CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/go-unit-tests

Use for any question or task about Go tests, including quick how-to questions and one table-driven test: t.Run subtests, t.Parallel, helpers, data races that fail in CI (go test -race), fuzz tests, benchmarks and coverage, plus testify, gomock and Ginkgo. Has Go test idioms, CI flags and anti-patterns.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

Quality

Content

86%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.

A well-built knowledge skill: fully executable examples throughout, a clear step sequence backed by an authoring checklist, and properly split, well-signaled one-level-deep reference files. The minor room to improve is trimming the Overview and the duplicated loop-variable note, and adding an explicit verify step for newly authored tests.

DimensionReasoningScore

Conciseness

The body is dense and largely fluff-free with no filler sentences, but the Overview restates conventions Claude already knows ("Go's `testing` package is stdlib - no separate install, no configuration file") and the pre-Go 1.22 loop-variable capture guidance appears both in Step 3 ("capture the loop variable (`tt := tt`)") and again in the Anti-patterns table — minor over-explanation that could be trimmed.

4 / 5

Actionability

Every section supplies complete, copy-paste-ready code and commands — the table-driven TestAdd, "go test -bench=. -benchmem", "go test -fuzz=FuzzAdd -fuzztime=30s", the coverage-gating shell snippet, and the CI YAML — with specific examples covering the common cases end to end. Not the level below (4) because there are no pseudocode or missing-detail gaps anywhere.

5 / 5

Workflow Clarity

Steps 1–9 plus the numbered "Authoring conventions" checklist give a clear sequence with decision checkpoints ("Conflicting signals → stop and ask"), but there is no explicit run-to-verify step (e.g., re-run "go test -run TestXxx" to confirm a newly authored test passes) in the authoring workflow. Not a 3 because the sequence is coherent and checkpoints like the stop-and-ask rule and refuse rules are explicit.

4 / 5

Progressive Disclosure

The SKILL.md keeps the stdlib core inline and splits specialized topics into one-level-deep references that both exist in the bundle (references/ginkgo.md, references/go-mocking.md) and are signaled with explicit trigger conditions ("Ginkgo + Gomega when the project lives in the Kubernetes ecosystem... → references/ginkgo.md"), plus a closing References section — clear overview, easy navigation.

5 / 5

Total

18

/

20

Passed

Description

92%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 opens with an explicit "Use for..." trigger clause and enumerates concrete, Go-specific capabilities and libraries that comprehensively cover the testing domain. Its only weakness is keyword coverage — a few natural synonyms such as "golang", "unit test", and "_test.go" are absent.

DimensionReasoningScore

Specificity

It enumerates concrete capabilities — "t.Run subtests, t.Parallel, helpers, data races that fail in CI (go test -race), fuzz tests, benchmarks and coverage, plus testify, gomock and Ginkgo" — comprehensively covering the Go testing domain. Not a 4 because coverage has no real gaps; the closing clause "Has Go test idioms, CI flags and anti-patterns" is slightly less action-phrased but still concrete.

5 / 5

Completeness

Explicit trigger guidance answers 'when' with concrete phrases ("Use for any question or task about Go tests, including quick how-to questions and one table-driven test"), and the enumerated topics plus "Has Go test idioms, CI flags and anti-patterns" explicitly answer 'what'. The 'Use for...' clause is present, so no cap applies.

5 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would actually say ("Go tests", "table-driven test", "fuzz tests", "benchmarks and coverage", "testify", "gomock", "Ginkgo", "go test -race"), but a few natural variations are missing — "golang", "unit test", and the "_test.go" suffix. Not a 5 because the top anchor expects synonyms/extensions; not a 3 because most common phrasings are present.

4 / 5

Distinctiveness Conflict Risk

The description is tightly scoped to Go testing via distinctive terms ("t.Run subtests", "go test -race", "gomock", "Ginkgo"), giving it a clear niche with minimal risk of triggering for non-Go or non-testing skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

On this page