tdd-workflow

TDD workflow for Meerkat SDK — Jest with @swc/jest, Nx monorepo, SQL AST testing patterns.

Quality

60%

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 ./.claude/skills/tdd-workflow/SKILL.md

Quality

Content

67%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 is a well-structured, genuinely actionable TDD workflow with concrete commands, realistic TypeScript test examples, and a clear six-step sequence with verification checkpoints. Its main weaknesses are redundancy between the Core Principles, Step 1, Testing Patterns, and Best Practices sections, a non-runnable detail in the flagship code example, and the absence of explicit error-recovery guidance.

Suggestions

Merge the 'Best Practices' list into 'Core Principles' and the workflow steps to eliminate the duplicated guidance ('Write Tests First', 'Cover edge cases', 'Test SQL output directly').

Fix the Step 1 example so it is copy-paste runnable — derive the asserted value from the call (e.g. const generatedSQL = transformNotEquals('status', ['active'])) or show the full transform call.

Add an explicit error-recovery loop, e.g. 'If a test fails or coverage is below 80%, write additional edge-case tests and re-run before refactoring', to complete the workflow's feedback cycle.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but there is real tightening potential: the 'Best Practices' list restates the 'Core Principles' section ('Write Tests First - Always TDD' duplicates 'Tests BEFORE Code'; 'Cover edge cases' duplicates the coverage requirements), and the Step 1 test block overlaps the 'Testing Patterns' examples. This is more than the minor trimming of anchor 4, but well short of the padding that would justify a 2.	3 / 5
Actionability	The content provides real, executable Nx commands ('npx nx test meerkat-core --testPathPattern="not-equals"') and complete TypeScript test blocks, plus a concrete file-organization tree. It falls short of anchor 5 because the Step 1 example asserts an undeclared 'generatedSQL' variable (the result of 'transformNotEquals' is assigned to 'result' but never used), so that block is not copy-paste runnable as-is.	4 / 5
Workflow Clarity	The six-step TDD sequence is clearly ordered with explicit checkpoints ('Run Tests (They Should Fail)', 'Run Tests Again', 'Verify Coverage'), matching the 'clear sequence with most checkpoints' anchor. It does not reach anchor 5 because there is no explicit error-recovery loop (e.g. what to do when a test fails or coverage falls below 80%), though it clearly exceeds anchor 3 since checkpoints are stated, not implicit.	4 / 5
Progressive Disclosure	This is a single-file skill with no bundle files, organized under clear '##' sections (When to Activate, Workflow Steps, Testing Patterns, File Organization, Running Tests, Common Mistakes, Best Practices) that are easy to navigate. It holds at anchor 4 rather than 5 because at ~190 lines some material (e.g. the extended testing-pattern examples) could arguably live in a reference file, and there is no reference signaling at all.	4 / 5
	Total	15 / 20 Passed

Description

52%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 description is highly distinctive thanks to Meerkat-specific tooling, but it functions as a label rather than a capability statement: it lists no concrete actions and provides no 'Use when...' trigger guidance. Adding explicit actions and activation conditions would substantially improve it.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when writing or fixing tests in the Meerkat SDK, adding filter operators or transformers, or debugging SQL generation.'

Replace the noun-phrase style with concrete third-person actions, e.g. 'Guides writing failing tests first, implementing SQL AST transformers, and verifying 80% coverage via Nx/Jest.'

Include natural trigger terms users would actually say, such as 'unit tests', 'spec', 'test coverage', and 'bug fix in query translation'.

Dimension	Reasoning	Score
Specificity	The description names the domain and tooling ('TDD workflow for Meerkat SDK — Jest with @swc/jest, Nx monorepo, SQL AST testing patterns') but states no concrete actions or verbs — it reads as a title, not a capability list. It is not entirely vague (specific tools are named), so it sits at anchor 2 rather than 1, but it never reaches the 1-2 explicit actions of anchor 3.	2 / 5
Completeness	The 'what' is clear (a TDD workflow for a specific SDK with named tooling), but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which the judging guidelines explicitly cap at 3. It cannot score 4 because the 'when' is entirely absent rather than just weakly implied.	3 / 5
Trigger Term Quality	Terms like 'TDD', 'Jest', and 'testing' are ones users would naturally say, but common variations are missing ('unit tests', 'spec', 'write tests for', 'bug fix', 'coverage'). This matches the 'some relevant keywords but missing common variations' anchor rather than the good-coverage anchor 4.	3 / 5
Distinctiveness Conflict Risk	The description is anchored to a highly specific niche ('Meerkat SDK', '@swc/jest', 'Nx monorepo', 'SQL AST'), making it clearly distinguishable from generic testing or workflow skills with minimal conflict risk. It matches the 'clear niche with distinct triggers' anchor.	5 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: devrev/meerkat
Path: .claude/skills/tdd-workflow/SKILL.md
Commit: ab88ae9

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.