go-testing

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

Quality

78%

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 ./internal/assets/skills/go-testing/SKILL.md

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.

The content is an exemplary lean skill: no padding, a decision table mapping test targets to patterns, sequenced execution steps with a golden-file validation loop, and well-structured progressive disclosure to a verified reference file. The only gaps are minor: no inline code in the body and no general feedback loop beyond golden files.

Suggestions

Inline one minimal teatest or table-driven snippet in the body so the core pattern is executable without opening the reference.

Add a brief failure-recovery step to Execution Steps (e.g. what to do when the narrow package test fails before running the broader suite).

Dimension	Reasoning	Score
Conciseness	The body contains no concept explanations or padding — every line is a rule, gate, or sequenced step, and it references specific APIs (t.TempDir(), testing.Short(), Model.Update()) without explaining them. This matches anchor 5 (lean, assumes Claude's competence) with nothing to trim.	5 / 5
Actionability	Concrete, specific guidance throughout: t.Run(tt.name, ...), -update/-short flags, a target-to-pattern decision table, and an explicit golden-file procedure. Scored 4 rather than 5 because the body itself has no inline code — the copy-paste examples are deferred to references/examples.md (which exists and is complete), leaving minor gaps within the body.	4 / 5
Workflow Clarity	Execution Steps 1-6 are clearly sequenced with an explicit validation loop in step 6 (run with -update, inspect diff, rerun without -update) and an output contract. Not 5 because validation exists only for the golden-file path — there is no general failure-recovery guidance; not 3 because checkpoints are present, not missing.	4 / 5
Progressive Disclosure	The 40-line body keeps rules and decision gates inline while splitting runnable code examples into a single clearly-labeled, one-level-deep reference (references/examples.md), which exists and matches its description. This matches anchor 5 (clear overview, well-signaled references, appropriate split).	5 / 5
	Total	18 / 20 Passed

Description

70%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.

The description has strong, explicit trigger guidance and a distinctive niche, with natural trigger terms. Its main weakness is the vague capability statement 'Apply focused Go testing patterns', which does not convey the concrete actions the skill performs.

Suggestions

Replace 'Apply focused Go testing patterns' with concrete actions, e.g. 'Write table-driven Go tests, manage golden files, and test Bubbletea models with teatest'.

Add common synonym trigger terms such as 'golang' or 'unit tests' to broaden natural-language matching.

Clarify scope to reduce overlap risk, e.g. noting the skill applies when testing Go code specifically, not golden files in other languages.

Dimension	Reasoning	Score
Specificity	The domain is named precisely ('Go tests, go test coverage, Bubbletea teatest, golden files'), but the only stated action is the generic 'Apply focused Go testing patterns'. This sits between anchor 2 (domain named, actions generic) and anchor 3 (1-2 concrete actions); the enumerated capability areas lift it just above pure domain naming.	3 / 5
Completeness	The 'Trigger:' prefix provides explicit when-guidance (so the missing-when cap at 3 does not apply), and 'Apply focused Go testing patterns' answers what. Not 5 because the 'what' lacks concrete actions; anchor 4 (both present, one side could be stronger) is the best fit.	4 / 5
Trigger Term Quality	'Go tests', 'go test coverage', 'teatest', and 'golden files' are natural phrases users would say. Common synonyms like 'golang', 'unit tests', or 'table-driven tests' are missing, matching anchor 4 (good coverage, a few natural terms missing) rather than 5.	4 / 5
Distinctiveness Conflict Risk	'Bubbletea teatest' is highly distinctive, but 'Go tests' could overlap with a general Go development skill and 'golden files' is a pattern used in other languages — minor overlap risk with closely related skills, matching anchor 4 rather than 5.	4 / 5
	Total	15 / 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: d96a5d4

Reviewed: 4 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.