tdd-guide

Test-first development route for TDD, writing failing tests first, RED -> GREEN -> REFACTOR, and behavior-changing feature/bug/refactor work. Do not use for already-failing test root-cause debugging, test-report packaging, or final completion evidence.

Quality

71%

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 ./bundled/skills/tdd-guide/SKILL.md

Quality

Content

70%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 concise, well-structured, and gives a clear TDD workflow with implicit checkpoints. Its main gap is actionability and workflow robustness: no executable examples and no explicit validate-fix-retry feedback loop for when a step fails.

Suggestions

Add an explicit failure-recovery feedback loop (e.g., 'If a test fails unexpectedly: review assertion, fix, re-run before proceeding to GREEN') to strengthen workflow clarity for a batch-like iterative process.

Include one concrete executable snippet or command (e.g., a sample test command invocation) so guidance is copy-paste ready rather than purely descriptive.

Consider adding a short 'When to stop / acceptance check' checkpoint at COVERAGE to make the validation gate explicit.

Dimension	Reasoning	Score
Conciseness	Lean bullet structure with no padding and no over-explanation of TDD concepts Claude already knows; nearly every token earns its place, sitting just below the leanest anchor due to a few elaborative lines.	4.5 / 5
Actionability	Provides concrete rules and an explicit workflow ('No production code before a failing test', 'Write one failing test for one behavior') but as an instruction skill offers no executable commands or code examples, leaving minor gaps versus copy-paste-ready guidance.	3.5 / 5
Workflow Clarity	RED -> GREEN -> REFACTOR -> COVERAGE is a clearly sequenced multi-step process with implicit checkpoints ('Confirm the failure is expected', 'Keep all tests green'), but it lacks an explicit failure-recovery feedback loop, placing it between listed-steps and clear-checkpoints.	3.5 / 5
Progressive Disclosure	Well-organized into clear sections in under 50 lines with no external references needed; the simple-skill exception applies and structure is strong, just below the top anchor because there is no explicit pointer-based navigation to expand.	4.5 / 5
	Total	16 / 20 Passed

Description

71%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 is well-targeted with concrete what/when guidance and unusually thorough negative routing that sharpens the trigger. It falls just short of the top band on specificity and trigger-term coverage because the action and keyword lists are moderately scoped rather than comprehensive.

Suggestions

Broaden trigger terms with common synonyms users say (e.g., 'unit tests', 'test coverage', 'failing test') to lift trigger-term quality toward the top anchor.

Add one or two more concrete actions (e.g., 'drive design from tests', 'refactor under green tests') to strengthen specificity beyond RED/GREEN/REFACTOR naming.

Dimension	Reasoning	Score
Specificity	Names the domain (TDD, test-first development) and concrete actions (writing failing tests first, RED -> GREEN -> REFACTOR) but the action list is moderately scoped rather than comprehensive, fitting between the anchor for 1-2 concrete actions and several specific actions.	3.5 / 5
Completeness	Explicitly answers both 'what' (test-first development route, RED/GREEN/REFACTOR) and 'when' (feature/bug/refactor work that changes behavior) with concrete trigger phrases, and adds explicit negative-routing; the 'when' is concrete enough to sit just below the top anchor.	4.5 / 5
Trigger Term Quality	Includes natural user-facing terms ('TDD', 'test-first development', 'writing failing tests first', 'RED -> GREEN -> REFACTOR') but misses common synonyms such as 'unit tests' or file extensions, placing it between good keyword coverage and some-relevant-keywords.	3.5 / 5
Distinctiveness Conflict Risk	Clear niche (test-first behavior change) reinforced by explicit negative routing to systematic-debugging and test-report skills, giving minimal conflict risk just short of the strongest anchor.	4.5 / 5
	Total	16 / 20 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/tdd-guide/SKILL.md
Commit: ddcaa2a

Reviewed: 6 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.