common-tdd

Implements a strict Red-Green-Refactor loop to ensure zero production code is written without a prior failing test. Use when: creating new features, fixing bugs, or expanding test coverage.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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

The body delivers a clear, well-checkpointed RGR workflow with good reference navigation, but loses points to repetition across the red-flag/anti-pattern sections and to deferring all executable examples to bundle files. Consolidating the overlapping sections and surfacing at least one inline runnable example would lift conciseness and actionability.

Suggestions

Merge the 'Red Flags', 'Rationalization Prevention', and 'Anti-Patterns' sections into one deduplicated block (and remove the mock-rule duplication between Step 3 and Step 4) to improve conciseness.

Inline one minimal failing-test→passing-code example (or the AAA structure) so the body is self-containedly actionable instead of deferring all code to references.

Move the inline 'Anti-Patterns' content into the existing anti-patterns reference files to avoid duplication and sharpen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude knows TDD basics, but it repeats the same guidance across 'Red Flags', 'Rationalization Prevention', and 'Anti-Patterns', and duplicates mock rules across Step 3 and Step 4, so it could be tightened.	2 / 3
Actionability	Process steps and coverage thresholds are concrete, but all executable detail (AAA code, test-runner commands) is deferred to references with no inline runnable examples, leaving key details out of the body.	2 / 3
Workflow Clarity	The Red-Green-Refactor loop is a clearly sequenced multi-step process with explicit verification at each step, stop-and-restart feedback loops in 'Red Flags', and a closing verification checklist.	3 / 3
Progressive Disclosure	References are real, one level deep, and clearly signaled via inline links and an 'Expert References' block, but inline 'Anti-Patterns' and 'Rationalization Prevention' content overlaps the anti-patterns reference files, so content that should be separate is inline.	2 / 3
	Total	9 / 12 Passed

Description

90%

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 third-person, concise, and explicitly pairs a concrete methodology with a 'Use when' trigger clause, scoring well on completeness, triggers, and distinctiveness. Its only weakness is specificity, since it names one process action rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the concrete Red-Green-Refactor methodology and the zero-production-code-without-failing-test constraint, but lists a single process action rather than multiple specific concrete actions, matching the 'names domain and some actions' anchor.	2 / 3
Completeness	Clearly states what it does ('Implements a strict Red-Green-Refactor loop...') and provides an explicit 'Use when:' clause with concrete triggers, answering both what and when.	3 / 3
Trigger Term Quality	Includes natural terms a user would say — 'failing test', 'Red-Green-Refactor', 'test coverage', 'fixing bugs' — giving good coverage rather than jargon-only phrasing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear TDD niche with distinct triggers (failing test, Red-Green-Refactor, test coverage) unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HoangNguyen0403/agent-skills-standard
Commit: 611f52a

Reviewed: 4 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.