testing

Use when writing or running tests for this project. Covers unit vs E2E test decisions, test file locations, mock patterns, and project-specific testing conventions. (project)

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is highly actionable with project-specific commands, locations, and a usable decision table, and it cleanly defers methodology to another skill. It loses points for a touch of Claude-known boilerplate, a missing validate-retry loop in the dev workflow, and no progressive disclosure into reference files.

Suggestions

Remove or trim the generic 'Test structure' Arrange/Act/Assert example and the 'use vitest expect() with clear assertions' line — Claude already knows this.

Add a feedback loop to the dev workflow, e.g. after 'npm test': if failures appear, read the failure, fix, and re-run before proceeding to E2E.

Move the full E2E command/filter reference and the writing-template into a references file (e.g. references/e2e.md) and link to it from the body to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, locations, and runtimes, but the 'Test structure' snippet showing describe/it with Arrange/Act/Assert comments explains boilerplate Claude already knows, and the generic assertion guidance adds little.	2 / 3
Actionability	Provides exact runnable commands (npm test, scoped package flags, e2e filters), real import paths, a complete E2E test example, and a decision table — copy-paste ready and specific to the project.	3 / 3
Workflow Clarity	The 'Running Tests During Development' section lists a clear sequence (check -> unit tests -> e2e) with a 'catch type errors first' checkpoint, but there is no validate-and-retry feedback loop for when a step fails, so checkpoints are implicit.	2 / 3
Progressive Disclosure	Single self-contained file with well-organized sections, but at ~110 lines it exceeds the simple-skill threshold and contains inline material (full command lists, code templates, the decision table) that is not split out into any references despite being reference-worthy.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 is specific and well-scoped with an explicit 'Use when' trigger and clear distinctiveness from the general TDD skill. Its main weakness is limited trigger-term coverage — only 'writing or running tests' is offered where richer variations would help matching.

Suggestions

Broaden the trigger to include natural variations users would say, e.g. 'Use when writing or running tests, picking between unit and E2E tests, finding where tests live, or setting up mocks'.

Drop the trailing '(project)' tag from the description — it reads as a metadata artifact rather than capability language and dilutes specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete capabilities — 'unit vs E2E test decisions, test file locations, mock patterns, and project-specific testing conventions' — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what it covers (test decisions, locations, mock patterns, conventions) and when to use it via the 'Use when writing or running tests for this project' trigger clause.	3 / 3
Trigger Term Quality	'writing or running tests' is a natural phrase a user would say, but coverage is thin — common variations like 'unit tests', 'E2E tests', 'test suites', or 'mocking' are absent from the trigger, leaving some relevant keywords missing.	2 / 3
Distinctiveness Conflict Risk	Scoped to 'this project' with project-specific conventions and explicitly defers generic TDD methodology to another skill, giving it a clear niche unlikely to conflict.	3 / 3
	Total	11 / 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.

Repository: cloudflare/sandbox-sdk
Commit: ebb7be9

Reviewed: 4 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.