core

Core package for defining schemas, catalogs, and AI prompt generation for json-render. Use when working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video generation.

Quality

83%

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

78%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 dense, actionable API reference with strong executable examples and a thoughtful validation repair loop. Its main weakness is monolithic inlining: the full export catalog and reference detail would benefit from being split into bundled reference files.

Suggestions

Move the Key Exports table and detailed API reference into a bundled references/ file (e.g. REFERENCE.md) and link to it from SKILL.md to improve progressive disclosure.

Add explicit validate-then-proceed feedback loops for batch/state operations beyond autoFixSpec to raise workflow clarity.

Trim the few introductory explanatory sentences (e.g. "Control element visibility with state-based conditions") since the code already conveys the behavior.

Dimension	Reasoning	Score
Conciseness	The body is largely lean API reference with executable snippets and a dense exports table, assuming Claude's competence; only minor explanatory phrasing like "Control element visibility with state-based conditions" could be trimmed, keeping it below 5.	4 / 5
Actionability	Sections provide copy-paste ready TypeScript with real imports and concrete output shapes (e.g. createSpecStreamCompiler, buildUserPrompt, autoFixSpec), covering the common cases expected at score 5.	5 / 5
Workflow Clarity	Feature sections are well organized and the autoFixSpec repair loop shows explicit validation thinking (withholding lossy fixes until retries exhausted), but other operations lack the feedback-loop checkpoints needed for a 5.	4 / 5
Progressive Disclosure	The ~270-line body has good section headers but inlines the full API reference and a 24-row Key Exports table that belong in separate files, with no external references used; since it far exceeds the simple-skill threshold, this lands at 3 rather than higher.	3 / 5
	Total	16 / 20 Passed

Description

87%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, third-person description that clearly states the package's purpose and gives explicit, concrete usage triggers. Minor room for more comprehensive action coverage and synonyms, but it cleanly answers both what and when.

Dimension	Reasoning	Score
Specificity	"defining schemas, catalogs, and AI prompt generation for json-render" names several concrete actions with only minor coverage gaps, fitting the score-4 anchor rather than the comprehensive list expected for 5.	4 / 5
Completeness	It explicitly answers both what ("Core package for defining schemas, catalogs, and AI prompt generation") and when ("Use when working with @json-render/core..."), matching the score-5 anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	"working with @json-render/core, defining schemas, creating catalogs, or building JSON specs for UI/video generation" offers good natural keyword coverage a developer would say, missing a few synonyms/extensions that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The scoped package name "@json-render/core" and its specific triggers carve a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 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/core/SKILL.md
Commit: 0f6798b

Reviewed: 2 days 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.