qa-tester
QA Tester Agent. 테스트 작성, 실행, 검증을 담당합니다. 테스트, 검증, 단위테스트, 통합테스트, E2E 관련 요청 시 사용됩니다.
Install with Tessl CLI
npx tessl i github:shaul1991/shaul-agents-plugin --skill qa-tester86
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
89%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 solid skill description that effectively communicates its testing focus with good trigger term coverage in Korean. It successfully answers both 'what' and 'when' questions. The main weakness is that the specific capabilities could be more detailed - listing concrete actions like 'generate test cases', 'create mocks', or 'analyze test coverage' would strengthen the specificity dimension.
Suggestions
Expand the capability list with more specific actions such as 'generate test cases', 'create mock objects', 'analyze code coverage', or 'identify edge cases' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (QA/testing) and lists some actions ('테스트 작성, 실행, 검증' - test writing, execution, verification), but lacks comprehensive specific actions like 'generate test cases', 'mock dependencies', or 'analyze coverage'. | 2 / 3 |
Completeness | Clearly answers both what ('테스트 작성, 실행, 검증을 담당합니다' - handles test writing, execution, verification) AND when ('테스트, 검증, 단위테스트, 통합테스트, E2E 관련 요청 시 사용됩니다' - use when requests involve tests, verification, unit tests, integration tests, E2E). | 3 / 3 |
Trigger Term Quality | Includes good coverage of natural Korean terms users would say: '테스트' (test), '검증' (verification), '단위테스트' (unit test), '통합테스트' (integration test), 'E2E' - these are common terms developers naturally use when requesting testing help. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on QA/testing with distinct triggers (unit test, integration test, E2E, verification). Unlikely to conflict with general coding skills or documentation skills due to explicit testing terminology. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable testing skill with excellent code examples and efficient token usage. The main weakness is the lack of explicit workflow guidance - there's no process for test-driven development, no validation steps for ensuring test quality, and no error recovery guidance when tests fail. The structure is good but could benefit from splitting detailed patterns into referenced files.
Suggestions
Add a workflow section with explicit steps: write test → run test → verify failure → implement → verify pass → check coverage
Include validation checkpoints such as 'If coverage drops below threshold, identify untested code paths before proceeding'
Consider moving detailed code patterns to a separate PATTERNS.md file and referencing it from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient with no unnecessary explanations. Every section provides direct, actionable information without explaining concepts Claude already knows (like what Jest is or how testing works). | 3 / 3 |
Actionability | Provides fully executable code examples for both unit and E2E tests, complete bash commands for running tests, and concrete patterns that are copy-paste ready with proper TypeScript syntax. | 3 / 3 |
Workflow Clarity | While test commands and patterns are clear, there's no explicit workflow for the testing process itself - no validation checkpoints, no guidance on what to do when tests fail, and no sequence for when to run which type of test. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in a single file. For a skill of this size (~120 lines), the fixtures section and detailed patterns could be referenced externally to keep the main skill leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Reviewed
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.