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).
80
75%
Does it follow best practices?
Impact
88%
2.51xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/zod/skills/zod/SKILL.mdQuality
Discovery
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.
This is a strong skill description that clearly identifies its domain (TypeScript schema validation), lists numerous concrete use cases, and includes an explicit 'Use for...' clause with both positive triggers and problem-state triggers. The description is information-dense without being verbose, uses third-person voice correctly, and includes enough specific terminology to be easily distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: validating API requests/responses, form data, env vars, configs, defining type-safe schemas with runtime validation, transforming data, generating JSON Schema for OpenAPI/AI. Very detailed and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (TypeScript-first schema validation and type inference with specific capabilities listed) and 'when' (explicit 'Use for...' clause covering multiple trigger scenarios including problem states like 'missing validation errors' and 'type inference issues'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'schema validation', 'type inference', 'API requests/responses', 'form data', 'env vars', 'configs', 'JSON Schema', 'OpenAPI', 'validation errors', 'type inference issues'. These are terms developers naturally use when needing this kind of tool. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: TypeScript schema validation with runtime type checking. The combination of 'TypeScript-first', 'schema validation', 'type inference', 'runtime validation', and 'JSON Schema' creates a very specific identity unlikely to conflict with other skills. This clearly points to a Zod-like library skill. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive Zod reference manual that excels in actionability with concrete, executable code examples throughout. However, it is significantly too verbose — it reads like library documentation rather than a skill that teaches Claude what it doesn't already know. The progressive disclosure structure is well-designed in theory (with clear reference file pointers and loading guidance) but undermined by inlining too much reference-level content in the main file and having no actual bundle files to back up the references.
Suggestions
Drastically reduce the main file by moving exhaustive API listings (all string validators, all number validators, all object methods) into reference files, keeping only the most common 3-5 patterns inline with brief examples.
Remove the three duplicate 'bun add zod' installation lines and the 'What's New in This Version' marketing section — these waste tokens without adding actionable value.
Cut explanatory text that Claude already knows (e.g., 'Zod is a TypeScript-first validation library that enables developers to define schemas...') and replace with terse, action-oriented headers.
Provide the referenced bundle files (migration-guide.md, error-handling.md, etc.) so the progressive disclosure structure actually functions, and move the detailed API surface content into them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines. It explains concepts Claude already knows (what Zod is, what schemas are, basic TypeScript concepts), includes redundant installation commands (three identical 'bun add zod' lines), lists every possible method exhaustively as a reference manual rather than teaching what Claude doesn't know, and ends with marketing-style 'What's New' bullet points. The quick reference section at the end duplicates much of what was already shown above. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout — from basic usage patterns to environment variables, API request validation, form validation, and partial updates. All code is concrete TypeScript, not pseudocode, with realistic examples. | 3 / 3 |
Workflow Clarity | The skill covers individual API usage well but lacks explicit multi-step workflows with validation checkpoints. The 'When to Load References' section provides good decision guidance, but there's no clear workflow for common multi-step processes like 'setting up Zod in a new project' or 'migrating from v3 to v4' with validation steps — it just points to a reference file. | 2 / 3 |
Progressive Disclosure | The skill references multiple reference files (migration-guide.md, error-handling.md, advanced-patterns.md, type-inference.md, ecosystem-integrations.md, troubleshooting.md) with clear 'When to Load References' guidance, which is good structure. However, no bundle files are provided, so these references don't actually exist. Additionally, the main file itself is bloated with content that should be in those reference files (e.g., exhaustive primitive type listings, full object/array/tuple/enum API surfaces), undermining the progressive disclosure pattern. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (803 lines); consider splitting into references/ and linking | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- secondsky/claude-skills
- Commit
5e92b71
- 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.