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 findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-tester/SKILL.md

Quality

Content

15%

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 exhaustive, verbose testing treatise that over-explains basics Claude already knows and lacks a concrete, sequenced testing workflow with validation checkpoints. It is a monolithic wall of text with no progressive disclosure into reference files.

Suggestions

Cut explanatory padding (test pyramid diagram, FIRST characteristics, best-practices platitudes) and keep only the concrete patterns and thresholds Claude would not already know.

Add a numbered testing workflow with explicit validation checkpoints (e.g. run tests -> read failures -> fix -> re-run -> report coverage), including a feedback loop for batch/full-suite runs.

Move the lengthy per-type code examples into reference files (e.g. references/unit-testing.md, references/e2e-testing.md) and keep SKILL.md as a concise overview that links to them.

Dimension	Reasoning	Score
Conciseness	The ~320-line body re-teaches concepts Claude already knows (an ASCII test pyramid, the FIRST test characteristics, TDD, arrange-act-assert) and is padded with motivational filler like "Tests are a safety net that enables confident refactoring," matching the verbose anchor.	1 / 3
Actionability	It provides concrete Jest/TypeScript examples for each test type, but they are generic illustrative templates rather than copy-paste-ready for a real task, and the "MCP Tool Integration" blocks use non-executable pseudo-syntax (e.g. `mcp__claude-flow__memory_usage { ... }`), fitting the "some concrete guidance but incomplete" anchor.	2 / 3
Workflow Clarity	There is no sequenced multi-step testing workflow with validation checkpoints; the body is a catalog of test types and a best-practices list, and it never specifies a validate-fix-retry loop, matching the "steps unclear or missing; no validation mentioned" anchor.	1 / 3
Progressive Disclosure	The skill is a single monolithic file with no bundle references, and hundreds of lines of code examples that should live in separate reference files are inlined, matching the "monolithic wall of text" anchor; it is well over 50 lines so the simple-skill exception does not apply.	1 / 3
	Total	5 / 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.

This is a poor activation description: it states only that the skill is a "tester" agent and how to invoke it, without describing concrete capabilities or when to use it. It is unlikely to drive correct skill activation.

Suggestions

Replace the description with concrete actions, e.g. "Writes and runs unit, integration, and end-to-end test suites, analyzes coverage, and reports failures."

Add an explicit trigger clause such as "Use when the user asks to write tests, increase coverage, debug a failing test, or validate code changes."

Drop the "invoke with $agent-tester" syntax from the description; invocation mechanics do not belong in the activation description.

Dimension	Reasoning	Score
Specificity	The description is "Agent skill for tester - invoke with $agent-tester", which names only a vague domain ("tester") and lists no concrete actions, matching the "vague or no actions" anchor.	1 / 3
Completeness	It gives a very weak "what" ("Agent skill for tester") and no "when"/"Use when" trigger guidance at all, so both halves are weak or missing.	1 / 3
Trigger Term Quality	"invoke with $agent-tester" is invocation syntax rather than natural keywords a user would say; the only term ("tester") is overly generic, fitting the technical-jargon/no-natural-keywords anchor.	1 / 3
Distinctiveness Conflict Risk	"Agent skill for tester" is so generic it would overlap with any testing-related skill and gives no distinct trigger, matching the "very generic; would conflict with many skills" anchor.	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
Path: .agents/skills/agent-tester/SKILL.md
Commit: 26c35b5

Reviewed: about 5 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.