test-coverage

MUST be used whenever fixing test coverage for a Flows app to meet the 80% line coverage hard gate. This skill finds AND fixes coverage gaps — it configures tooling, writes missing tests, covers untested paths, and refactors code for testability. It does not just report. Triggers: test coverage, fix tests, write tests, add tests, coverage fix, 80% coverage, coverage gate, missing tests, testability, vitest coverage, jest coverage.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A highly actionable, well-sequenced workflow with strong validation feedback loops, but it is verbose for a single SKILL.md and keeps reference-worthy material (test templates, testability table) inline rather than splitting it into bundle files.

Suggestions

Move the per-file-type test example templates (hooks, services, components) and the testability fix table into separate files under references/, keeping SKILL.md a lean overview with one-level-deep links — this improves both progressive_disclosure and conciseness.

De-duplicate the coverage `exclude` array (shown verbatim in Step 1 and Step 2) and trim the full boilerplate testing-library/react examples, since Claude already knows those patterns.

Tighten Step 3's 'Common fixes' prose and Step 6's refactoring narrative into scannable checklists to reduce token overhead while preserving the validate→fix→retry loops.

Dimension	Reasoning	Score
Conciseness	It is mostly actionable but ~367 lines with full boilerplate test templates (hooks, services, components) Claude already knows and a duplicated coverage `exclude` array shown verbatim in both Step 1 and Step 2, so it could be tightened.	2 / 3
Actionability	It provides executable commands (`pnpm add -D @vitest/coverage-v8`, `npx vitest run --coverage`, the coverage-summary node snippet), concrete config snippets, and copy-paste-ready code examples throughout.	3 / 3
Workflow Clarity	Steps 1–7 are explicitly sequenced ("Work through every step in order") with validation feedback loops such as "Re-run tests after each fix until all tests pass" and "verify it passes" after each change.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a 367-line monolith; the per-file-type example templates and the testability fix table are inline material that could be split into reference files, so structure is present but content that should be separate is not.	2 / 3
	Total	10 / 12 Passed

Description

100%

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, third-person description that states concrete capabilities, gives an explicit when-to-use trigger list, and is scoped to a distinct niche (Flows apps meeting an 80% coverage gate). No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — "configures tooling, writes missing tests, covers untested paths, and refactors code for testability" — matching the anchor for listing several specific concrete actions rather than naming a domain only.	3 / 3
Completeness	It clearly answers both what ("finds AND fixes coverage gaps — it configures tooling, writes missing tests…") and when ("MUST be used whenever fixing test coverage for a Flows app to meet the 80% line coverage hard gate") with an explicit Triggers clause.	3 / 3
Trigger Term Quality	The explicit "Triggers:" list gives natural phrases a user would say ("test coverage", "fix tests", "write tests", "missing tests", "80% coverage", "vitest coverage", "jest coverage"), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	It is scoped to a clear niche ("a Flows app", the "80% line coverage hard gate", vitest/jest) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: cognitedata/builder-skills
Commit: ab7b5f8

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.