zod

TypeScript-first schema validation and type inference. Use for validating API requests/responses, form data, env vars, configs, defining type-safe schemas with runtime validation, transforming data, generating JSON Schema for OpenAPI/AI, or encountering missing validation errors, type inference issues, validation error handling problems. Zero dependencies (2kb gzipped).

Quality

88%

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

77%Weight 40%Scale 1-3

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

A well-structured, code-heavy reference skill with strong actionability and clean progressive disclosure to verified reference files. Its main weaknesses are mild verbosity (a duplicated install block and some restated basics) and the absence of explicit validation/retry checkpoints for its riskier tasks.

Suggestions

Fix the Installation block: 'bun add zod' is repeated three times — replace the duplicates with the actual alternatives (npm/pnpm/yarn) or remove them.

Trim restated basics (e.g. the Overview re-explaining zero-dependency/2kb facts already in frontmatter) and consider condensing the Production Notes and Quick Reference to reduce token cost.

Add an explicit validate-fix-retry checkpoint for higher-risk tasks like v3-to-v4 migration and env-var validation (e.g. run a parse test after migrating a schema, fix and re-run on failure).

Dimension	Reasoning	Score
Conciseness	Mostly efficient code-first reference, but the Installation block repeats 'bun add zod' three times and some sections restate Zod concepts Claude already knows; the long Quick Reference and Production Notes add length that could be trimmed.	2 / 3
Actionability	Body is dominated by executable, copy-paste-ready TypeScript snippets with concrete API calls (z.object, z.discriminatedUnion, safeParse) and direct usage patterns rather than vague direction.	3 / 3
Workflow Clarity	This is a catalog/reference skill rather than a procedural workflow, so the single action is largely unambiguous, but there are no explicit validation checkpoints or fix-retry feedback loops for risky operations like migration or env validation.	2 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references — each 'Load references/X.md' line maps to a verified existing file — and inline quick-reference summaries keep the body focused while details live in the bundle.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 highly specific, third-person description that clearly states capabilities and gives explicit usage triggers tied to concrete problem phrases. It cleanly answers both what the skill does and when to use it with minimal fluff.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions such as 'validating API requests/responses, form data, env vars, configs', 'transforming data', and 'generating JSON Schema for OpenAPI/AI' rather than vague language.	3 / 3
Completeness	Explicitly answers what it does ('TypeScript-first schema validation and type inference') and when to use it via the 'Use for ... or encountering ...' clause, covering both what and when.	3 / 3
Trigger Term Quality	Includes natural terms a user would say — 'API requests/responses', 'form data', 'env vars', 'validation errors', 'type inference issues' — with strong coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The Zod/TypeScript-validation niche with specific triggers (JSON Schema for OpenAPI/AI, validation error handling) is clearly distinct from other skills and unlikely to fire for the wrong one.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (802 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: secondsky/claude-skills
Path: plugins/zod/skills/zod/SKILL.md
Commit: 61cb874

Reviewed: 7 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.