tdd

Strict Python TDD workflow using pytest (Red-Green-Refactor).

Quality

72%

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 ./.cursor/skills/tdd/SKILL.md

Quality

Content

55%

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

The body teaches a clear, well-sequenced TDD workflow with good guardrails, but it over-explains concepts Claude knows, uses abstract diagrams instead of executable pytest examples, and critically links out to five bundle files that do not exist.

Suggestions

Create the referenced bundle files (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) or remove the dead links — currently progressive disclosure points to missing files.

Replace the abstract RED/GREEN text diagrams with at least one concrete, executable pytest example showing a failing test becoming a passing one.

Trim the Philosophy/Anti-Pattern exposition of basic TDD concepts; keep only the non-obvious guidance (vertical vs horizontal slicing, behavior-over-implementation tests).

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes competence, but the Philosophy and Anti-Pattern prose is fairly discursive and re-explains TDD/red-green concepts Claude already knows, which could be tightened.	2 / 3
Actionability	Gives a concrete RED→GREEN workflow and per-cycle checklist, but the 'code examples' are abstract text diagrams (test1→impl1) rather than executable pytest code, and the concrete tool (pytest) is named in frontmatter but never shown in the body.	2 / 3
Workflow Clarity	Clear four-step sequence (Planning → Tracer Bullet → Incremental Loop → Refactor) with checkboxes, an explicit 'Never refactor while RED' guard, and 'Run tests after each refactor step' as a validation checkpoint.	3 / 3
Progressive Disclosure	The body signals one-level-deep references (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) but none of these bundle files actually exist in references/, scripts/, or assets/, so the navigation points to nothing.	1 / 3
	Total	8 / 12 Passed

Description

90%

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 second frontmatter description is well-constructed: concise, third-person, with explicit Use-when triggers and natural keywords. Its only weakness is moderate action specificity — it names the methodology and use cases rather than enumerating several distinct concrete capabilities.

Suggestions

Consider folding in one or two more concrete capability verbs (e.g. 'write failing tests, implement minimal code, then refactor') to lift specificity from 'names the loop' to 'lists multiple specific actions'.

The SKILL.md contains two frontmatter blocks; consolidate to a single description to avoid ambiguity about which one is authoritative.

Dimension	Reasoning	Score
Specificity	Names the domain (TDD, red-green-refactor) and the use cases (build features, fix bugs, integration tests) but only names the loop concept rather than multiple distinct concrete actions like the score-3 anchor.	2 / 3
Completeness	Explicitly answers what ("Test-driven development with red-green-refactor loop") and when ("Use when user wants to build features or fix bugs using TDD...") with concrete triggers.	3 / 3
Trigger Term Quality	Strong coverage of natural user phrasing: "build features", "fix bugs", "using TDD", "red-green-refactor", "wants integration tests", "test-first development".	3 / 3
Distinctiveness Conflict Risk	Distinct niche (test-first/TDD methodology) with specific triggers unlikely to fire for unrelated coding skills.	3 / 3
	Total	11 / 12 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: 5 missing	Warning

	Total	15 / 16 Passed

Repository: MODSetter/SurfSense
Path: .cursor/skills/tdd/SKILL.md
Commit: 3b319ce

Reviewed: about 13 hours 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.