et-tdd

ET test-driven development workflow for WOW. Use when implementing features or bug fixes through a complete loop of requirements, test plan, ATestHandler test writing, implementation, dotnet build ET.sln, targeted test execution, regression checks, and AGENTS.md rule updates.

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.

A tight, well-structured orchestration skill that lays out a clear TDD loop with real tooling and good progressive disclosure through on-demand sibling-skill references. Weakest in explicit error-recovery feedback and in delegating actionable code detail to other skills.

Suggestions

Add an explicit feedback/retry branch to 默认动作 (e.g. 'if dotnet build or a test fails, fix and re-run before proceeding') to close the validation loop.

Inline one minimal ATestHandler test skeleton or a copy-paste build+test command pair so the core loop is executable without loading a sibling skill first.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned (何时使用, 不要加载, 默认动作, 按需补读) with terse bullets and no padding or explanation of concepts Claude already knows; every line earns its place.	5 / 5
Actionability	Concrete file and command references ('dotnet build ET.sln', 'Logs/All.log', 'Test.md', 'ATestHandler', 'AGENTS.md') make the steps executable, but it delegates the actual code/test-writing detail to sibling skills rather than including ready-to-run snippets.	4 / 5
Workflow Clarity	The 7-step 默认动作 sequence is clear with explicit validation checkpoints (build, run target tests, regression, check Logs/All.log), but it lacks an explicit error-recovery branch ('if build/test fails, fix and retry') for the loop.	4 / 5
Progressive Disclosure	A short, well-organized skill with clearly signaled one-level-deep on-demand references ('读取 ../et-test-write/SKILL.md', '读取 ../et-test-run/SKILL.md') under a dedicated 按需补读 section; no bundle files are needed and none are missing.	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.

A strong, specific description that names the domain, enumerates the concrete loop stages with real tooling, and provides an explicit 'Use when' trigger. The main gap is the absence of explicit disambiguation against sibling et-* skills and a few natural synonyms.

Suggestions

Add a brief boundary clause to the description (e.g. 'For running existing tests use et-test-run; for writing tests only use et-test-write') to reduce overlap with sibling skills.

Include the synonym 'TDD' or 'write tests first' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full loop—'requirements, test plan, ATestHandler test writing, implementation, dotnet build ET.sln, targeted test execution, regression checks, and AGENTS.md rule updates'—with specific tooling named, matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (the complete TDD loop with enumerated stages) and 'when' ('Use when implementing features or bug fixes through a complete loop of...'), matching the concrete-what-and-when anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('test-driven development workflow', 'implementing features or bug fixes') alongside domain jargon (ATestHandler, dotnet build ET.sln); good coverage but missing a few common synonyms like 'TDD' or 'write tests first'.	4 / 5
Distinctiveness Conflict Risk	The full-loop TDD framing and ET/WOW-specific tooling carve a clear niche, but it does not explicitly disambiguate from closely related sibling skills (et-test-run, et-test-write, et-build) in the description itself, 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-tdd/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.