et-test-write

ET test authoring workflow for WOW. Use when writing or modifying ATestHandler tests, choosing test package placement, naming test classes, creating test-only model types, preparing deterministic coroutine-style assertions, handling ObjectWait, constructing test config data, and enforcing EntityRef safety in tests.

Quality

87%

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

86%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 a tight, well-structured ruleset with concrete paths, naming conventions, and explicit do/don't lists that assume Claude's competence. It could be slightly more actionable with a copy-paste test skeleton and slightly clearer on the verify step, but navigation and token efficiency are excellent.

Suggestions

Add a minimal copy-paste ATestHandler coroutine test skeleton showing the awaited-event + EntityRef re-fetch + ErrorCode.ERR_Success pattern, so guidance is fully executable.

Add an explicit 'verify by running with et-test-run' checkpoint at the end of 编写规则 to close the write→run feedback loop.

Note one concrete example of a correctly placed test class name (e.g. gameplay_MyCase_Test) beside rule 7 to make the {PackageType}_{TestName}_Test convention unambiguous.

Dimension	Reasoning	Score
Conciseness	Lean numbered/bulleted lists with no padding and no explanation of concepts Claude already knows — every line ('类名遵守 {PackageType}_{TestName}_Test', '成功返回 ErrorCode.ERR_Success') earns its place and assumes competence.	5 / 5
Actionability	Concrete specifics throughout — exact paths ('Packages/cn.etetet.{被测包}/Scripts/Hotfix/Test/'), a class-naming format, and exact log/error-code methods — but no copy-paste C# test template is provided, leaving a minor gap for an instruction-only skill.	4 / 5
Workflow Clarity	Placement/naming (1–8) and writing rules (1–7) are clearly sequenced with '何时使用'/'不要加载' decision guidance; no explicit validate→fix→retry loop, but test execution is intentionally delegated to et-test-run so validation is external rather than missing.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, and organized into clearly headed sections (何时使用, 不要加载, 落点与命名, 编写规则, 常见错误) with no bundle files present and none needed — well-organized sections suffice for a simple skill.	5 / 5
	Total	18 / 20 Passed

Description

88%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 specific, complete, and uses concrete third-person trigger phrases that clearly convey both what the skill does and when to invoke it. It is held back only slightly by jargon-heavy trigger terms and the absence of an explicit boundary against sibling test skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'writing or modifying ATestHandler tests, choosing test package placement, naming test classes, creating test-only model types, preparing deterministic coroutine-style assertions, handling ObjectWait, constructing test config data, and enforcing EntityRef safety' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' ('ET test authoring workflow for WOW') and 'when' with a concrete 'Use when writing or modifying ATestHandler tests, choosing test package placement...' trigger clause enumerating concrete triggers.	5 / 5
Trigger Term Quality	Natural domain phrases like 'writing or modifying ATestHandler tests' and 'naming test classes' are present and would be said by users, though the terms are heavily jargon-laden (EntityRef, ObjectWait) and lack common synonyms, leaving a few natural variations missing.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and triggers (ATestHandler, test-only model types, EntityRef safety) are highly specific, but the description does not itself draw the boundary against closely related sibling skills (et-test-run, et-tdd), leaving minor overlap risk.	4 / 5
	Total	18 / 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: egametang/ET
Path: Packages/cn.etetet.test/skills/et-test-write/SKILL.md
Commit: ff68102

Reviewed: 10 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.