CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tdd

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/tdd/SKILL.md
SKILL.md
Quality
Evals
Security

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 delivers a clear, well-sequenced TDD process with strong checklists and an excellent anti-horizontal-slicing section, but it is padded with standard testing exposition and all five of its cross-references point to files missing from the bundle. Fixing the dangling references would raise both navigation and actionability.

Suggestions

Add the referenced bundle files (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) or remove the links, since none of them exist in the bundle and every detailed-guidance pointer currently dead-ends.

Trim the Philosophy section (behavior-vs-implementation testing, good/bad test definitions) to the project-specific diagnostics and move extended examples into tests.md to reduce repetition of concepts Claude already knows.

Consolidate the three separate RED/GREEN loop diagrams (sections 2, 3, and the anti-pattern ASCII) into one, keeping the horizontal-vs-vertical contrast only.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the Philosophy section re-explains behavior-vs-implementation testing that a competent model already knows, and the RED/GREEN loop is diagrammed three times (sections 2, 3, and the anti-pattern ASCII), so it could be tightened.

3 / 5

Actionability

Concrete, directive process guidance is present ("Write ONE test that confirms ONE thing", per-cycle checklists, exact questions to ask the user, "Never refactor while RED"), but there is no example test in the body — examples are deferred to tests.md, which is not in the bundle.

4 / 5

Workflow Clarity

The workflow is clearly sequenced (Planning → Tracer Bullet → Incremental Loop → Refactor) with the RED/GREEN cycle as an explicit validation feedback loop, a per-cycle checklist, and guardrails like "Run tests after each refactor step" and "Never refactor while RED. Get to GREEN first."

5 / 5

Progressive Disclosure

Sections are well-organized and the five links (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) are clearly signaled at relevant points, but none of these files exist in the bundle (no references/, scripts/, or assets/ directories), so every deep-dive pointer dead-ends.

3 / 5

Total

15

/

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 and well-differentiated trigger clause; the main weakness is that the capability statement is a single methodology phrase rather than a concrete list of what the skill does. It stays concise, uses third person, and avoids fluff.

DimensionReasoningScore

Specificity

"Test-driven development with red-green-refactor loop" names the domain and its core loop, but offers only a single methodology phrase as the 'what' rather than several concrete actions, matching anchor 3 rather than 4.

3 / 5

Completeness

The description explicitly answers both what ("Test-driven development with red-green-refactor loop") and when (a four-clause "Use when..." with concrete trigger phrases), matching the top anchor exactly.

5 / 5

Trigger Term Quality

Natural triggers are present ("using TDD", "mentions 'red-green-refactor'", "wants integration tests", "asks for test-first development"), but common phrasings like "write tests first" or "unit tests" are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The TDD/red-green-refactor niche is distinct with specific triggers, but "wants integration tests" could fire for ordinary test-writing requests that overlap a general testing skill, leaving minor conflict risk.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 5 missing

Warning

Total

15

/

16

Passed

Repository

saski/arnesto

Path

.agents/skills/tdd/SKILL.md

Reviewed

Table of Contents

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.