CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

zod-validation-expert

Expert in Zod — TypeScript-first schema validation. Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/zod-validation-expert/SKILL.md

The canonical home for this skill is zod-validation-expert in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 body delivers concrete, near copy-paste-ready Zod patterns with good internal organization, useful best-practice warnings, and a practical troubleshooting section. Its weaknesses are redundancy with Zod knowledge Claude already has, version-ambiguous API snippets, and a monolithic single-file structure that would benefit from splitting integration patterns into reference files.

Suggestions

Split the React Hook Form, Next.js Server Actions, and environment-variable sections into references/ files (e.g., references/rhf.md, references/nextjs.md), keeping SKILL.md as a lean overview with well-signaled links.

Trim foundational sections (primitives, parse vs safeParse) down to non-obvious gotchas only — e.g., keep the `z.coerce.boolean()` "false"/"off" pitfall and drop standard boilerplate.

Pin version-sensitive APIs (note that the two-argument `z.record(key, value)` form is Zod 4, and mark `z.setErrorMap` as the legacy Zod 2/3 approach) or place them in an explicit version-compatibility section.

DimensionReasoningScore

Conciseness

The prose is lean and code-dense, but substantial sections re-teach Zod fundamentals Claude already knows ("Basic primitives", parse vs safeParse mechanics, standard React Hook Form resolver boilerplate). More than minor trimming is possible, so it sits between anchors 3 and 4 rather than clearly at either.

3 / 5

Actionability

Nearly all guidance is executable TypeScript: safeParse narrowing, `.refine` with `path`, coercion in Server Actions, fail-fast env parsing. Minor version-consistency flaws (the two-argument `z.record(z.string(), z.string())` is Zod 4-only; `z.setErrorMap` is legacy API given without version notes) keep it from being fully copy-paste safe.

4 / 5

Workflow Clarity

As a reference skill it is logically sequenced (schema definition → parsing → customization → integrations → best practices → troubleshooting), and the Server Action and safeParse patterns demonstrate validate-then-early-return checkpoints. No explicit multi-step workflow with feedback loops exists, so it does not reach anchor 5.

4 / 5

Progressive Disclosure

Section headers are clear, but ~268 lines of reference content live entirely inline in SKILL.md with no bundle files at all — the integration patterns (React Hook Form, Next.js, tRPC) clearly belong in separate references/ files. Good structure argues against anchor 2; zero content splitting argues against anchor 4.

3 / 5

Total

14

/

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 is specific and highly distinct, naming Zod and concrete capability areas plus three named framework integrations in concise third-person voice. Its main weakness is the complete absence of "when to use" trigger guidance, which both caps completeness and leaves some natural user phrasings (form validation, environment variables) uncovered.

Suggestions

Append an explicit trigger clause, e.g., "Use when writing or debugging Zod schemas, validating form or API input, or validating environment variables."

Mention environment-variable validation and transformations/coercion — both significant body topics currently absent from the description.

Include natural user phrasings like "form validation", "validate API input", and "environment variables" alongside the existing framework names.

DimensionReasoningScore

Specificity

"Covers parsing, custom errors, refinements, type inference, and integration with React Hook Form, Next.js, and tRPC" lists several concrete capability areas plus three named frameworks. Score 5 is not reached because transformations, coercion, and environment-variable validation — all covered in the body — are missing from the description.

4 / 5

Completeness

The "what" is clear (parsing, custom errors, refinements, type inference, framework integrations), but there is no "Use when..." clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is specific rather than vague.

3 / 5

Trigger Term Quality

Good natural keyword coverage: "Zod", "schema validation", "parsing", "type inference", "React Hook Form", "Next.js", "tRPC", "TypeScript". A few natural phrases users would say are missing (e.g., "form validation", "environment variables", "validate API input"), so it does not reach the comprehensive-synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Expert in Zod — TypeScript-first schema validation... React Hook Form, Next.js, and tRPC" carves out a clear niche around one specific library and named integrations, with minimal risk of triggering for unrelated skills.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/AI-Agents-Safe-Coding-Skills/skills/zod-validation-expert/SKILL.md

Reviewed

Table of Contents

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.