output

Import and use Kubb's generated code (types, clients, hooks, schemas, mocks). Use when writing app or test code that consumes a Kubb build.

Quality

66%

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 ./tools/claude/skills/output/SKILL.md

Quality

Content

57%

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

A tight, well-structured instruction skill with specific, actionable guidance and clean sectioning. The main gaps are the absence of any executable example and an implicit regeneration feedback loop rather than an explicit sequenced one.

Suggestions

Add one short executable import example (e.g., importing a generated client and calling a hook) to move actionability toward copy-paste-ready.

Render the regenerate workflow as a numbered loop with the typecheck as an inline checkpoint (edit -> `kubb generate` -> typecheck -> fix -> regenerate) so the feedback loop is explicit.

Cut the meta "What It Does" section and the restating intro line to tighten conciseness further.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not over-explain known concepts, but the meta "What It Does" bullets and the restated intro line ("This skill instructs agents on importing and using the code Kubb generates...") could be trimmed, matching the score-2 anchor of mostly-efficient-but-tightenable.	2 / 3
Actionability	Guidance is concrete with exact paths and keys ("node_modules/@kubb/plugin-<name>/src/types.ts", "output.barrel", the kubb.dev URL) and a clear import rule, but it offers no executable code snippet, so it stops short of the copy-paste-ready score-3 anchor.	2 / 3
Workflow Clarity	There is a numbered "Find what was generated" sequence and an explicit typecheck validation rule, but the regeneration feedback loop (edit spec/config -> regenerate -> typecheck -> fix) stays implicit rather than sequenced with inline checkpoints, fitting the score-2 anchor.	2 / 3
Progressive Disclosure	The ~50-line body is well-organized into clearly labeled sections with no need for external bundle references (none exist), and the only link is a one-level peer-skill pointer, satisfying the scoring-note allowance for score 3 on simple well-organized skills.	3 / 3
	Total	9 / 12 Passed

Description

75%

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 concise, well-targeted description that clearly answers both what it does and when to use it, with a strong Kubb-specific niche. It is held back only by a single combined action and somewhat technical trigger phrasing rather than broad natural keyword coverage.

Suggestions

Add a couple of distinct verbs to broaden the action set (e.g., "Import, call, and mock Kubb's generated code...") to lift specificity toward the score-3 anchor.

Soften trigger phrasing with common user terms such as "generated API client", "generated hooks", or "Kubb mocks in tests" to improve natural keyword coverage.

Dimension	Reasoning	Score
Specificity	"Import and use Kubb's generated code (types, clients, hooks, schemas, mocks)" names the domain and enumerates concrete artifact types, but the action set is essentially one combined "import and use" rather than multiple distinct actions like the score-3 anchor (extract/fill/merge).	2 / 3
Completeness	It explicitly states what ("Import and use Kubb's generated code...") and when ("Use when writing app or test code that consumes a Kubb build."), with an explicit "Use when" trigger satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Terms like "Kubb", "generated code", "app or test code", and "Kubb build" are relevant to the niche but lean technical/jargon-heavy and miss common user-facing variations, matching the score-2 anchor more closely than the broad natural-term coverage of a 3.	2 / 3
Distinctiveness Conflict Risk	The Kubb-specific niche ("Kubb's generated code", "consumes a Kubb build") gives distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	10 / 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/output/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.