twd-test-writer
TWD test writing context — teaches AI agents how to write correct TWD (Test While Developing) in-browser tests. Use this when writing, reviewing, or modifying TWD test files (*.twd.test.ts).
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 with clear trigger guidance and distinctive identifiers. The main weakness is the lack of specific concrete actions beyond the general 'write, review, modify' - it could benefit from listing specific TWD testing capabilities like element selection, async handling, or assertion patterns.
Suggestions
Add 2-3 specific concrete actions the skill enables, such as 'write browser assertions', 'handle async test flows', or 'create page object patterns' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TWD in-browser tests) and general actions (write, review, modify), but doesn't list specific concrete actions like 'create test fixtures', 'mock browser APIs', or 'assert DOM states'. | 2 / 3 |
Completeness | Clearly answers both what ('teaches AI agents how to write correct TWD in-browser tests') and when ('Use this when writing, reviewing, or modifying TWD test files') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'TWD', 'test', 'writing', 'reviewing', 'modifying', and the specific file pattern '*.twd.test.ts'. Good coverage of how users would reference these tests. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche with the TWD framework name and exact file pattern '*.twd.test.ts'. Unlikely to conflict with general testing skills or other test frameworks. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill document that provides comprehensive guidance for writing TWD tests. The executable code examples and clear workflow patterns are excellent. However, the document is somewhat verbose with explanatory content Claude likely doesn't need, and the monolithic structure could benefit from progressive disclosure to separate reference material.
Suggestions
Remove or condense the 'Key characteristics' and 'Why flow-based?' explanatory sections - Claude understands testing philosophy without the rationale
Extract the 'Module Stubbing with Sinon' and 'Component Mocking' sections into separate reference files (e.g., MOCKING.md) and link to them from the main skill
Condense the 'Common Mistakes to AVOID' section into a tighter checklist format rather than numbered prose
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good code examples, but includes some unnecessary explanation (e.g., the 'Key characteristics' section explaining what SPAs are, the verbose 'Why flow-based?' section). Some sections could be tightened without losing clarity. | 2 / 3 |
Actionability | Excellent actionability with fully executable code examples throughout. Every concept is demonstrated with copy-paste ready code, including imports, mocking patterns, assertions, and a complete test template. The 'Common Mistakes to AVOID' section provides concrete anti-patterns. | 3 / 3 |
Workflow Clarity | Clear workflow with explicit sequencing: mock BEFORE visit, wait for requests, then assert. The standard test template demonstrates the numbered flow (1. Setup mocks, 2. Navigate, 3. Verify, 4. Interact, 5. Assert). The beforeEach cleanup pattern provides validation/reset checkpoints. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear section headers, but it's a monolithic document (~300 lines) that could benefit from splitting advanced topics (component mocking, module stubbing) into separate reference files. No external file references are provided for deeper dives. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- BRIKEV/twd
- Commit
d42316b
- 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.