CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-tester

Agent skill for tester - invoke with $agent-tester

Install with Tessl CLI

npx tessl i github:ruvnet/claude-flow --skill agent-tester
What are skills?

26

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

98%

3%

Unit Test Suite for Currency Calculator Service

Unit test structure and edge cases

Criteria
Without context
With context

Describe grouping

100%

100%

beforeEach setup

100%

100%

Dependency mocking

100%

100%

Success path test

100%

100%

Error path test

100%

100%

Empty/null handling

100%

100%

Boundary value test

37%

100%

Concurrent operations

100%

100%

AAA structure

100%

100%

Descriptive test names

100%

100%

Single behavior per test

100%

60%

Test data factory

100%

100%

Test independence

100%

100%

Coverage thresholds

100%

100%

Without context: $0.5310 · 2m 4s · 27 turns · 34 in / 7,236 out tokens

With context: $0.7580 · 2m 45s · 33 turns · 41 in / 9,271 out tokens

85%

30%

Performance and Security Test Suite for Analytics Platform

Performance and security testing

Criteria
Without context
With context

Timing measurement

100%

100%

1000-item benchmark

100%

100%

100ms threshold

100%

100%

Heap memory capture

0%

100%

50MB memory threshold

0%

100%

SQL injection payload

100%

100%

Data integrity after injection

0%

0%

XSS payload

100%

100%

Script tag absence

100%

100%

JSDoc @test tag

0%

100%

JSDoc @description tag

0%

100%

JSDoc @steps tag

0%

0%

JSDoc @expected tag

0%

0%

Without context: $0.2664 · 1m 33s · 16 turns · 17 in / 4,796 out tokens

With context: $0.6829 · 2m 49s · 29 turns · 191 in / 9,368 out tokens

82%

Integration Test Suite for Task Management API

Integration tests and coverage configuration

Criteria
Without context
With context

beforeAll setup

20%

20%

afterAll teardown

0%

0%

POST status 201

100%

100%

GET retrieval test

100%

100%

Response body assertions

100%

100%

Statements coverage ≥80%

100%

100%

Branches coverage ≥75%

100%

100%

Functions coverage ≥80%

100%

100%

Lines coverage ≥80%

100%

100%

Test independence

100%

100%

Error response test

100%

100%

Without context: $0.4537 · 2m · 28 turns · 33 in / 6,176 out tokens

With context: $0.7049 · 2m 23s · 36 turns · 43 in / 7,531 out tokens

Evaluated
Agent
Claude Code

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.