et-build

ET build, analyzer, proto export, server startup, and publish workflow. Use when compiling WOW with dotnet build ET.sln, exporting Proto to C#, starting ET.App, publishing, or validating analyzer/build results.

Quality

83%

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

83%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 exceptionally concise and action-oriented with copy-paste commands and a clean one-level-deep reference. The main weakness is the absence of explicit validation/verification checkpoints in the build→publish workflow.

Suggestions

Add an explicit validation checkpoint in '默认动作' (e.g. '编译/导出后用 dotnet build ET.sln 复核结果，失败则定位错误并重试') to support a validate→fix→retry loop for the publish workflow.

In '按需补读', confirm the cross-skill paths ('../et-luban/SKILL.md', '../../../cn.etetet.test/AGENTS.md') resolve at runtime, or mark them as conditional/routing hints to avoid dead references.

De-duplicate the entry-point commands between the body's '优先入口' and references/et-build-commands.md so the body stays a pure overview and the detail file holds the elaboration.

Dimension	Reasoning	Score
Conciseness	The body is lean and list-driven across every section ('何时使用', '不要加载', '默认动作', '优先入口', '按需补读'), assumes Claude's competence, and contains no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	The '优先入口' section gives copy-paste-ready commands for each common case ('dotnet build ET.sln', 'dotnet ./Bin/ET.Proto2CS.dll', 'dotnet ./Bin/ET.App.dll --Console=1', 'pwsh -ExecutionPolicy Bypass -File ./Scripts/Publish.ps1') and the '默认动作' rules are concrete guardrails.	5 / 5
Workflow Clarity	A sequence is present (compile → export proto → start server → publish) with prep guardrails ('运行服务器前先清理旧 Logs/', '必须在 Unity 项目根目录启动'), but the body lacks explicit validate→fix→retry checkpoints, and publish/log-clearing are batch/destructive-style operations where missing verification caps the score at 3.	3 / 5
Progressive Disclosure	A clear, lean overview points to a real one-level-deep bundle file ('references/et-build-commands.md') with well-signaled descriptions, but two cross-skill references ('../et-luban/SKILL.md', '../../../cn.etetet.test/AGENTS.md') lie outside the bundle and cannot be verified, keeping it just below a clean 5.	4 / 5
	Total	17 / 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, well-structured description that clearly states both capability and trigger conditions with concrete verbs. It is held back from top marks only by jargon-bound trigger terms and slight generic overlap on 'build'/'publish'.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('build, analyzer, proto export, server startup, and publish') paired with concrete verbs ('compiling…exporting…starting…publishing…validating'), but 'ET build' and 'analyzer' read as domain labels rather than fully spelled-out actions, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers 'what' ('ET build, analyzer, proto export, server startup, and publish workflow') and 'when' with a concrete 'Use when…' clause enumerating trigger scenarios.	5 / 5
Trigger Term Quality	Natural action verbs a developer would say ('compiling', 'exporting Proto to C#', 'starting ET.App', 'publishing', 'validating analyzer/build results') are present, but coverage is project-jargon-bound (WOW, ET.sln) with few synonyms or file-extension variants.	4 / 5
Distinctiveness Conflict Risk	Carves a clear ET build-pipeline niche and contrasts with sibling skills (et-luban, et-code), though 'build'/'publish'/'validating build results' are broad enough to risk minor overlap with closely related et-* 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: egametang/ET
Path: Packages/cn.etetet.harness/skills/et-build/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.