config

How to author a kubb.config.ts and pick the right @kubb/plugin-* packages when generating TypeScript from an OpenAPI/Swagger spec. Use whenever setting up Kubb, adding a generator, or debugging codegen output.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is dense, actionable, and well-structured with executable config and CLI guidance. It loses points only on mild redundancy in the overview section and an implicit rather than explicit error-recovery loop for destructive generation.

Suggestions

Drop or shrink the 'What It Does' section — its bullets duplicate the 'Shape of a config', 'Available generator plugins', and 'Workflow' sections that follow.

Make the generate-step feedback loop explicit in the Workflow, e.g. 'If typecheck fails or a file is missing, re-run kubb generate --verbose, fix the config/spec, then typecheck again.'

Note that the Related Skills link ../output/SKILL.md does not resolve in this bundle; either add the target skill or remove the row so navigation is not broken.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation padding, but the 'What It Does' bullets restate the later detailed sections and lines like 'The commands wrap the kubb CLI...' add little; could be tightened.	2 / 3
Actionability	Provides an executable defineConfig example, a need→package→import table, and concrete CLI commands (kubb validate/init/generate with --verbose/--watch), all copy-paste ready.	3 / 3
Workflow Clarity	A clear validate→init→generate→typecheck sequence exists with an upfront validation checkpoint, but the error-recovery feedback loop (fail → fix → re-run) for the destructive generate step is only implicit via the --verbose note.	2 / 3
Progressive Disclosure	A single well-organized file with clearly signaled one-level-deep pointers to authoritative external sources (kubb.dev plugin pages, installed Options types) and no nested references; no bundle files exist to misorganize.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 is concise, third-person, and covers concrete capabilities plus an explicit 'Use whenever' trigger clause. It is clearly scoped to Kubb codegen and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'author a kubb.config.ts', 'pick the right @kubb/plugin-* packages', 'generating TypeScript from an OpenAPI/Swagger spec' — matching the score-3 anchor of several specific concrete actions.	3 / 3
Completeness	Explicitly states what the skill does (author config, pick plugins, generate TS from a spec) and when to use it via an explicit 'Use whenever' clause, satisfying both halves.	3 / 3
Trigger Term Quality	'Use whenever setting up Kubb, adding a generator, or debugging codegen output' gives natural trigger phrases a user would actually say, alongside 'OpenAPI/Swagger spec' and 'TypeScript'.	3 / 3
Distinctiveness Conflict Risk	The Kubb/OpenAPI codegen niche with its specific triggers is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: kubb-labs/kubb
Path: tools/claude/skills/config/SKILL.md
Commit: 8349acf

Reviewed: 2 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.