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

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 known issues

Quality

Content

72%

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

A highly actionable, well-structured reference skill with excellent progressive disclosure and copy-paste-ready examples. Its main weakness is verbosity from redundant inline API listings and a duplicated quick-reference section.

Suggestions

Remove the trailing 'Quick Reference' code block and the 'What's New in This Version' list, which duplicate APIs and frontmatter metadata already shown earlier in the body.

Move the exhaustive Primitives/Complex Types API listings into a reference file, keeping SKILL.md as a lean overview with a few representative examples.

Fix the Installation section where 'bun add zod' is repeated four times and add the npm/pnpm equivalents that were likely intended.

Frame the define -> safeParse -> branch-on-error pattern as one explicit sequenced workflow with a validation checkpoint so the core process is unambiguous.

Dimension	Reasoning	Score
Conciseness	Mostly code-driven rather than explaining concepts Claude already knows, but at ~730 lines it is padded with a duplicate end-of-doc Quick Reference, a repeated 'bun add zod' install block, and inline API-reference material that overlaps the reference files.	2 / 3
Actionability	Densely packed with fully executable, copy-paste-ready TypeScript examples (basic usage, primitives, objects, env-var validation, Express request validation, codecs), matching the executable-code anchor.	3 / 3
Workflow Clarity	The core define-schema -> parse/safeParse -> handle-error sequence is demonstrated across scattered examples rather than framed as an explicit sequenced workflow with validation checkpoints, and no feedback-loop guidance is given for risky operations.	2 / 3
Progressive Disclosure	Six verified reference files are each signaled with section-level 'Load references/X.md' prompts and a consolidated 'When to Load References' decision guide; references are one level deep with easy navigation.	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.

A strong, concrete description that answers both what the skill does and when to use it, with explicit trigger guidance and a distinct niche. It is slightly dense but every clause earns its place.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as 'validating API requests/responses, form data, env vars, configs', 'transforming data', and 'generating JSON Schema for OpenAPI/AI', matching the multiple-specific-actions anchor.	3 / 3
Completeness	States what it does ('TypeScript-first schema validation and type inference') and when to use it via an explicit 'Use for ... or encountering ...' clause, satisfying both what and when with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms users would say ('form data', 'env vars', 'configs', 'API requests/responses') plus problem-state triggers ('missing validation errors, type inference issues, validation error handling problems').	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (TypeScript-first runtime schema validation/type inference) with Zod-specific triggers, making it unlikely to fire for unrelated skills.	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
Commit: c4889f6

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.