codegen

Code generation utilities for json-render. Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props for @json-render/codegen.

Quality

96%

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

100%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.

A lean, fully executable codegen reference that pairs each primitive with its expected output and culminates in a composable generator example. It assumes Claude's competence, wastes no tokens on background, and is well-organized for a single-purpose skill with no external references.

Dimension	Reasoning	Score
Conciseness	Every section is executable code plus a one-line output comment (e.g. `// Set { "Card", "Metric", "Button" }`); there is no padding, no explanation of what JSON-render or TypeScript is, and it assumes Claude's competence throughout.	5 / 5
Actionability	Full import blocks, executable calls with inline results for traverseSpec, collectUsedComponents, serializePropValue, serializeProps, and escapeString, plus a complete CodeGenerator interface example and a working generator skeleton make this copy-paste ready across the common cases.	5 / 5
Workflow Clarity	This is a single-purpose API reference (not a multi-step destructive process), so the simple-skill exception applies; usage is cleanly sequenced install → traversal → serialization → types → composition with no ambiguity and no destructive/batch operations requiring validation checkpoints.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the genuine content is under 50 lines with clean section headers, so the simple-skill rule permits a 5 on well-organized sections alone; nothing that belongs in a separate file is forced inline.	5 / 5
	Total	20 / 20 Passed

Description

92%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.

A strong, well-structured description that names a clear niche and concrete capabilities with an explicit "Use when..." clause. The only gap is trigger-term breadth: the keywords are relevant but framework-specific, lacking synonyms or file-extension variants that would broaden natural-language matching.

Dimension	Reasoning	Score
Specificity	Names the json-render codegen domain plus four concrete actions ("generating code from UI specs", "building custom code exporters", "traversing specs", "serializing props"), giving comprehensive coverage of the package's surface.	5 / 5
Completeness	Explicitly answers both "what" ("Code generation utilities for json-render" plus the four actions) and "when" ("Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes several relevant technical triggers a json-render developer would say ("generating code", "building custom code exporters", "traversing specs", "serializing props", "UI specs"), but they are framework-jargon-bound with no synonyms or file extensions, so it falls short of comprehensive score-5 coverage.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to @json-render/codegen and json-render UI specs, a clear niche with distinct triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vercel-labs/json-render
Path: skills/codegen/SKILL.md
Commit: a4d033c

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.