test

Run unit tests, integration tests, or slow integration tests matching CI. Use to validate changes before submitting a PR.

1.13x

Quality

90%

Does it follow best practices?

Impact

100%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

96%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.

An exemplary command-reference skill: fully executable commands for every usage tier, useful CI context, and clean section organization. The only weakness is redundant, stale-prone JDK/OS detail repeated across sections and the summary table.

Suggestions

Remove the per-section "CI runs this on..." JDK/OS lines and keep only the CI reference table — the matrix is currently stated four times, and consolidating it trims tokens and leaves one place to update when the CI matrix changes.

Consider noting that JDK/OS matrix details come from .github/workflows/skywalking.yaml and deferring exact versions to that file, reducing stale-prone version numbers in the skill body.

Dimension	Reasoning	Score
Conciseness	The body is efficient — commands, tables, and short prose with no concept explanations — but the JDK/OS matrix is stated redundantly (per-section "CI runs this on..." lines plus the CI reference table), and those version numbers are time-sensitive details that will go stale, fitting the 'efficient; minor instances that could be trimmed' anchor rather than the lean 5.	4 / 5
Actionability	Every argument variant has a fully executable, copy-paste-ready Maven command, including single-module unit and integration recipes with -pl; the naming-convention and tagging tables give concrete rules, matching the 'fully executable; covers the common cases' anchor.	5 / 5
Workflow Clarity	This is a simple single-purpose skill where each argument maps to one unambiguous command, satisfying the simple-skill exception; it even includes a failure-handling checkpoint ("if a test fails locally, investigate rather than relying on retries") and no destructive or batch operations require additional validation.	5 / 5
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ absent) and the ~80-line body is appropriately self-contained with well-organized sections and a clear header structure; per the simple-skill exception, well-organized sections alone merit a 5 since no external references are needed.	5 / 5
	Total	19 / 20 Passed

Description

83%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.

A strong description: it states concrete, tiered actions and includes an explicit use clause with a concrete trigger ("before submitting a PR"). The main gaps are missing synonyms and the broader set of test-running variants covered in the body.

Dimension	Reasoning	Score
Specificity	"Run unit tests, integration tests, or slow integration tests" names the domain and several concrete actions; it is not comprehensive since module-scoped runs and other variants are only covered in the body, matching the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	It explicitly answers both: what — "Run unit tests, integration tests, or slow integration tests matching CI" — and when — "Use to validate changes before submitting a PR", a concrete trigger phrase matching the anchor-5 example's structure; it is not 4 because the when-clause is explicit rather than needing more specificity.	5 / 5
Trigger Term Quality	Terms "unit tests", "integration tests", "tests", "validate changes", and "PR" are phrases users naturally say, giving good coverage; it misses common variations like "run the tests", "test suite", or naming the build tool, so it fits the 'good coverage; a few natural terms missing' anchor rather than the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	"matching CI" and the three-tier test framing carve out a distinct niche, but a generic "run the tests" request could also plausibly route to other test-related skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict 5.	4 / 5
	Total	17 / 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: apache/skywalking
Path: .claude/skills/test/SKILL.md
Commit: 0a01d89

Reviewed: 5 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.