CtrlK
BlogDocsLog inGet started
Tessl Logo

qa-test-planner

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

Install with Tessl CLI

npx tessl i github:softaworks/agent-toolkit --skill qa-test-planner
What are skills?

76

1.58x

Does it follow best practices?

Evaluation95%

1.58x

Agent success when using this skill

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

90%

63%

QA Test Cases for User Authentication Module

Test Case Format and Structure

Criteria
Without context
With context

Naming convention

0%

0%

Priority notation

0%

100%

Objective section

12%

100%

Preconditions section

100%

100%

Expected result per step

100%

100%

Test Data section

0%

100%

Status field

0%

100%

Estimated time

0%

100%

Edge cases included

40%

100%

Post-conditions section

0%

100%

P0 test for critical path

0%

100%

Without context: $0.2608 · 1m 18s · 9 turns · 10 in / 4,907 out tokens

With context: $0.5306 · 2m 9s · 15 turns · 17 in / 6,974 out tokens

100%

18%

Document Defects Found During E-Commerce Checkout Testing

Bug Report Quality and Structure

Criteria
Without context
With context

Title format

50%

100%

BUG-ID format

100%

100%

Severity field

100%

100%

Priority field

100%

100%

Environment section

100%

100%

URL in environment

100%

100%

Numbered repro steps

100%

100%

Expected behavior

100%

100%

Actual behavior

100%

100%

Reproduction rate

100%

100%

Impact assessment

25%

100%

Visual evidence section

0%

100%

Without context: $0.1625 · 47s · 7 turns · 8 in / 2,598 out tokens

With context: $0.4868 · 2m 5s · 14 turns · 46 in / 6,668 out tokens

96%

24%

Build Regression Suite for Payment Processing Module

Regression Suite Structure and Execution Strategy

Criteria
Without context
With context

Smoke suite defined

100%

100%

Full regression suite defined

60%

100%

Suite durations specified

100%

100%

Execution frequency specified

100%

100%

Smoke runs first

100%

100%

P0 before P1/P2 order

62%

100%

90% pass rate criterion

100%

100%

P0 failure blocks release

50%

100%

Security/data loss in fail criteria

33%

100%

Test case priority assigned

100%

100%

P0 cases for critical paths

0%

100%

Exploratory testing mentioned

0%

0%

Without context: $0.2057 · 1m 6s · 8 turns · 8 in / 4,008 out tokens

With context: $0.5091 · 2m 18s · 13 turns · 14 in / 7,603 out tokens

Evaluated
Agent
Claude Code
Model
Unknown

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.