pleaseai/zod
TypeScript-first schema validation with static type inference - version-aware skill for Zod v3 and v4
75
94%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 an exemplary skill description that excels across all dimensions. It provides specific concrete actions, comprehensive trigger terms that match real developer vocabulary, explicit 'Use when' guidance with multiple scenarios, and is highly distinctive due to the Zod-specific terminology. The description is thorough without being padded, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'build schemas, parsers, refinements, transforms, codecs, and error formatters', plus details about migration between Zod v3 and v4 with specific API changes. | 3 / 3 |
Completeness | Clearly answers both 'what' (answer questions about Zod, help build schemas/parsers/refinements/transforms/codecs/error formatters) and 'when' with explicit 'Use when developers...' clause covering four distinct scenarios plus a comprehensive 'Triggers on' list. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually type, including API names like 'z.object', 'z.string', 'safeParse', 'ZodError', version-specific terms like 'zod/v4', 'zod/v3', and utility terms like 'treeifyError', 'prettifyError'. These are exactly what developers would mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — Zod is a specific library with unique API names. The extensive list of Zod-specific trigger terms like 'z.object', 'ZodError', 'safeParse', 'zod/v4' makes it extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-crafted skill that provides highly actionable guidance for working with Zod across versions. Its greatest strength is the emphasis on verification — never trusting internal knowledge, always checking the installed version, and validating APIs against source before generating code. The content could be slightly more concise by reducing some redundancy between the main body and the referenced files, but overall it's an excellent example of a version-sensitive library skill.
Suggestions
Trim the 'Finding Documentation' section slightly — the multiple fallback paths (ask, node_modules, zod.dev) could be condensed into a prioritized list rather than full code blocks for each approach.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-structured and avoids explaining basic concepts Claude knows (like what Zod is), but it's quite long (~200+ lines) with some redundancy. The version detection table, entry points table, and the 'Critical: Do Not Trust Internal Knowledge' section overlap with content in the referenced files. Some sections like 'Finding Documentation' are thorough but verbose with multiple fallback paths spelled out in full. | 2 / 3 |
Actionability | Excellent actionability throughout — concrete bash commands for version detection, specific `rg` and `fd` commands for symbol verification, executable code snippets for version branching, and precise API mappings (v3 vs v4). The troubleshooting section maps specific error messages to concrete fixes. Every instruction is copy-paste ready. | 3 / 3 |
Workflow Clarity | The skill establishes a clear workflow: (1) detect version, (2) resolve docs via `ask`, (3) verify APIs against source before generating code, (4) typecheck after changes. The 'Critical: Do Not Trust Internal Knowledge' section provides explicit validation checkpoints (verify API names against source/d.ts, cross-reference at matching version pin). The troubleshooting section provides a clear diagnostic flow with fallback grep commands. | 3 / 3 |
Progressive Disclosure | The skill is well-structured as an overview that delegates detailed content to three clearly-signaled reference files: `references/versions.md`, `references/schemas.md`, and `references/parsing-and-errors.md`. References are one level deep, clearly linked with descriptions, and the main body contains just enough context (rules of thumb, quick maps) to be useful without duplicating the reference content. However, no bundle files were provided to verify these references exist. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents