tdd-workflows-tdd-red

Generate failing tests for the TDD red phase to define expected behavior and edge cases.

Quality

62%

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 ./skills/tdd-workflows-tdd-red/SKILL.md

Quality

Content

65%

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 cross-framework examples and validation guidance, but is held back by verbosity from a duplicated prompt template, a fragmented workflow, and inline content that would benefit from being split into reference files.

Suggestions

Consolidate the duplicated test-category guidance between the prompt template and "Edge Case Categories" into one section to cut tokens.

Merge the Instructions and Validation lists into a single numbered workflow with explicit validation checkpoints (generate -> run -> confirm failure reason -> fix -> re-run).

Move the framework-specific patterns and the full TypeScript example into reference files (e.g. framework-patterns.md, example.test.ts) and link to them from SKILL.md to apply progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and is mostly actionable, but the large prompt-template block duplicates guidance (e.g. test categories reappear as "Edge Case Categories") and could be tightened, so it does not reach the lean score-3 anchor.	2 / 3
Actionability	Provides framework-specific executable patterns (jest.fn, pytest fixtures, Go table-driven tests), a complete copy-paste TypeScript example with imports and mocks, and concrete validation steps — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	Steps are listed (Instructions 1-4 and a Validation section with a verify-then-fix loop), but they are split across two fragmented lists with implicit checkpoints rather than one unified sequenced workflow with explicit validation gates.	2 / 3
Progressive Disclosure	It is a well-organized single file with no nested references, but at ~160 lines it exceeds the simple-skill threshold and keeps splittable content (framework patterns, the example) inline instead of pointing to one-level-deep reference files.	2 / 3
	Total	9 / 12 Passed

Description

60%

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 is specific and action-oriented within a clear TDD niche, but omits an explicit "Use when..." trigger clause, leaving both completeness and conflict-risk at the middle level.

Suggestions

Add an explicit trigger clause, e.g. "Use when starting the TDD red phase, writing test-first, or defining edge cases before implementation."

Broaden trigger terms with natural user variations like "red-green-refactor", "test-first", and "write failing tests" to improve keyword coverage.

Reinforce distinctiveness by contrasting the red phase against green/refactor phases directly in the description.

Dimension	Reasoning	Score
Specificity	Names the domain ("TDD red phase") plus multiple concrete actions — "Generate failing tests", "define expected behavior", and "edge cases" — matching the multiple-specific-actions anchor rather than the partial score-2 anchor.	3 / 3
Completeness	Clearly states what (generate failing tests defining behavior/edge cases) but has no explicit "Use when..." trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant natural keywords ("TDD red phase", "failing tests", "edge cases") but lacks common user variations (e.g. "write tests", "test-first", "red-green-refactor"), so it does not reach the full coverage anchor.	2 / 3
Distinctiveness Conflict Risk	The "TDD red phase" niche is specific and unlikely to conflict broadly, but the absence of explicit distinct triggers leaves some overlap with general testing skills, so it sits at the middle anchor.	2 / 3
	Total	9 / 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: rmyndharis/antigravity-skills
Path: skills/tdd-workflows-tdd-red/SKILL.md
Commit: e63f7dd

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.