CtrlK
BlogDocsLog inGet started
Tessl Logo

tdd

Enforces strict test-driven development -- write a failing test first, implement minimal code to pass, then refactor. Use when implementing a feature, fixing a bug, adding behavior, refactoring, or any time production code will be written or changed. Also use when the user says "write tests", "add tests", "TDD", or "test first". DO NOT TRIGGER for throwaway prototypes, generated code, or config-only changes unless the user explicitly requests TDD.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

Highly actionable and clearly sequenced with strong validation checkpoints and executable examples. The main weaknesses are philosophical padding that could be trimmed and a dangling reference to a missing bundle file.

Suggestions

Trim the argumentative 'Why Order Matters' and excuse-rebuttal tables to the essentials; Claude already understands sunk-cost and regression arguments, so keep only the actionable signal.

Create the referenced testing-anti-patterns.md bundle file (or inline the few anti-pattern bullets) so the reference resolves; if it exists, link it as [testing-anti-patterns.md](testing-anti-patterns.md) to clearly signal the one-level-deep reference.

Consider moving the lengthy 'Recognizing When You've Left TDD' checklist into the testing-anti-patterns reference so the SKILL.md body stays a lean overview pointing to detail.

DimensionReasoningScore

Conciseness

Mostly efficient with actionable diagrams and Good/Bad pairs, but sections like 'Why Order Matters' (four rebuttal paragraphs) and 'Recognizing When You've Left TDD' restate TDD philosophy and argue against excuses that Claude already grasps, so the body could be tightened.

2 / 3

Actionability

Provides complete, executable TypeScript and bash examples ('npm test path/to/test.test.ts') in copy-paste-ready Good/Bad pairs plus a worked bug-fix example, giving concrete instruction rather than abstraction.

3 / 3

Workflow Clarity

Sequences RED -> Verify RED -> GREEN -> Verify GREEN -> REFACTOR with explicit validation checkpoints ('Watch It Fail', 'Watch It Pass') and feedback loops ('Test fails? Fix code, not test'), capped by a verification checklist.

3 / 3

Progressive Disclosure

Section organization is clear, but the single external reference 'read testing-anti-patterns.md in this directory' points to a file that does not exist in the bundle and is not signaled as a proper link, leaving the document monolithic with a dangling reference.

2 / 3

Total

10

/

12

Passed

Description

100%

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 concretely states the workflow, provides natural trigger terms, answers both what and when, and adds negative-scope guidance to avoid conflict. It uses appropriate third-person voice throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions -- 'write a failing test first, implement minimal code to pass, then refactor' -- describing the actual TDD workflow steps rather than a vague domain label.

3 / 3

Completeness

Explicitly answers both what it does (the red-green-refactor cycle) and when to use it ('Use when implementing a feature... Also use when the user says...'), with explicit positive and negative trigger guidance.

3 / 3

Trigger Term Quality

Includes natural terms a user would say -- 'TDD', 'test first', 'write tests', 'add tests' -- alongside activity-based triggers (feature, bug, refactoring), giving strong coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (strict TDD) with distinct triggers and an explicit 'DO NOT TRIGGER for throwaway prototypes, generated code, or config-only changes' clause that sharply reduces misfires.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
shousper/claude-kit
Reviewed

Table of Contents

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.