CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

writing-specs

Author good Ginkgo specs — container nodes (Describe/Context/When), subject nodes (It/Specify), setup/cleanup nodes (BeforeEach, JustBeforeEach, AfterEach, DeferCleanup, BeforeSuite/AfterSuite), capturing failure diagnostics before teardown with DeferOnFailure, the "declare in container, initialize in BeforeEach" rule, separating creation from configuration, reusable test helpers with GinkgoHelper()/GinkgoHelperGo(), and By/GinkgoWriter output. Use when writing or reviewing specs or extracting a test helper. Covers the tree-construction-time pitfalls (no assertions/init/loop-capture in container bodies).

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

Exemplary skill body: it assumes prior knowledge, packs every section with Ginkgo-specific rules and pitfalls backed by complete executable Go examples, and cleanly delegates adjacent topics (decorators, timeouts, tables, filtering) to sibling skills with a consistent reference convention. No padding, no basics re-explained, no misplaced content.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence from the first line ("Assumes Ginkgo is wired into the suite (`ginkgo:setup`) and you know the two-phase model") and never explains what Ginkgo or BDD testing is. Every section delivers non-obvious, Ginkgo-specific rules ("Container bodies run once, at tree-construction time", "DeferCleanup... runs in LIFO order"), matching the level-5 anchor 'every token earns its place' rather than level 4, which expects trimmable over-explanation.

5 / 5

Actionability

All examples are real, complete, executable Go — the spec skeleton, the WRONG construction-time example, the JustBeforeEach creation/config split, the DeferCleanup env-restore ("DeferCleanup(os.Setenv, \"MODE\", original)"), the GinkgoHelper and GinkgoHelperGo examples — covering the common cases copy-paste ready. This matches the level-5 anchor; level 4 would imply minor gaps in the examples.

5 / 5

Workflow Clarity

This is a single-task guidance skill (write good Ginkgo specs), and the single action is unambiguous: the content states decisive rules ("Declare shared variables in the container body... Initialize them in BeforeEach", "prefer DeferCleanup", "Prefer it to JustAfterEach + if CurrentSpecReport().Failed()", "Prefer it over the older manual frame-counting"), with ordering made explicit in the setup/cleanup table ("outer→inner", "inner→outer"). Under the simple-skill guideline, unambiguous single-action guidance scores 5; there are no destructive/batch operations that would require validation checkpoints and cap the score.

5 / 5

Progressive Disclosure

No bundle files exist, and none are needed: the body is one coherent, well-sectioned topic that delegates advanced material to sibling skills via clearly signaled one-level-deep references ("→ `ginkgo:decorators`", "→ `ginkgo:timeouts-and-async`", and a 'Where to go next' section). Navigation is easy via consistent headers, matching the level-5 anchor ('well-signaled one-level-deep references... easy navigation'); level 4 would require buried references or content misplaced relative to the split, which is not the case.

5 / 5

Total

20

/

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 enumerates concrete capabilities with actual API names, gives an explicit 'Use when...' trigger clause covering three scenarios, and occupies a clearly distinct niche (Ginkgo spec authoring). The only weakness is mild — trigger coverage omits natural synonyms a user might say, like 'Go test' or 'BDD'.

DimensionReasoningScore

Specificity

The description lists many concrete, named capabilities — "container nodes (Describe/Context/When), subject nodes (It/Specify)", "capturing failure diagnostics before teardown with DeferOnFailure", "reusable test helpers with GinkgoHelper()/GinkgoHelperGo()", "By/GinkgoWriter output" — which matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' rather than the level-4 anchor, which expects minor gaps in coverage.

5 / 5

Completeness

Both questions are explicitly answered: the 'what' is the detailed capability list ('Author good Ginkgo specs — container nodes... reusable test helpers...'), and the 'when' is a concrete trigger clause: "Use when writing or reviewing specs or extracting a test helper." This matches the level-5 anchor (explicit what AND when with concrete trigger phrases) and exceeds level 4, where the 'when' is only loosely specified.

5 / 5

Trigger Term Quality

Good natural keywords: "writing or reviewing specs", "extracting a test helper", "Ginkgo", "test helper" — phrases a user would plausibly say. It falls short of the level-5 anchor ('comprehensive coverage of natural terms including synonyms and file extensions') because common variations like "Go test", "BDD", or "test suite" are absent, and the when-clause relies on the Ginkgo-specific term "specs" rather than broader synonyms.

4 / 5

Distinctiveness Conflict Risk

Ginkgo spec authoring is a clear niche with distinct triggers ("Ginkgo", "specs", "DeferOnFailure", "GinkgoHelper()"), and the scope boundary to sibling skills is implicit but effective ('Assumes Ginkgo is wired into the suite'). Only negligible overlap with a generic Go-testing skill exists, fitting the level-5 anchor 'Clear niche with distinct triggers; minimal conflict risk'.

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

Path

plugins/ginkgo/skills/writing-specs/SKILL.md

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.