tdd

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

Quality

58%

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

56%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 content lays out a clear, well-sequenced TDD workflow with useful checklists and inherent RED/GREEN feedback loops, but it spends tokens re-teaching concepts Claude knows, provides no executable pytest examples, and relies on five referenced files that do not exist in the bundle. A duplicated frontmatter block in the body is an additional structural defect.

Suggestions

Provide the referenced bundle files (tests.md, mocking.md, refactoring.md, deep-modules.md, interface-design.md) or remove the broken links so navigation actually works.

Add at least one concrete, executable pytest example (a failing test → minimal implementation → passing test) inline so the guidance is copy-paste ready rather than diagrammatic.

Trim the Philosophy/Anti-Pattern exposition that re-explains general testing concepts Claude already knows, and delete the duplicated frontmatter block stranded in the body.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and gives opinionated methodology guidance (vertical slices, tracer bullets), but the Philosophy and Anti-Pattern sections re-explain what good vs bad tests are — concepts Claude already knows — and a duplicated frontmatter block sits in the body as pure token waste, fitting the 'mostly efficient but includes some unnecessary explanation' anchor.	3 / 5
Actionability	The workflow steps and per-cycle checklist are concrete as a process, but there are no executable pytest examples or commands — the RED/GREEN blocks are diagrams/pseudocode, and actual examples are deferred to referenced files (tests.md, mocking.md) that do not exist, matching the 'some concrete guidance but incomplete; pseudocode instead of executable code' anchor.	3 / 5
Workflow Clarity	Planning, Tracer Bullet, Incremental Loop, and Refactor are clearly sequenced with RED/GREEN gates, multiple checklists, and 'Run tests after each refactor step' as an explicit checkpoint; it stops short of 5 because there is no explicit error-recovery guidance when a test fails unexpectedly or a refactor breaks something.	4 / 5
Progressive Disclosure	Section structure is reasonable and references are inline-signaled, but every referenced file (tests.md, mocking.md, deep-modules.md, interface-design.md, refactoring.md) points to a non-existent bundle file and a duplicate frontmatter block is inlined in the body, so navigation is broken and the content does not reach the 'good structure, references mostly clear' anchor at 4.	3 / 5
	Total	13 / 20 Passed

Description

61%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.

The frontmatter description is specific and uses natural TDD terminology, but it lacks any 'Use when...' trigger clause, which caps completeness at 3 and limits distinctiveness. Notably, a stronger description with explicit triggers exists in a second, duplicated frontmatter block stranded in the body rather than in the canonical frontmatter.

Suggestions

Add an explicit 'Use when...' trigger clause to the canonical frontmatter description (e.g., 'Use when the user wants test-first development, mentions red-green-refactor, or asks for integration tests with pytest').

Merge the stranded second frontmatter description into the single canonical description so the richer trigger terms ('integration tests', 'test-first development') are actually exposed.

Expand the 'what' with one or two more concrete actions (e.g., 'write failing tests, implement minimal code, refactor') to lift specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	The description names its domain and tooling ('Strict Python TDD workflow using pytest (Red-Green-Refactor)') but states only one concrete action — running a TDD workflow — so it matches the 'names domain and 1-2 concrete actions, not comprehensive' anchor rather than the multi-action anchor above.	3 / 5
Completeness	It gives a clear 'what' (a Python TDD workflow using pytest) but has no 'Use when...' clause or equivalent trigger guidance, so per the guideline a missing explicit trigger caps completeness at 3; it does not reach the 'both what AND when' anchor at 4.	3 / 5
Trigger Term Quality	It includes natural terms a user would actually say ('TDD', 'pytest', 'Red-Green-Refactor'), giving good keyword coverage, though common variations like 'test-driven development', 'test-first', and 'integration tests' are absent — fitting the 'good coverage, a few natural terms missing' anchor rather than the comprehensive one.	4 / 5
Distinctiveness Conflict Risk	'Strict Python TDD workflow using pytest (Red-Green-Refactor)' carves a fairly distinct niche with method-specific triggers and only minor overlap with general testing or Python skills, matching the 'mostly distinct; minor overlap risk' anchor rather than the fully-distinct anchor (which expects an explicit 'Use when' trigger).	4 / 5
	Total	14 / 20 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: d96e29d

Reviewed: 8 days 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.