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

68

Quality

86%

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%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 tightly structured TDD workflow with concrete good/bad examples, explicit per-phase verification, and an escalation feedback loop. Only minor issues hold it back: slight duplication between the required TODO block and the section headers, and a non-runnable placeholder in the flagship example.

DimensionReasoningScore

Conciseness

Sections are lean and every code example earns its place (e.g., the compact retryOperation good/bad pair). Not 5 because the <required> TODO list partially restates the later RED/GREEN/REFACTOR section headers, and the stray inline <system-reminder> line adds noise that could be trimmed or folded into the list.

4 / 5

Actionability

Provides executable bash commands ("npm test path/to/test.test.ts"), concrete good/bad TypeScript examples, and explicit confirmation checklists. Not 5 because the primary good example depends on an undefined placeholder ("foobar.retryOperation") rather than a runnable snippet, so it is not fully copy-paste ready.

4 / 5

Workflow Clarity

The RED → verify fail → GREEN → verify pass → REFACTOR → verify pass sequence has explicit validation checkpoints at every phase ("Confirm: Test fails (not errors)", "Failure message is expected") and an error-recovery feedback loop ("If you go through three loops without making progress, switch to running .claude/skills/creating-debug-tests-and-iterating"). This matches the top anchor with validation steps, checkpoints, and recovery loops.

5 / 5

Progressive Disclosure

A self-contained, well-sectioned single file with no content that belongs in separate bundle files (no references/scripts/assets exist), and the one external pointer is a clearly signaled escalation path. Per the simple-skill exception, well-organized sections with no external references merit the top score.

5 / 5

Total

18

/

20

Passed

Description

80%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 that explicitly covers both what the skill does and when to use it, with a concrete three-step workflow. Its main weakness is a very broad trigger condition that overlaps with general coding work, and it omits the refactor phase and TDD-specific synonyms users might naturally say.

Suggestions

Narrow the trigger condition from "any feature or bugfix" to situations where tests matter most, or add distinguishing qualifiers, to reduce conflict with other development-workflow skills.

Include natural synonyms such as "TDD", "test-driven development", or "write tests first" in the description so users who name the practice directly will trigger it.

Mention the refactor/cleanup phase of the workflow so the 'what' fully covers the RED-GREEN-REFACTOR cycle the skill actually implements.

DimensionReasoningScore

Specificity

Lists several concrete actions ("write the test first, watch it fail, write minimal code to pass") that clearly define the workflow. Not 5 because the refactor/cleanup step and any mention of code-quality outcomes are absent, leaving minor gaps in coverage of the described workflow.

4 / 5

Completeness

Explicitly answers both: what ("write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first") and when ("Use when implementing any feature or bugfix, before writing implementation code") with concrete trigger phrases. Not 4 because the 'when' clause is fully explicit rather than merely present.

5 / 5

Trigger Term Quality

"implementing any feature or bugfix" and "before writing implementation code" are natural phrases users say when needing this skill. Not 5 because common synonyms like "TDD", "test-driven", and "write the tests first" are missing.

4 / 5

Distinctiveness Conflict Risk

The what is clearly niched to test-first development, but the trigger "Use when implementing any feature or bugfix" fires on virtually every coding task, creating real overlap risk with other development-workflow skills. Not 4 because the trigger breadth is a genuine conflict surface, not a minor one; not 2 because the test-first framing keeps it distinguishable.

3 / 5

Total

16

/

20

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.

Validation — 16 / 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.