CtrlK
BlogDocsLog inGet started
Tessl Logo

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first

75

Quality

92%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is a well-structured, actionable TDD workflow with strong validation checkpoints and feedback loops. Its only real weakness is mild redundancy between the required TodoWrite block and the expanded phase sections, which keeps conciseness below a perfect score.

Suggestions

Consolidate the '<required>' TodoWrite block and the detailed RED/GREEN/REFACTOR sections, which restate the same workflow; let the sections carry the detail and keep the todo as a terse checklist to remove redundancy.

Tighten the REFACTOR bullet list ('Remove duplication, Improve names, Extract helpers') into a single line, since Claude already knows standard refactorings.

Consider shortening the bad-example annotations or merging each good/bad pair into a single contrastive note to reduce length while preserving the correct-pattern guidance.

DimensionReasoningScore

Conciseness

Mostly efficient with no concept-explanation fluff, but the '<required>' TodoWrite block and the detailed RED/GREEN/REFACTOR sections restate the same workflow, so not every token earns its place; a 3 would require eliminating that redundancy.

2 / 3

Actionability

Provides fully executable TypeScript examples, concrete bash commands ('npm test path/to/test.test.ts'), and specific verification checklists; the good/bad example pairs are copy-paste ready and contrastive.

3 / 3

Workflow Clarity

Clear RED/GREEN/REFACTOR sequence with explicit validation checkpoints ('Verify RED - Watch It Fail', 'Verify GREEN - Watch It Pass'), checklists, and a feedback loop ('three loops without making progress, switch to ...').

3 / 3

Progressive Disclosure

Self-contained single-purpose workflow with no bundle files and no nested references; content is organized into clearly labeled sections with easy navigation, which fits the well-organized-sections allowance for single-purpose skills.

3 / 3

Total

11

/

12

Passed

Description

100%

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 strong: it has an explicit 'Use when' trigger, concrete sequential actions, natural TDD vocabulary, and a clearly distinct niche. It cleanly satisfies the anchor-3 criteria on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'write the test first', 'watch it fail', 'write minimal code to pass' — matching the anchor for several specific concrete actions; not below since it goes well beyond naming only a domain.

3 / 3

Completeness

Explicitly answers both what ('write the test first, watch it fail, write minimal code to pass') and when ('Use when implementing any feature or bugfix'); the explicit 'Use when' clause clears the completeness cap.

3 / 3

Trigger Term Quality

Contains natural phrases users say ('write the test first', 'watch it fail', 'implementing any feature or bugfix') with good coverage; exceeds the single-keyword anchor for 2, though the 'TDD'/'test-driven' abbreviation is absent.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (test-first development) with distinctive triggers unlikely to match other skills; the 'any feature or bugfix' opening is broad but the test-first qualifier unmistakably scopes it to TDD.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
microsoft/FluidFramework
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.