tdd-workflow

在编写新功能、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），包括单元测试、集成测试和端到端（E2E）测试，覆盖率需达到 80% 以上。

Quality

71%

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 ./.agents/skills/tdd-workflow/SKILL.md

Quality

Content

65%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 abundant executable code and a clear 7-step TDD workflow, but it is padded with generic best-practice lists and basic concept explanations Claude already knows, and it is a monolithic file with no progressive disclosure. Workflow clarity is capped by missing explicit validation/feedback loops.

Suggestions

Trim redundant explanation Claude already knows — remove the 10-item generic 最佳实践 list, the basic test-type descriptions, and the closing "测试不是可选的" manifesto.

Add explicit validation/feedback loops to the workflow: after running tests state "if failing, fix the implementation and re-run" and after coverage state "if below 80%, add tests for the uncovered paths and re-run".

Move the large code-pattern sections (unit/API/E2E patterns, mocking recipes) into reference files under references/ and link to them from SKILL.md to enable progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body pads with concepts Claude already knows — e.g. "务必先编写测试，然后编写代码使测试通过", the 10-item generic 最佳实践 list ("每个测试只做一个断言", "保持测试快速"), and the closing manifesto "测试不是可选的". It is not a 3 because of this redundant explanatory fluff; not a 1 because substantial portions are real executable code rather than a prose wall.	2 / 3
Actionability	It provides copy-paste-ready executable TypeScript/Playwright examples, real bash commands (npm test, npm run test:coverage), a real Jest coverageThresholds JSON block, and concrete Supabase/Redis/OpenAI mock snippets. It is not a 2 because the guidance is genuinely executable and complete rather than pseudocode.	3 / 3
Workflow Clarity	The 7-step TDD workflow is clearly sequenced, but it lacks explicit validation feedback loops — step 5 states tests "现在应该通过" with no "if not, fix and re-run" recovery, and the coverage step does not say what to do below 80%. Per the rubric, missing validation/feedback loops for a process with checkpoints caps this at 2; not a 1 because the sequence itself is clear and present.	2 / 3
Progressive Disclosure	It is a monolithic ~405-line SKILL.md with no references/, scripts/, or assets/ bundles and no external file links; large pattern sections (unit/API/E2E, mocking) that could be separate reference files are all inline. It is not a 3 because nothing is split out and the simple-skill exception (under 50 lines) does not apply; not a 1 because sections are well-organized rather than a wall of text.	2 / 3
	Total	9 / 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.

The description clearly states both what the skill does and when to use it, with concrete capabilities and an explicit Use-when clause in third person. Its main weakness is partial trigger-term coverage and broad triggers that could overlap with general coding skills.

Suggestions

Add broader natural trigger terms (e.g. "write tests", "add test coverage", "TDD") so users phrase the need in more ways.

Sharpen the triggers to reduce overlap with general coding skills — e.g. tie activation specifically to scenarios requiring test coverage enforcement rather than all feature/bug/refactor work.

Dimension	Reasoning	Score
Specificity	"强制执行测试驱动开发（TDD），包括单元测试、集成测试和端到端（E2E）测试，覆盖率需达到 80% 以上" lists multiple concrete actions (enforce TDD across unit/integration/E2E with an explicit 80% coverage target). It is not a 2 because the capability set is comprehensive rather than naming only a domain and a few actions.	3 / 3
Completeness	It explicitly answers both what ("强制执行测试驱动开发...覆盖率需达到 80% 以上") and when ("在编写新功能、修复 Bug 或重构代码时使用此技能"). It is not a 2 because the "when" is an explicit Use-when clause, not merely implied.	3 / 3
Trigger Term Quality	Triggers "编写新功能、修复 Bug 或重构代码" are natural phrases a user would say, but coverage is partial — it is Chinese-only and lacks common English variations such as "write tests", "test coverage", or "add tests". Not a 3 because common natural trigger variations are missing; not a 1 because the stated triggers are genuinely natural rather than jargon.	2 / 3
Distinctiveness Conflict Risk	The TDD-plus-80%-coverage mandate is a fairly distinct niche, but the triggers (new features, bug fixes, refactoring) are broad general coding activities that could overlap with other coding skills. Not a 3 because the triggers are broad; not a 1 because the enforced TDD/coverage requirement is distinctive.	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: xu-xiang/everything-claude-code-zh
Path: .agents/skills/tdd-workflow/SKILL.md
Commit: dfbf946

Reviewed: 28 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.