CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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, executable, well-organized reference: concise code examples with expected outputs and no filler. The main gaps are the stubbed "Building a Custom Generator" example and the absence of any deeper reference files for the full API surface.

Suggestions

Complete the "Building a Custom Generator" example with a fully working generateNextJSProject implementation (actual package.json and page.tsx generation) instead of the '// Generate package.json, component files, main page...' stub with an empty return array.

Move the exhaustive API surface (all traversal/serialization functions and their options) into a references/API.md file and keep only a quick-start subset inline, enabling progressive disclosure for this 113-line skill.

Add a brief validation step to the custom-generator workflow (e.g., asserting every file path in GeneratedFile[] has content before returning) so the one multi-step process has an explicit checkpoint.

DimensionReasoningScore

Conciseness

The body is lean and code-first: every section is a short code block with output comments (e.g., "// Set { \"Card\", \"Metric\", \"Button\" }") and zero explanation of concepts Claude already knows. It matches anchor 5 — every token earns its place; not a 4 because there are no padded passages to trim.

5 / 5

Actionability

Most examples are executable and show expected return values (e.g., serializeProps producing 'title="Dashboard" columns={3} disabled'), matching anchor 4. It is not a 5 because the "Building a Custom Generator" example is a stub — "// Generate package.json, component files, main page..." with an empty files array — leaving the culminating use case incomplete.

4 / 5

Workflow Clarity

As a single-purpose utility reference with unambiguous, well-separated sections, it largely satisfies the simple-skill exception, matching anchor 4. It falls short of 5 because the one multi-step activity it introduces (building a custom generator) is presented without a sequenced process or validation checkpoints, and above 3 because what is written is fully coherent and gap-free at the section level.

4 / 5

Progressive Disclosure

Sections are clearly organized and appropriately sized for a small library, matching anchor 4 ("most content is appropriately placed"). It is not a 5 because at ~113 lines — over the 50-line simple-skill threshold — the full API reference is inlined in SKILL.md with no one-level-deep reference files for deeper detail.

4 / 5

Total

17

/

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 description: concrete actions, an explicit and well-formed "Use when..." clause, and a distinct niche anchored to the json-render ecosystem. The only minor weakness is slightly incomplete keyword coverage (missing common synonyms such as "codegen" or framework-specific exporter terms).

DimensionReasoningScore

Specificity

The description lists several concrete actions — "generating code from UI specs, building custom code exporters, traversing specs, or serializing props" — matching the anchor for several specific actions with minor gaps. It falls short of a 5 because coverage of the library's full surface (e.g., its types or generator interface) is not exhaustive.

4 / 5

Completeness

It clearly answers both "what" ("Code generation utilities for json-render") and "when" with an explicit "Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props" clause — directly paralleling the anchor-5 example. Not a 4 because the "when" is explicit and enumerates concrete trigger phrases rather than being merely adequate.

5 / 5

Trigger Term Quality

Natural phrases a json-render user would say ("generate code", "UI specs", "code exporters", "serializing props") are present with good keyword coverage, matching anchor 4. A few natural variations users might type (e.g., "codegen", framework names like Next.js/Remix) are missing, so it does not reach comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche tied to "@json-render/codegen" with distinct trigger terms, so risk of firing for an unrelated skill is minimal. It matches anchor 5; a 4 would require identifiable overlap with a closely related skill, which is not the case here.

5 / 5

Total

18

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
vercel-labs/json-render
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.