The body is an exemplar of a lean operational skill: executable commands, an unambiguous decision tree anchored to a machine-readable source of truth, an explicit default case, and a self-maintenance procedure. Nothing is padded, missing, or misplaced.

Dimension	Reasoning	Score
Conciseness	Every section earns its tokens: two commands, a decision rule with a source of truth, the package lists, and a re-derive grep. There is no padding and no explanation of concepts Claude already knows, matching the lean-and-efficient anchor exactly.	5 / 5
Actionability	"yarn test packages/<package-name>" and "yarn test:os packages/<package-name>" are copy-paste ready, the grep re-derivation command is executable, and an explicit default ("If a package is not listed above, run only yarn test") covers the common case fully.	5 / 5
Workflow Clarity	As a simple single-purpose skill the decision procedure is unambiguous: check the package against the listed categories, run the matching command(s), with a source of truth (the storageOps key in ci.config.json) and a recovery step if the list is stale. Running tests is not destructive or batch, so no validation checkpoint is required.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed at this size; per the simple-skill guideline, well-organized sections alone qualify. The package lists are appropriately inline as the fast path, with the grep command as the fallback rather than a buried external reference.	5 / 5
	Total	20 / 20 Passed

Description

66%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 answers both what and when in an appropriately concise way, with natural trigger phrasing around running tests. Its main weaknesses are a thin capability list, missing common trigger variations, and a broad 'running tests' trigger that could conflict with other test-related skills.

Suggestions

Add one or two more concrete capability statements, e.g. 'Runs yarn test or yarn test:os for a single package and picks the right one based on each package's ci.config.json storageOps'.

Broaden trigger terms with natural variations users would say, such as 'unit tests', 'test suite', 'run the tests for a package', or 'yarn test'.

Tighten the when clause to reduce conflict risk, e.g. 'Use when running tests for a package in this monorepo, including OpenSearch (ddb-os) tests for packages that declare ddb-os support.'

Dimension	Reasoning	Score
Specificity	"Shows how to run tests for a single package" and "OpenSearch (ddb-os) tests" name the domain and 1-2 concrete actions, but there is no fuller enumeration of capabilities, matching the anchor for domain plus 1-2 actions rather than several specific actions.	3 / 5
Completeness	Both parts are explicitly present: the what ("Shows how to run tests for a single package, including OpenSearch (ddb-os) tests") and the when ("Use when running tests"). The when clause is explicit but terse and could be more specific about scope (this repo's packages, when ddb-os applies), which is the anchor-4 fit rather than a clearly concrete trigger phrase set.	4 / 5
Trigger Term Quality	"running tests", "tests", "package", and "OpenSearch (ddb-os)" are phrases a user would naturally say, giving good keyword coverage, but common variations like "unit tests", "test suite", or the literal commands (yarn test) are missing, placing it just above the midpoint rather than at comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	"Use when running tests" is a broad trigger that could overlap with any test-related skill, though the "single package" and "OpenSearch (ddb-os)" scoping narrows it; it remains somewhat specific but still able to collide with similar test-runner skills.	3 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: webiny/webiny-js
Path: .claude/skills/tester/SKILL.md
Commit: f0d3d3e

Reviewed: 3 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.