tdd-workflow

在创建新功能、修复 Bug 或重构代码时使用此技能。强制执行测试驱动开发（TDD），要求包括单元测试、集成测试和 E2E 测试在内的测试覆盖率达到 80% 以上。

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 ./docs/ja-JP/skills/tdd-workflow/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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

A highly actionable, well-sequenced TDD workflow with extensive executable examples and clear validation checkpoints. Its main weaknesses are verbosity from restating well-known concepts and a monolithic structure with no progressive disclosure via reference files.

Suggestions

Trim sections that restate concepts Claude already knows (the 10 generic best practices, the common-testing-errors examples, and the 'test-first' principle explanation) to reduce token cost.

Move the large code-pattern blocks (Supabase/Redis/OpenAI mocks, E2E specs, common-errors examples) into reference files under references/ and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The actionable code blocks earn their place, but the body pads with concepts Claude already knows (the 10 generic best practices, the common-testing-errors section, and the 'test-first' principle restatement), so it is mostly efficient with unnecessary explanation rather than lean.	2 / 3
Actionability	Provides fully executable, copy-paste-ready examples across unit (Jest/Vitest), API integration, Playwright E2E, Supabase/Redis/OpenAI mocks, coverage thresholds, and CI/CD yaml — matching the anchor for specific, executable guidance.	3 / 3
Workflow Clarity	A clearly sequenced 7-step TDD workflow with explicit validation checkpoints (run tests expecting failure, re-run expecting success, then verify 80% coverage), giving the feedback structure the level-3 anchor requires.	3 / 3
Progressive Disclosure	The 400+ line body is well-sectioned but entirely monolithic with no reference files; large blocks that should be split out (mock patterns, E2E specs, common errors) are inline, matching the anchor for content that should be separate being inline.	2 / 3
	Total	10 / 12 Passed

Description

77%Weight 40%Scale 1-3

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 clear, third-person description that states concrete capabilities and an explicit use-when clause. It is slightly weakened by missing testing-oriented trigger terms and broad triggers that could overlap with general development skills.

Suggestions

Add explicit testing-language triggers (e.g. 'write/add tests', 'increase test coverage', 'test my code') so the skill fires when users request testing directly, not only during feature/bug/refactor work.

Tighten the 'when' clause with the TDD-specific framing (e.g. 'Use when the task should follow TDD with ≥80% coverage') to reduce overlap with general coding and refactoring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "强制执行测试驱动开发（TDD）", "要求...测试覆盖率达到 80% 以上" spanning unit, integration, and E2E tests — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (enforces TDD with 80% coverage across three test types) and when ("在创建新功能、修复 Bug 或重构代码时使用此技能") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural dev-context terms ("创建新功能、修复 Bug 或重构代码") but omits common testing-language variations users would say (e.g. "write/add tests", "test coverage"), so it is not the level-3 full coverage.	2 / 3
Distinctiveness Conflict Risk	The TDD + 80% coverage framing is a niche, but the triggers (fixing bugs, refactoring, new features) are broad dev contexts that overlap with general coding skills, so it is not the level-3 clear-distinct-triggers case.	2 / 3
	Total	10 / 12 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: xu-xiang/everything-claude-code-zh
Path: docs/ja-JP/skills/tdd-workflow/SKILL.md
Commit: dfbf946

Reviewed: 2 months 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.