tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

Quality

78%

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 ./.agents/skills/tdd/SKILL.md

The canonical home for this skill is tdd in mattpocock/skills

Quality

Content

77%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.

A tight, well-sequenced TDD workflow with strong checklists and explicit RED/GREEN feedback loops; the main gap is progressive disclosure—three referenced detail files do not exist in the bundle, leaving navigation broken.

Suggestions

Either ship tests.md, mocking.md, and refactoring.md in a references/ bundle or remove the inline links so navigation is not broken.

Trim the Philosophy 'Good tests / Bad tests' section to the non-obvious guidance (the horizontal-slices anti-pattern) and drop the re-explanation of basic test coupling that Claude already knows.

Make the RED/GREEN workflow blocks concrete to the project's test runner (e.g., the actual test command to run) so the steps are executable rather than diagrammatic.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and well-organized, but the Philosophy section re-explains what good vs bad tests are—concepts Claude largely already knows—so a minor trimming opportunity keeps it just below the fully-lean 5.	4 / 5
Actionability	Concrete checklists (Planning, Refactor, Per-Cycle) and explicit RED/GREEN steps give actionable guidance; the RED/GREEN blocks are process diagrams rather than executable code, leaving a minor gap versus copy-paste-ready instructions.	4 / 5
Workflow Clarity	The process is clearly sequenced (Planning → Tracer Bullet → Incremental Loop → Refactor) with explicit validation feedback loops ('Never refactor while RED. Get to GREEN first.') and checklists for complex cycles, matching the top anchor.	5 / 5
Progressive Disclosure	Structure and one-level-deep inline references ([tests.md], [mocking.md], [refactoring.md]) are well-signaled, but no bundle files exist so the referenced detail paths are dangling and the disclosure promise is unfulfilled.	3 / 5
	Total	16 / 20 Passed

Description

78%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.

A strong description with an explicit 'Use when...' clause and natural trigger terms; its only weakness is light specificity, since it states the domain and triggers more than it enumerates concrete test-writing actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Test-driven development') and a couple of activities ('build features or fix bugs test-first'), but does not enumerate multiple concrete test-writing actions, so it sits at the 'domain + 1-2 actions' anchor rather than the comprehensive 4/5.	3 / 5
Completeness	It explicitly states what the skill does ('Test-driven development') and gives an explicit 'Use when...' clause with concrete trigger phrases, matching the top anchor for both what and when.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would actually say are present ('build features or fix bugs test-first', 'red-green-refactor', 'integration tests') with good synonym coverage, missing only a few variations like 'unit tests' or file/extension cues.	4 / 5
Distinctiveness Conflict Risk	The 'red-green-refactor' and 'test-first' triggers carve a clear niche with minimal conflict risk, but 'Test-driven development' has minor overlap with general testing/build skills, placing it just below the fully-distinct 5.	4 / 5
	Total	16 / 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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: coder/agent-tty
Path: .agents/skills/tdd/SKILL.md
Commit: ebff2c2

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.