platform-testing

Framework-agnostic testing principles — test philosophy, structure, mocking boundaries. Use when writing, reviewing, or debugging tests.

1.18x

Quality

51%

Does it follow best practices?

Impact

94%

1.18x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/platform/platform-testing/SKILL.md

Quality

Discovery

67%

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 has good structure with an explicit 'Use when' clause that clearly defines trigger scenarios. However, it leans toward abstract concepts (philosophy, principles) rather than concrete actions, and could benefit from more specific trigger terms that users naturally use when seeking testing help.

Suggestions

Add concrete actions like 'structure test suites', 'design mocks', 'organize test files' to improve specificity

Include additional natural trigger terms such as 'unit tests', 'test cases', 'TDD', 'mocking', 'assertions', or 'test coverage'

Dimension	Reasoning	Score
Specificity	Names the domain (testing) and some conceptual areas (test philosophy, structure, mocking boundaries), but lacks concrete actions like 'write unit tests', 'create mocks', or 'structure test suites'.	2 / 3
Completeness	Clearly answers both what (framework-agnostic testing principles covering philosophy, structure, mocking) and when (writing, reviewing, or debugging tests) with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Includes 'tests', 'writing', 'reviewing', 'debugging' which are natural terms, but misses common variations like 'unit tests', 'test cases', 'TDD', 'assertions', 'test coverage', or 'specs'.	2 / 3
Distinctiveness Conflict Risk	'Framework-agnostic' helps distinguish from framework-specific testing skills, but 'testing principles' is broad enough to potentially overlap with language-specific or framework-specific testing skills.	2 / 3
	Total	9 / 12 Passed

Implementation

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides reasonable high-level testing principles but lacks the concrete, actionable guidance that makes skills valuable. The majority of content is generic boilerplate (Examples, Troubleshooting, Workflow sections) that applies to any skill rather than testing-specific instruction. The actual testing guidance is limited to bullet-point principles without executable examples or concrete application patterns.

Suggestions

Add concrete code examples demonstrating AAA pattern, integration vs unit test boundaries, and proper mocking strategies

Remove or significantly condense the generic troubleshooting and examples sections - they don't add testing-specific value

Include a concrete testing workflow with validation steps (e.g., 'run tests in isolation first, then full suite')

Provide specific examples of what 'test behavior not implementation' looks like in code vs what to avoid

Dimension	Reasoning	Score
Conciseness	The principles section is lean and efficient, but the boilerplate sections (Examples, Troubleshooting, Workflow) add significant padding with generic content that doesn't provide testing-specific value.	2 / 3
Actionability	No concrete code examples, commands, or executable guidance. The principles are abstract statements without demonstration of how to apply them. The 'See rules index' reference defers all actionable content elsewhere.	1 / 3
Workflow Clarity	The workflow section provides a basic 3-step sequence, but it's generic meta-workflow about using the skill rather than a testing workflow. No validation checkpoints or concrete testing process steps.	2 / 3
Progressive Disclosure	References rules/_sections.md for detailed patterns (one level deep), but the main content is padded with generic troubleshooting that could be removed. The structure exists but content balance is off.	2 / 3
	Total	7 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	10 / 11 Passed

Repository: ravnhq/ai-toolkit
Commit: 7b466be

Reviewed: 11 days 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.