go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Quality

86%

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

Quality

Content

93%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 compact, highly actionable skill body that assumes competence, gives concrete patterns and a decision table, and offloads full code examples to one clearly-linked reference file. The only minor gap is that general test-writing feedback loops are implicit rather than called out as explicit checkpoints.

Suggestions

Add an explicit "run the test, if it fails fix and re-run" checkpoint to the Execution Steps so the feedback loop is not only present for golden files.

Dimension	Reasoning	Score
Conciseness	The body is lean and imperative ("Prefer table-driven tests", "Use t.TempDir()"); it assumes Claude's competence and never explains what Go or tests are, so every token earns its place.	5 / 5
Actionability	Concrete inline tokens (t.Run(tt.name, ...), t.TempDir(), testing.Short(), teatest.NewTestModel(), -update) plus a decision-gate table and references/examples.md with copy-paste Go code make the guidance fully executable.	5 / 5
Workflow Clarity	Execution Steps 1-6 give a clear sequence with an explicit validation loop for the fragile golden-file op (run -update, inspect diff, rerun without -update), but per-step validation for ordinary test writing is only implicit, leaving a minor gap below the 5 anchor.	4 / 5
Progressive Disclosure	Well-organized sections keep the SKILL.md as an overview, and a single clearly-signaled one-level-deep reference (references/examples.md, verified to exist) holds the bulk examples, giving easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

78%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 tight, well-triggered description that names a specific Go-testing niche with concrete trigger terms and explicit activation guidance. The only gap is that the stated capability ("Apply focused Go testing patterns") is a single generic verb rather than a list of distinct concrete actions.

Suggestions

Expand the action clause from "Apply focused Go testing patterns" to list 2-3 concrete verbs (e.g., "Write table-driven tests, add coverage, test Bubbletea flows, update golden files").

Add a couple of natural synonyms such as "unit tests" or "TUI tests" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the Go-testing domain plus several concrete targets ("go test coverage", "Bubbletea teatest", "golden files"), but the lone action verb "Apply focused Go testing patterns" is generic rather than enumerating distinct actions, so it sits just below comprehensive.	4 / 5
Completeness	Both what ("Apply focused Go testing patterns") and when (explicit "Trigger: ..." clause) are present, satisfying the explicit-trigger requirement that prevents a cap of 3; the what is thinner than the 5-anchor's multi-verb action list.	4 / 5
Trigger Term Quality	"Go tests, go test coverage, Bubbletea teatest, golden files" are natural terms a user would actually say, but common synonyms like "unit tests", "TUI tests", or ".go" are missing.	4 / 5
Distinctiveness Conflict Risk	The Bubbletea/teatest/golden-file niche is clearly scoped with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/go-testing/SKILL.md
Commit: a245f26

Reviewed: 1 day 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.