tdd-workflow

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

The body is highly actionable with executable commands and concrete test examples, and the TDD workflow is clearly sequenced with verification checkpoints. Its weaknesses are mild verbosity from restating well-known TDD/testing basics, implicit rather than explicit error-recovery guidance, and a monolithic structure with no progressive disclosure.

Suggestions

Trim restatements of general knowledge — collapse the redundant "Best Practices" list and the textbook TDD-cycle prose, keeping only the SDK-specific guidance, to improve conciseness.

Add an explicit error-recovery feedback loop and a short checklist after the workflow steps (e.g. "If a test fails: read the assertion diff, fix the transformer/AST builder, re-run the specific test path, then re-run coverage") to raise workflow clarity.

Move the detailed testing-pattern examples and the running-tests command reference into separate reference files linked from the overview (e.g. See PATTERNS.md, See COMMANDS.md) to introduce one-level-deep progressive disclosure.

Fix the undefined-variable gap in the notEquals examples (connect transformNotEquals' return value to the asserted generatedSQL) so every code block is truly copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The SDK-specific material (nx commands, file org, SQL assertion patterns) earns its place, but the body restates the standard TDD cycle ("Write minimal code to make tests pass", "Improve code quality while keeping tests green") and general testing best practices ("One behavior per test", "Independent tests") that Claude already knows. It is mostly efficient but could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands (e.g. "npx nx test meerkat-core --testPathPattern=\"not-equals\"", "--coverage", "--watch") and concrete Jest test blocks with real assertions. A minor undefined-variable gap (generatedSQL in one example) is a small blemish rather than pseudocode or substantial incompleteness.	3 / 3
Workflow Clarity	The 6-step TDD sequence is clear with verification checkpoints (expect tests to fail, re-run, verify coverage), but there is no explicit error-recovery feedback loop (what to do when a test fails) and no checklist. Checkpoints are present but error recovery is implicit rather than spelled out.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers and code blocks, but the skill is a monolithic single file (well over 50 lines) with no external references or signaled navigation, and content such as the detailed testing patterns and the running-tests command reference could be split out. It is structured but not progressively disclosed.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 specific to a clear niche and names concrete tooling, but it omits an explicit "Use when..." trigger clause and relies on somewhat technical terms, leaving all dimensions at the mid level. Adding natural trigger phrasing and common keyword variations would raise it.

Suggestions

Append an explicit trigger clause, e.g. ".Use when writing or fixing tests for the Meerkat SDK, adding filter operators/transformers, or working with Cube-to-DuckDB SQL generation." to satisfy the 'when' half of completeness.

Broaden trigger terms with natural variations users would say ("write tests", "unit tests", "SQL generation tests", "filter operators") rather than only tooling names like @swc/jest and Nx monorepo.

Lead with a concrete action list (e.g. "Write failing tests first, implement filter transformers and AST builders, verify generated SQL") to move specificity from naming a workflow to listing multiple concrete actions.

Dimension	Reasoning	Score
Specificity	It names a concrete domain and specific tooling ("TDD workflow for Meerkat SDK — Jest with @swc/jest, Nx monorepo, SQL AST testing patterns"), but conveys a single workflow concept plus tools rather than listing multiple discrete concrete actions. It is not vague (so not 1) but is not comprehensive in multiple specific actions (so not 3).	2 / 3
Completeness	It clearly states WHAT the skill does (TDD workflow with specific tooling) but provides no "Use when..." or equivalent explicit trigger guidance for WHEN to use it. Per the rubric, a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Some natural keywords are present (TDD, Jest, tests, SQL) but the description leans technical (@swc/jest, Nx monorepo, SQL AST testing patterns) and omits common variations a user would say. It has relevant keywords but not broad natural coverage.	2 / 3
Distinctiveness Conflict Risk	The "Meerkat SDK" framing pins a niche, but the generic "TDD workflow" lead could still overlap with general testing/TDD skills, and there is no explicit trigger clause to sharpen distinction. It is somewhat specific but not a fully distinct, conflict-proof trigger set.	2 / 3
	Total	8 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: devrev/meerkat
Commit: 8155fdc

Reviewed: 1 day 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.