overview

The Ginkgo mental model for writing Go tests — the one idea that explains everything (Ginkgo builds a spec tree at construction time, then runs it) and its consequences for how you write specs, plus spec independence and the node taxonomy. Use this first when you start working with Ginkgo in a project, or to decide how to approach a Ginkgo task. Routes to the other ginkgo:* skills.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/ginkgo/skills/overview/SKILL.md

Quality

Content

71%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-structured orientation skill that efficiently conveys a unifying mental model and cleanly routes to deeper sibling skills. Its main weakness is actionability: it teaches rules and concepts but offers no executable code or commands, which is acceptable for an overview yet leaves concrete execution to the routed skills.

Suggestions

Add one tiny executable snippet (e.g. a minimal Describe/It/BeforeEach shell) so the core pattern is copy-paste ready before routing to ginkgo:writing-specs.

Tighten the intro: the Gomega link and 'Strongly prefer ginkgo over go test' could move to ginkgo:setup to reduce non-essential tokens in the overview.

Show the CLI invocation that runs specs (e.g. `ginkgo` or `ginkgo -p`) once, since the skill repeatedly references running specs but never shows how.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's intelligence (e.g. 'Ginkgo runs your suite in two distinct phases' with no library primer), with only minor padding like the Gomega parenthetical and the CLI preference line that could be trimmed.	4 / 5
Actionability	Guidance is concrete at the conceptual level (named node types, explicit rules like 'declare in the container, initialize in BeforeEach') but contains no executable code or CLI commands beyond passing references; it instructs via rules rather than copy-paste-ready examples.	3 / 5
Workflow Clarity	The two-phase model and its consequences are laid out as a clear, sequenced mental procedure with concrete 'do/don't' rules, though there are no explicit validation checkpoints because the skill is orientation rather than a destructive/batch workflow.	4 / 5
Progressive Disclosure	The body is a concise overview that consistently routes deeper material to sibling ginkgo:* skills (e.g. 'ginkgo:writing-specs', 'ginkgo:decorators') with one-level-deep, clearly signaled navigation; no bundle files exist, and none are needed for this orientation skill.	5 / 5
	Total	16 / 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, well-scoped description that clearly states both purpose and trigger conditions in third person, with concrete conceptual anchors and explicit routing to sibling skills. Minor room to sharpen the 'what' as discrete actions rather than concepts.

Dimension	Reasoning	Score
Specificity	Names the domain (Ginkgo mental model) and several concrete concepts (tree construction vs running, spec independence, node taxonomy, routing to other skills), but is more conceptual than a list of discrete actions, leaving minor gaps in concrete-action coverage.	4 / 5
Completeness	Explicitly answers both 'what' (the one idea and its consequences, spec independence, node taxonomy) and 'when' ('Use this first when you start working with Ginkgo in a project, or to decide how to approach a Ginkgo task').	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('start working with Ginkgo', 'decide how to approach a Ginkgo task') and the framework name itself, though it lacks file-extension-style synonyms; good but not exhaustive keyword coverage.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to Ginkgo and explicitly routes to sibling ginkgo:* skills, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: onsi/ginkgo
Path: plugins/ginkgo/skills/overview/SKILL.md
Commit: f2d0f65

Reviewed: 10 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.