testing-strategy
Guidelines for writing effective tests in this project
38
36%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./testing-strategy/SKILL.mdQuality
Discovery
14%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 description is too vague and generic to serve as an effective skill selector. It lacks concrete actions, explicit trigger conditions, and distinguishing details that would help Claude choose it over other skills. It reads more like a document title than a functional skill description.
Suggestions
Add a 'Use when...' clause specifying when this skill should be selected, e.g., 'Use when the user asks about writing tests, test patterns, or test best practices in this project.'
List specific concrete actions or topics covered, such as 'Covers unit test structure, mocking strategies, assertion patterns, and test naming conventions for [language/framework].'
Include natural trigger terms users would say, such as 'unit tests', 'test cases', 'testing', 'TDD', 'test coverage', and mention the specific project or framework to improve distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is vague — 'writing effective tests' names a broad domain but lists no concrete actions (e.g., unit tests, integration tests, mocking, assertions, coverage). 'Guidelines' is abstract. | 1 / 3 |
Completeness | It weakly addresses 'what' (guidelines for writing tests) but completely lacks any 'when' clause or explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains 'tests' and 'writing' which are natural keywords a user might say, but misses common variations like 'unit tests', 'test cases', 'testing', 'TDD', 'assertions', 'mocks', or specific frameworks. | 2 / 3 |
Distinctiveness Conflict Risk | Very generic — 'writing effective tests' could overlap with any testing-related skill, code quality skill, or project-specific coding guidelines skill. No distinguishing details about the project, language, or testing framework. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable overview of testing conventions with some concrete elements (bash commands, directory structure), but leans heavily on general testing best practices that Claude already knows. It would benefit from project-specific examples, concrete test code patterns, and less restating of universal testing wisdom.
Suggestions
Replace generic advice (e.g., 'test one thing per test', 'Arrange-Act-Assert') with project-specific test examples showing the actual testing framework, assertion style, and patterns used in this codebase.
Add a concrete, executable example of a unit test and an integration test using the project's actual test framework and conventions.
Include a brief workflow for writing a new test: create file in correct directory → follow naming convention → run tests → check coverage threshold.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably concise but includes some guidance that Claude already knows well (e.g., 'Test one thing per test', 'Mock external dependencies', Arrange-Act-Assert pattern). Several bullet points state general testing wisdom rather than project-specific conventions. | 2 / 3 |
Actionability | The bash commands for running tests are concrete and executable, and the directory structure is specific. However, the bulk of the content is general advice ('use descriptive test names', 'keep tests fast') rather than concrete, project-specific examples of test code or patterns to follow. | 2 / 3 |
Workflow Clarity | The test running commands are clearly listed, and the directory structure provides orientation. However, there's no workflow for writing a new test (e.g., create file → write test → run → verify coverage), and no validation checkpoints or feedback loops for ensuring test quality. | 2 / 3 |
Progressive Disclosure | For a simple skill under 50 lines with no need for external references, the content is well-organized into clear sections (Unit Tests, Integration Tests, Running Tests, Test Structure, Best Practices, Coverage Goals) that are easy to scan and navigate. | 3 / 3 |
Total | 9 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- block/agent-skills
- Commit
60bfdad
- 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.