Name: testland/ava-tests
Rating: 73.6 (1 reviews)
Author: testland

testland/ava-tests

Configures and runs AVA - concurrent-by-default JS/TS test framework with isolated test files (each file runs in its own Node process), no globals (explicit `import test from 'ava'`), async-first API, snapshot support, and TypeScript via `@ava/typescript`. Use when AVA is already the chosen framework and the user wants minimal-API parallel-by-default tests, works with libraries (vs apps) where per-file isolation prevents test interference, or is switching from Mocha for per-file process isolation Mocha cannot provide. For choosing between AVA and Mocha, or for Mocha-specific work, use mocha-tests.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%

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

A dense, actionable, code-heavy reference that assumes Claude's competence and avoids concept re-explanation. Its main gaps are the missing run-to-verify checkpoint in the setup workflow and a monolithic single-file structure that keeps detailed reference material inline rather than splitting it into bundle files.

Suggestions

Add an explicit verification step after configuration (e.g. Step 2.5: "Run `npx ava` to confirm tests execute and config is picked up") so the install→configure→run workflow has a validation checkpoint.

Move the detailed assertion-API table and the full hooks/snapshot/exclusive-test reference into a references/ bundle file, keeping SKILL.md as a lean overview that links to it — this improves progressive disclosure toward the 3-anchor.

Fix the garbled anti-pattern row that duplicates itself ("Use `t.true(myArr.includes(x))` instead of `t.true(myArr.includes(x))` with assertion-specific matcher") — the two sides are identical, so the intended contrast is lost.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-forward — it does not explain generic concepts Claude already knows (e.g. what async or a test is) and frames only AVA-specific behavior, fitting the "every token earns its place" anchor rather than the padded 2-anchor.	3 / 3
Actionability	Provides copy-paste-ready, executable guidance throughout — `npm init ava`, full test files, package.json config blocks, and a matcher table with real signatures — matching the fully-executable top anchor.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Step 1 Install through Step 9 CI) but there is no explicit verification checkpoint (e.g. "run `npx ava` to confirm setup"), fitting the 2-anchor "sequence present but checkpoints missing or implicit" rather than the validation-loop 3-anchor.	2 / 3
Progressive Disclosure	Well-organized into sections with one-level-deep external URL references, but ~237 lines of reference material (full assertion table, hooks, config, snapshots) live inline in a single file with no bundle split, matching the 2-anchor "content that should be separate is inline" rather than the split-file 3-anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities, gives explicit "Use when" triggers, and explicitly disambiguates from the sibling mocha-tests skill. It is somewhat dense with parentheticals but every clause carries information rather than fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "Configures and runs AVA", "isolated test files", "no globals", "async-first API", "snapshot support", "TypeScript via @ava/typescript" — matching the multi-action anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly answers both what ("Configures and runs AVA - ...") and when ("Use when AVA is already the chosen framework and the user wants...") with explicit triggers, satisfying the top anchor; it is not the 2-anchor case where "when" is only implied.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "AVA", "Mocha", "TypeScript", "parallel-by-default tests", "switching from Mocha", "test interference" — with good variation rather than the thin single-keyword coverage at 2.	3 / 3
Distinctiveness Conflict Risk	Clear AVA-specific niche with an explicit handoff ("For choosing between AVA and Mocha, or for Mocha-specific work, use mocha-tests"), making wrong-skill triggering unlikely rather than the overlapping 2-anchor case.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

6 days ago

Table of Contents

Discovery Implementation Validation