tdd-workflow

Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.

Quality

32%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/tdd-workflow/SKILL.md

Quality

Discovery

22%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is too abstract and principle-focused rather than action-oriented. It names a methodology (TDD) but fails to specify what concrete actions Claude performs or when this skill should be triggered. The lack of a 'Use when...' clause and absence of specific capabilities makes it difficult for Claude to reliably select this skill.

Suggestions

Add concrete actions: 'Guides writing failing tests first, implementing minimal code to pass, then refactoring. Helps structure test cases and maintain test coverage.'

Add explicit trigger guidance: 'Use when the user mentions TDD, test-driven development, writing tests first, RED-GREEN-REFACTOR, or asks for help with a test-first approach.'

Include natural user phrases: 'test first', 'write tests before code', 'failing test', 'make the test pass', 'refactor safely'

Dimension	Reasoning	Score
Specificity	The description uses abstract concepts ('TDD workflow principles', 'RED-GREEN-REFACTOR cycle') without listing concrete actions Claude would perform. It doesn't specify what Claude actually does - write tests, run tests, refactor code, etc.	1 / 3
Completeness	The description only vaguely addresses 'what' (TDD principles) and completely lacks a 'when' clause. There is no explicit guidance on when Claude should select this skill, which per the rubric should cap completeness at 2 maximum, but the 'what' is also weak.	1 / 3
Trigger Term Quality	Contains some relevant keywords like 'Test-Driven Development', 'TDD' (implied), and 'RED-GREEN-REFACTOR' that users familiar with the methodology might use, but misses common variations like 'write tests first', 'unit testing', 'test before code'.	2 / 3
Distinctiveness Conflict Risk	TDD is a specific methodology which provides some distinctiveness, but 'workflow principles' is vague and could overlap with general coding skills, testing skills, or software development methodology skills.	2 / 3
	Total	6 / 12 Passed

Implementation

42%

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

This skill effectively organizes TDD concepts with good visual structure and tables, but fails to provide actionable guidance. It reads more like a reference card explaining TDD philosophy than a skill teaching Claude how to actually implement TDD in practice. The lack of any executable code examples or language-specific test syntax significantly limits its utility.

Suggestions

Add concrete, executable test examples in at least one language (e.g., Python pytest or JavaScript Jest) showing the RED-GREEN-REFACTOR cycle with actual code

Replace conceptual explanations Claude already knows (YAGNI, AAA pattern definitions) with specific commands or patterns unique to this codebase/workflow

Include a validation checkpoint showing how to verify tests are actually failing for the right reason in the RED phase before proceeding to GREEN

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient with good use of tables, but includes conceptual explanations Claude already knows (TDD laws, YAGNI definition, AAA pattern). Some sections like 'When to Use TDD' and 'Test Prioritization' add limited value for an AI that understands these concepts.	2 / 3
Actionability	The skill describes TDD principles abstractly but provides no executable code examples, no concrete test syntax, and no copy-paste ready commands. It tells Claude what TDD is rather than showing how to do it with specific language/framework examples.	1 / 3
Workflow Clarity	The RED-GREEN-REFACTOR cycle is clearly sequenced with a visual diagram, but lacks validation checkpoints or feedback loops. There's no guidance on what to do when tests fail unexpectedly or how to verify the refactor phase didn't break anything beyond 'all tests must stay green.'	2 / 3
Progressive Disclosure	For a conceptual skill of this size (~100 lines), the content is well-organized with clear numbered sections, tables for quick scanning, and logical progression from cycle overview to specific phases to anti-patterns. No external references needed for this scope.	3 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: lchenrique/politron-ide
Commit: 7114206

Reviewed: 29 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.