tdd-workflow

在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发，确保单元测试、集成测试和端到端测试的覆盖率超过80%。

Quality

80%

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/zh-CN/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.

The content is highly actionable with concrete, executable code examples and a clearly sequenced TDD workflow, but it is verbose (rehashing concepts Claude knows) and monolithic with no progressive disclosure via separate reference files.

Suggestions

Trim the '核心原则', '最佳实践', and '成功指标' sections to essentials Claude doesn't already know, removing generic TDD platitudes.

Split the large test-pattern and mocking examples into reference files (e.g., references/test-patterns.md) and link to them from SKILL.md to improve progressive disclosure.

Fill the placeholder test blocks (e.g., '// Test implementation', '// Test error handling') with concrete assertions so every example is fully executable.

Dimension	Reasoning	Score
Conciseness	The body is ~440 lines with extensive concrete code, but sections like '核心原则', '最佳实践' (10 generic items), and '成功指标' restate TDD concepts Claude already knows and could be trimmed.	2 / 3
Actionability	Provides multiple fully executable, copy-paste-ready examples (Jest/Vitest unit tests, Next API integration tests, Playwright e2e, Supabase/Redis/OpenAI mocks, coverage config), though a few blocks contain placeholder comments.	3 / 3
Workflow Clarity	The 7-step TDD workflow is clearly sequenced with explicit validation checkpoints (run tests to see them fail, run tests to see them pass, verify 80% coverage) and an implicit fail→implement→pass feedback loop.	3 / 3
Progressive Disclosure	No bundle files exist and the single ~440-line file keeps everything inline; section headers provide structure, but content like test patterns, mocks, and common errors that could be separate reference files is all in one monolithic document.	2 / 3
	Total	10 / 12 Passed

Description

82%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.

The description clearly states what the skill does and when to use it with natural trigger terms, but its capability list is somewhat high-level and its triggers are broad enough to risk overlap with general development skills.

Suggestions

Add more concrete actions to the 'what' portion (e.g., 'generates failing tests first, implements minimal code, then refactors') to raise specificity.

Narrow the 'when' triggers or add a distinguishing qualifier (e.g., 'when a test-first workflow with enforced coverage is required') to reduce overlap with general coding skills.

Dimension	Reasoning	Score
Specificity	Names the TDD domain and concrete elements (enforces TDD, ensures unit/integration/e2e coverage >80%) but the actions are fewer and more abstract than the score-3 example's multiple distinct concrete operations.	2 / 3
Completeness	It explicitly answers both 'what' (enforces TDD, ensures >80% coverage across three test types) and 'when' ('在...时使用此技能' / 'Use this skill when...') with an explicit trigger clause.	3 / 3
Trigger Term Quality	The 'when' clause uses natural terms users actually say — '编写新功能' (write new features), '修复错误' (fix bugs), '重构代码' (refactor code) — giving good coverage of common trigger variations.	3 / 3
Distinctiveness Conflict Risk	The TDD/coverage focus is a recognizable niche, but the triggers (writing features, fixing bugs, refactoring) are broad enough to overlap with general coding skills.	2 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: docs/zh-CN/skills/tdd-workflow/SKILL.md
Commit: 06c5e11

Reviewed: 1 day 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.