whitebox-e2e

Standardized guide and protocol for authoring robust Whitebox End-to-End tests using the Neural Link Playwright fixture. CRITICAL: Neo.mjs uses Playwright in a highly custom way. Standard Playwright patterns will fail. Triggers: Use this skill before writing, modifying, or executing Playwright End-to-End tests, or if the user asks you to write an E2E test, add end-to-end coverage, or test a component holistically.

Quality

77%

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/whitebox-e2e/SKILL.md

Quality

Content

71%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.

The body is an exemplary lean overview that correctly delegates detail to a real one-level-deep reference file, but because it defers essentially all actionable and workflow content to that reference, its body-level actionability and workflow clarity are only moderate. Adding a minimal inline quick-start snippet and a one-line workflow checkpoint would lift those dimensions without sacrificing conciseness.

Suggestions

Add a 3-4 line inline quick-start snippet (e.g., the `neuralLink.connectToApp` + `queryComponent` assertion pattern) so the body itself is actionable, not only a pointer.

Surface a one-line explicit workflow checkpoint in the body (e.g., 'Read the protocol -> explore live state with Neural Link -> write interactions -> assert engine truth') so the sequence is visible before reading the reference.

Convert the bare reference path into a clearly labeled, relative link (e.g., 'See [whitebox-e2e-protocol.md](references/whitebox-e2e-protocol.md)') to improve navigation signaling.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean (two short paragraphs), assumes Claude's competence, and contains no padding or re-explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	It gives one concrete, executable directive (use `view_file` to read the named reference path), but the actual test-authoring guidance is entirely deferred to the reference file, so the body itself lacks copy-paste-ready code or specific steps.	3 / 5
Workflow Clarity	A clear first step is present (read the protocol before planning assertions or writing code) with an implicit checkpoint (adhere strictly before writing), but the multi-step test-authoring workflow and any validation/feedback loops live only in the reference, so checkpoints are implicit rather than explicit in the body.	3 / 5
Progressive Disclosure	The body acts as a clean overview pointing to a single, real, one-level-deep reference (references/whitebox-e2e-protocol.md, which exists in the bundle), with the reference clearly signaled; it is not a 5 because the pointer is a bare path rather than a labeled link and the rationale is light.	4 / 5
	Total	15 / 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.

The description is strong: it concisely states both what the skill does and explicit trigger conditions, and the Neo.mjs-specific framing makes it largely distinct from generic testing skills. Minor gains are possible by tightening the somewhat generic 'test a component holistically' trigger and adding a few more concrete authoring actions.

Dimension	Reasoning	Score
Specificity	The description names the domain (Whitebox E2E tests via the Neural Link Playwright fixture) and concrete actions (authoring, writing, modifying, executing E2E tests), but stops short of comprehensively listing multiple distinct test-authoring actions like the score-5 anchor.	4 / 5
Completeness	It explicitly answers both 'what' (standardized guide/protocol for authoring robust Whitebox E2E tests using the Neural Link Playwright fixture) and 'when' ('Triggers: Use this skill before writing, modifying, or executing Playwright End-to-End tests, or if the user asks...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	It surfaces several natural phrases a user would say ('write an E2E test', 'add end-to-end coverage', 'test a component holistically', 'Playwright End-to-End tests'), with good coverage but a few common synonyms/extensions missing.	4 / 5
Distinctiveness Conflict Risk	The Neo.mjs/Neural Link framing carves a clear niche with distinct triggers and minimal conflict risk, though the broad phrase 'test a component holistically' could overlap with general testing skills, keeping it just below a 5.	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: neomjs/neo
Path: .agents/skills/whitebox-e2e/SKILL.md
Commit: 210c03c

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.