Name: agent-tester
Rating: 52.8 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-tester

Agent skill for tester - invoke with $agent-tester

1.14x

Quality

30%

Does it follow best practices?

Impact

88%

1.14x

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-tester/SKILL.md

The canonical home for this skill is agent-tester in ruvnet/claude-flow

Quality

Content

32%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 body is an oversized, generic testing tutorial padded with concepts Claude already knows, and its code examples are corrupted (forward slashes replaced with '$') so they are not copy-paste executable. It lacks a sequenced workflow with validation checkpoints and inlines everything instead of splitting into reference files.

Suggestions

Fix the corrupted '/' -> '$' characters throughout the code blocks (e.g. $users -> /users, $dev$null -> /dev/null, $script> -> </script>) so examples are executable.

Cut the conceptual primer (test pyramid, test-type definitions, FAST mnemonic, arrange-act-assert) that Claude already knows, keeping only skill-specific guidance.

Split the large example collections into references/ files and point to them from a concise overview in SKILL.md, and add a sequenced run-validate-report workflow with explicit checkpoints.

Dimension	Reasoning	Score
Conciseness	The ~320-line body is a general testing tutorial — test pyramid, unit vs integration vs e2e definitions, arrange-act-assert, FAST characteristics — extensively covering concepts Claude already knows, fitting 'noticeably verbose; several unnecessary explanations or padded sections'.	2 / 5
Actionability	Concrete Jest/TypeScript examples are provided, but many are non-executable because '/' is corrupted to '$' (e.g. '$users', '$dev$null', '$script>', 'swarm$tester$status') and at least one references an undefined `userData`, so guidance is concrete but incomplete with broken details.	3 / 5
Workflow Clarity	There is no sequenced workflow with checkpoints — the body is a reference of test types and best practices rather than a 'do this, then validate, then that' process, matching 'rough sequence present but many gaps; validation absent'.	2 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and all ~320 lines are inlined in one file with no pointers to separate materials, fitting 'minimal structure; content that clearly belongs in separate files is inlined'.	2 / 5
	Total	9 / 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 too vague to be a useful skill trigger: it names the testing domain but states no concrete capabilities and offers no natural-language 'when to use' guidance, relying on invocation syntax instead. It would rarely be selected from a natural user request.

Suggestions

Replace the description with concrete actions, e.g. 'Runs unit, integration, and e2e test suites and reports coverage and failures.'

Add an explicit trigger clause such as 'Use when the user asks to run tests, fix failing tests, or check test coverage.'

Drop the '$agent-tester' invocation syntax from the description; that belongs in usage docs, not the trigger description.

Dimension	Reasoning	Score
Specificity	The phrase 'Agent skill for tester' names the testing domain but lists no concrete actions (e.g. run tests, report coverage), matching the 'names the domain but actions are minimal or generic' anchor rather than the entirely-vague 1.	2 / 5
Completeness	It gives only a vague 'what' (an agent skill 'for tester') and no real 'when' — 'invoke with $agent-tester' is usage syntax, not a trigger condition, matching the 'vague what and no when' anchor.	2 / 5
Trigger Term Quality	'$agent-tester' is an invocation syntax token and 'tester' is a single generic keyword; there are no natural phrases a user would say when needing QA (e.g. 'run tests', 'fix failing tests'), so it sits at the one-or-two-generic-keywords anchor.	2 / 5
Distinctiveness Conflict Risk	The unique '$agent-tester' invocation gives it some distinctiveness, but 'tester' alone is broad and could overlap with general coding/QA skills, fitting 'somewhat specific but could still overlap'.	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-tester/SKILL.md
Commit: fa13ee4

Reviewed: about 4 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.