tdd-workflows-tdd-green

Implement the minimal code needed to make failing tests pass in the TDD green phase.

Quality

58%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/tdd-workflows-tdd-green/SKILL.md

The canonical home for this skill is tdd-workflows-tdd-green in rmyndharis/antigravity-skills

Quality

Content

63%Weight 40%Scale 1-5

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

The body is well-structured and concise with a clear, checkpointed workflow, but its code examples are illustrative rather than executable and it points to a resource file that is missing. The first Python block also lacks an opening code fence, breaking markdown rendering.

Suggestions

Create the missing 'resources/implementation-playbook.md' (or fix the path) so the Resources reference resolves to a real file.

Make the green-phase code examples self-contained (add imports, the Product/model context) or clearly label them as illustrative, and add an explicit 'if tests fail, fix and re-run' feedback loop to the Instructions.

Fix the malformed first code block by adding an opening ```python fence so the Django snippet renders correctly.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding of concepts Claude already knows, and the green-to-refactor code progressions are the skill's point. Not 5 because the inlined Django and Express refactor ladders could be trimmed, and the first code block's missing opening fence wastes clarity; not 3 because it is efficient rather than noticeably verbose.	4 / 5
Actionability	The four-step Instructions are a concrete process, but the code snippets are illustrative and not standalone-executable (missing imports, Product model, JsonResponse), and 'identify the smallest fix' is generic. Not 4 because the code is not copy-paste ready and key details are missing; not 2 because there is more than minimal high-level hinting.	3 / 5
Workflow Clarity	A clear four-step sequence includes a validation checkpoint (step 3: 'Run tests after each change to confirm progress'), and the operation is not destructive/batch so the cap-3 does not apply. Not 5 because there is no explicit error-recovery feedback loop ('if tests fail, fix and re-run'); not 3 because a checkpoint is explicitly present.	4 / 5
Progressive Disclosure	Section structure (Use when / Do not use / Instructions / Safety / Resources) is reasonable and one reference is clearly signaled, but the referenced 'resources/implementation-playbook.md' does not exist and substantial illustrative code is inlined rather than split out. Not 4 because the reference is a dangling path; not 2 because structure is present rather than minimal.	3 / 5
	Total	14 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 a single concrete action and a recognizable TDD niche, but lacks an explicit 'Use when' trigger clause and has limited keyword coverage. It is adequate but leaves the trigger condition implicit.

Suggestions

Add an explicit trigger clause, e.g. 'Use when moving from red to green in a TDD cycle or when making failing tests pass.'

Broaden trigger keywords with natural synonyms such as 'red-green-refactor', 'test failure', and 'stub implementation' so users' phrasings match.

Optionally name a second concrete action (e.g. 'run tests after each change') to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (TDD green phase) and one concrete action ('Implement the minimal code needed to make failing tests pass'), but coverage is not comprehensive. Not 4 because only a single action is named; not 2 because it does state a concrete action rather than a generic domain.	3 / 5
Completeness	Provides a clear 'what' but no explicit 'Use when...' clause, so the 'when' is only weakly implied by 'TDD green phase'. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3; not 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	Includes relevant terms like 'failing tests', 'TDD green phase', and 'minimal code', but 'TDD green phase' is jargon and common synonyms ('red-green-refactor', 'test failure', 'stub') are missing. Not 4 because keyword coverage is limited rather than good; not 2 because the terms present are on-domain, not generic.	3 / 5
Distinctiveness Conflict Risk	The TDD green-phase niche is mostly distinct with only minor overlap risk against a broader TDD or refactor skill. Not 5 because the trigger is not highly distinctive and could collide with related TDD skills; not 3 because it is more specific than a generic 'works with document files' anchor.	4 / 5
	Total	13 / 20 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/tdd-workflows-tdd-green/SKILL.md
Commit: debb2ec

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.