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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/testing/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

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

A dense, high-signal reference: exact commands, locations, decision table, and gotchas, with almost no filler. It falls just short of top marks on actionability (placeholder templates), workflow clarity (no failure-recovery loop), and progressive disclosure (all content inline in a single file).

Suggestions

Trim generic guidance (vitest expect() advice, Arrange/Act/Assert template) — it restates what Claude already knows and dilutes the project-specific signal that makes the skill valuable.

Add an explicit failure-handling step to the development workflow (e.g., what to do when npm run check or npm test fails, and when to re-run E2E after a fix) to close the feedback loop.

Show the real import for createTestSession and a filled-in E2E example instead of placeholder names ("ComponentName", "should do X when Y") so the examples are fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is dominated by lean bullets, exact commands, and a decision table, but a few generic bits could be trimmed ("Use vitest's expect() with clear, specific assertions", the Arrange/Act/Assert template, the "Build trust:" framing).	4 / 5
Actionability	Commands are copy-paste ready including argument-passthrough syntax and single-test filtering, plus a runnable E2E example; minor gaps remain in that the E2E template uses placeholder names and createTestSession is shown without its import path.	4 / 5
Workflow Clarity	"Running Tests During Development" gives a clear check-first sequence (npm run check -> npm test -> test:e2e) with the known-issue note preventing a hang from being misread as failure, but there is no explicit fix-and-retry loop on failure.	4 / 5
Progressive Disclosure	With no bundle files present, all content is inline under clean, well-ordered section headers with no nested references; at ~125 lines it is slightly past the simple-skill range and the E2E pattern detail could live in a separate reference file.	4 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 description: explicit what-and-when structure, natural trigger terms, and clear project scoping. Its only weakness is that the capability list names topics rather than concrete actions and omits a few natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	"Covers unit vs E2E test decisions, test file locations, mock patterns, and project-specific testing conventions" lists several specific coverage areas with only minor gaps (e.g., running commands are absent from the description).	4 / 5
Completeness	The "Covers..." sentence explicitly answers what the skill does, and "Use when writing or running tests for this project" is an explicit, concrete trigger clause answering when.	5 / 5
Trigger Term Quality	"writing or running tests", "unit", and "E2E" are natural phrases users would say, but common synonyms like "testing", "test suite", or the runner name "vitest" are missing.	4 / 5
Distinctiveness Conflict Risk	The "for this project" scope and "(project)" marker carve a distinct project-conventions niche, with only minor overlap risk against general TDD/testing-methodology skills.	4 / 5
	Total	17 / 20 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
Path: .agents/skills/testing/SKILL.md
Commit: 831b8c5

Reviewed: 7 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.