references; it is organized into clear sections, but long code/API patterns that could be split into separate files remain inline, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 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 a low-quality meta-description of the skill artifact rather than a statement of what the skill does or when to use it. It lists no concrete actions, no natural trigger terms, and no 'Use when' guidance, capping its usefulness for skill selection.

Suggestions

Rewrite the description to state concrete actions in third person, e.g. 'Designs and writes unit, integration, and end-to-end test suites, analyzes edge cases, and validates performance and security.'

Add an explicit trigger clause such as 'Use when the user asks to write tests, improve coverage, or validate code quality.'

Replace the technical invocation token ('$agent-tester') with natural keywords users would actually say ('testing', 'tests', 'QA', 'test coverage').

Dimension	Reasoning	Score
Specificity	The description ('Agent skill for tester - invoke with $agent-tester') names only a role and an invocation mechanism, listing no concrete actions or capabilities; it matches the 'Vague or no actions; abstract language' anchor.	1 / 3
Completeness	It neither explains concretely what the skill does nor provides any 'Use when...' trigger guidance; both 'what' and 'when' are very weak, matching the 'Missing what OR when, or both very weak' anchor.	1 / 3
Trigger Term Quality	It offers no natural trigger keywords a user would say (e.g. 'testing', 'tests', 'QA'); '$agent-tester' is a technical invocation token, matching the 'No natural keywords; technical jargon or overly generic' anchor.	1 / 3
Distinctiveness Conflict Risk	'tester' narrows the niche somewhat over a fully generic description, but with no distinct triggers it could still overlap with other testing-related skills, matching the 'Somewhat specific but could still overlap' anchor.	2 / 3
	Total	5 / 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.