bun-test-basics
Use for bun:test syntax, assertions, describe/it, test.skip/only/each, and basic patterns.
80
74%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/bun/skills/bun-test-basics/SKILL.mdQuality
Discovery
72%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has strong trigger terms specific to the bun:test ecosystem and is clearly distinctive from other skills. However, it lacks clarity on what concrete actions the skill performs (does it write tests, debug tests, explain syntax?) and the 'basic patterns' phrase is vague. The 'Use for' clause partially addresses when to use it but doesn't fully separate the what from the when.
Suggestions
Add explicit action verbs describing what the skill does, e.g., 'Generates and explains bun:test syntax' or 'Writes unit tests using bun:test'.
Replace 'basic patterns' with specific examples like 'mocking, lifecycle hooks (beforeEach/afterEach), expect matchers' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (bun:test) and lists some specific elements like assertions, describe/it, test.skip/only/each, but 'basic patterns' is vague and the description doesn't explain what concrete actions the skill performs (e.g., 'generates tests', 'fixes test syntax'). | 2 / 3 |
Completeness | Has a 'Use for...' clause which partially addresses 'when', but the 'what does this do' part is weak — it lists syntax topics but doesn't describe what actions the skill performs (writing tests? fixing tests? explaining syntax?). The 'when' is present but blended with the 'what'. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'bun:test', 'assertions', 'describe/it', 'test.skip', 'test.only', 'test.each'. These are the exact terms a developer would use when asking about Bun testing. | 3 / 3 |
Distinctiveness Conflict Risk | Very clearly scoped to bun:test specifically, with distinct trigger terms like 'bun:test', 'test.skip', 'test.only', 'test.each' that are unlikely to conflict with other testing frameworks or general coding skills. | 3 / 3 |
Total | 10 / 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 solid reference skill with excellent actionability—all examples are executable and well-structured. The main weakness is that it includes substantial inline content (matchers, CLI options) that it also points to in reference files, suggesting the inline content could be trimmed to a few key examples with the rest deferred. The introductory line and common errors table add minor bloat.
Suggestions
Trim the Common Matchers section to the 5-6 most essential matchers and defer the full list to references/matchers.md, which is already referenced.
Remove the introductory sentence ('Bun ships with a fast, built-in, Jest-compatible test runner...') as Claude already knows this context.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with good code examples, but includes some unnecessary elements like the introductory sentence explaining what Bun is and what it supports (Claude knows this). The common matchers section is quite extensive and could be in a reference file rather than inline. The common errors table adds marginal value for things Claude can diagnose. | 2 / 3 |
Actionability | All code examples are fully executable and copy-paste ready with proper imports. CLI commands are concrete and specific. The examples cover the full range of test patterns including parameterized tests, concurrent tests, and matchers with clear syntax. | 3 / 3 |
Workflow Clarity | This is a reference/syntax skill rather than a multi-step workflow, so the single-task clarity standard applies. The content is well-sequenced from quick start through writing tests, modifiers, parameterized tests, and CLI options. For a non-destructive reference skill, this level of organization is sufficient. | 3 / 3 |
Progressive Disclosure | The skill references external files (references/matchers.md, references/cli-options.md) with clear loading criteria, which is good. However, the common matchers section (~40 lines) and CLI options section are quite extensive and arguably should be in those reference files rather than duplicated inline, creating a tension between the inline content and the referenced files. | 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
- secondsky/claude-skills
- Commit
88da5ff
- 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.