CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tdd-workflow

Test-driven development workflow: write a failing test first, watch it fail, implement the smallest change to green, then refactor with 80%+ coverage across unit, integration, and E2E tests. Use when writing a new feature, fixing a bug, refactoring, or when told to write failing tests first.

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 ./skills/tdd-workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%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 core TDD workflow (Steps 0–8) is exceptionally well specified with rigorous validation gates and evidence reporting, and the guidance is largely executable. However, the file is bloated with generic testing knowledge Claude already possesses, and nothing is offloaded to reference files despite the length.

Suggestions

Delete or drastically compress the generic sections Claude already knows: "Best Practices", "Common Testing Mistakes to Avoid", the Button unit-test pattern, and the long generic Playwright example — keep only project-specific conventions.

Move the test patterns (unit/integration/E2E), mocking recipes (Supabase/Redis/OpenAI), and CI/CD examples into reference files (e.g., references/patterns.md, references/mocking.md) and link them from the body, turning SKILL.md into a lean workflow overview.

Complete or remove stub examples like "// Test implementation" and the unfinished database-error integration test so every code example is executable as written.

DimensionReasoningScore

Conciseness

Large sections restate testing knowledge Claude already has — the "Best Practices" list ("Write Tests First", "Arrange-Act-Assert", "Mock External Dependencies"), "Common Testing Mistakes to Avoid", a generic Button unit-test pattern, and a ~50-line generic Playwright example — so several padded sections dilute the genuinely non-obvious workflow steps.

2 / 5

Actionability

Mostly executable: a runner command matrix, an executable package-manager detector script with failure handling, exact commit message formats, and an evidence-report table template; minor gaps remain in stub examples like "// Test implementation" and the unfinished "handles database errors gracefully" test body.

4 / 5

Workflow Clarity

Steps 0–8 are explicitly sequenced with hard validation gates — the RED gate with runtime/compile-time paths and "Do not edit production code until this RED state is confirmed", the GREEN rerun, coverage verification — plus a plan-safety checklist, error-recovery loops, and per-stage checkpoint commit verification.

5 / 5

Progressive Disclosure

The single ~590-line file has clear section headers, but all reference material (test patterns, mocking recipes, mistake catalog, CI examples) is inlined rather than split into separate files, and no bundle files exist to offload it.

3 / 5

Total

14

/

20

Passed

Description

88%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: it concretely describes the TDD cycle with a measurable coverage target and pairs it with an explicit Use-when clause. Trigger coverage is good but misses common phrasings ("unit tests", "test coverage", "TDD"), and the broad development triggers create slight overlap risk with general coding skills.

Suggestions

Add common trigger phrasings such as "unit tests", "test coverage", or "TDD" to the Use-when clause so users who ask in those terms still surface the skill.

Narrow the broadest triggers (e.g., qualify "writing a new feature" with intent like "when the project requires tests") to reduce overlap with general development-workflow skills.

DimensionReasoningScore

Specificity

The description lists the complete concrete cycle — "write a failing test first, watch it fail, implement the smallest change to green, then refactor" — with a quantified "80%+ coverage across unit, integration, and E2E tests"; no generic filler or missing steps.

5 / 5

Completeness

It explicitly answers both questions: the "what" is the full RED/GREEN/refactor cycle with coverage requirements, and the "when" is an explicit "Use when..." clause listing concrete triggering scenarios.

5 / 5

Trigger Term Quality

Natural phrases like "writing a new feature", "fixing a bug", "refactoring", and "write failing tests first" are present, but common user variations such as "unit tests", "test coverage", "add tests", or the "TDD" acronym are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The TDD niche and triggers like "write failing tests first" are clearly distinct, but "writing a new feature, fixing a bug, refactoring" covers essentially all development work, creating minor overlap with general coding-workflow skills.

4 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (591 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

affaan-m/ECC

Path

skills/tdd-workflow/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.