CtrlK
BlogDocsLog inGet started
Tessl Logo

setup

Wire Ginkgo into a Go package — install the ginkgo CLI and Ginkgo+Gomega, ginkgo bootstrap to generate the suite_test.go (TestXxx/RegisterFailHandler(Fail)/RunSpecs), the package xxx_test convention, dot-import alternatives (aliased import, dsl/* subpackages, --nodot), ginkgo generate, and *testing.T interop via GinkgoT()/GinkgoTB() for testify/gomock. Use when first adding Ginkgo to a repo, bootstrapping a suite, or integrating a *testing.T-based library.

72

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 high-quality setup guide: fully executable commands and code, a clear numbered workflow with a version-verification checkpoint, and clean section structure with well-signaled navigation to sibling skills. The few deductions are for a re-explanation of Go's _test package convention, absent post-bootstrap validation, and inline detail that could live in reference files.

Suggestions

Trim §3 to the consequence (no access to unexported internals; test the external API) and drop the explanation of how Go permits *_test packages in the same directory — that is knowledge Claude already has.

Add a one-line validation after 'ginkgo bootstrap' (e.g. run 'go test ./...' and expect the empty-suite pass) so the workflow has an explicit post-bootstrap checkpoint.

If the skill family grows, move the dot-import alternative catalog (§4) and the *testing.T interop detail (§6) into a reference file, keeping SKILL.md to install → bootstrap → generate.

DimensionReasoningScore

Conciseness

The body is dense and lean — commands and code carry nearly all the weight — but §3 re-explains Go's basic *_test package mechanism ('Go specially permits a *_test package to live in the same directory...') which Claude already knows, fitting 'efficient; minor instances of over-explanation that could be trimmed' rather than the every-token-earns-its-place anchor at 5.

4 / 5

Actionability

Every step is executable and copy-paste ready: 'go install github.com/onsi/ginkgo/v2/ginkgo', 'ginkgo bootstrap', 'ginkgo generate book', a complete generated suite_test.go, and concrete GinkgoT()/gomock snippets covering the common cases — matching the fully executable top anchor.

5 / 5

Workflow Clarity

The numbered 1–6 sequence is coherent with a verification checkpoint ('ginkgo version confirms the install' plus the CLI/go.mod version-drift fix), but there is no post-bootstrap validation step and error-recovery loops are implicit, fitting 'clear sequence with most checkpoints present; minor validation gaps' rather than the explicit-feedback-loop anchor at 5 or the missing-checkpoint anchor at 3.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the ~107-line body is organized into six clearly headed sections with well-signaled one-level pointers to sibling skills ('ginkgo:writing-specs', 'ginkgo:ci', 'Where to go next'), but setup-adjacent detail (dot-import variants, GinkgoT interop) is inlined where it could be split out — 'good structure; most content appropriately placed' rather than the fully split anchor at 5.

4 / 5

Total

17

/

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 comprehensively and concretely states what the skill does, includes an explicit 'Use when...' clause with three natural trigger scenarios, and occupies a distinct niche. The only weakness is a keyword set skewed toward DSL-level jargon that may miss how average users phrase the request.

DimensionReasoningScore

Specificity

The description enumerates six concrete actions — 'install the ginkgo CLI and Ginkgo+Gomega', 'ginkgo bootstrap to generate the suite_test.go', 'the package xxx_test convention', 'dot-import alternatives (aliased import, dsl/* subpackages, --nodot)', 'ginkgo generate', and '*testing.T interop via GinkgoT()/GinkgoTB()' — comprehensive coverage with no meaningful gaps, matching the top anchor rather than the 'minor gaps' anchor at 4.

5 / 5

Completeness

It clearly answers both questions: the 'what' via the enumerated capability list and the 'when' via the explicit trigger clause 'Use when first adding Ginkgo to a repo, bootstrapping a suite, or integrating a *testing.T-based library' with concrete trigger phrases, exactly matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrases a user would say are present ('first adding Ginkgo to a repo', 'bootstrapping a suite', testify/gomock), but the keyword set leans technical ('dsl/* subpackages', '--nodot', 'GinkgoTB()') and omits common user phrasings like 'set up' or 'configure' Ginkgo, fitting 'good keyword coverage; a few natural terms missing' rather than the fully comprehensive anchor at 5 or the generic-keyword anchors below.

4 / 5

Distinctiveness Conflict Risk

The niche is tightly scoped to Ginkgo test-suite setup in Go packages (bootstrap, dot-imports, GinkgoT interop) — triggers are distinct and would not fire for generic Go testing or other framework skills, matching the 'clear niche with distinct triggers' anchor.

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.

Repository
onsi/ginkgo
Reviewed

Table of Contents

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.