CtrlK
BlogDocsLog inGet started
Tessl Logo

ink

Ink terminal renderer for json-render that turns JSON specs into interactive terminal UIs. Use when working with @json-render/ink, building terminal UIs from JSON, creating terminal component catalogs, or rendering AI-generated specs in the terminal.

74

Quality

91%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable reference skill with executable examples and a clear build sequence, weakened only by progressive disclosure: the entire component catalog and exports tables are inlined in SKILL.md with no separate reference files to offload detail.

Suggestions

Move the full Standard Components catalog and the Key Exports / Providers tables into a separate references file (e.g. references/COMPONENTS.md) and link to it from a concise overview, so SKILL.md stays a lean entry point.

Add a short 'Validation / troubleshooting' note or pointer for common render-time pitfalls (missing provider, unregistered component, bad $bindState path) to give the build flow an explicit feedback checkpoint.

Trim the Streaming and Server-Side Prompt Generation sections to one-line pointers unless they are needed up front, keeping the Quick Start sequence as the unambiguous primary path.

DimensionReasoningScore

Conciseness

Sections are dense and assume Claude's competence — terse one-line component descriptions and copy-paste code with no padding about what terminals, React, or Ink are; not level 2 because there is no extraneous explanation to tighten, and each reference entry earns its place for a rendering skill.

3 / 3

Actionability

Provides fully executable TypeScript in Quick Start plus complete JSON spec examples and runnable snippets for events, repeat, streaming, server-side prompt generation, and createRenderer; not level 2 because the code is real and copy-paste ready rather than pseudocode or abstract direction.

3 / 3

Workflow Clarity

Quick Start lays out a clear build sequence (define catalog → defineRegistry → wrap in JSONUIProvider → render) and the skill involves no destructive or batch operations requiring validation checkpoints, so clear organization suffices per the simple-skill guidance; not level 2 because the sequence is unambiguous and no feedback loop is warranted.

3 / 3

Progressive Disclosure

All ~270 lines are inline in SKILL.md with no bundle files and no one-level-deep references — the full standard-component catalog and Key Exports/Providers tables are reference material that could live in separate files, matching the level-2 anchor of content that should be separate being inline; not level 1 because section organization is clean with no nested references, not level 3 because there are no well-signaled external references at all.

2 / 3

Total

11

/

12

Passed

Description

90%

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 with an explicit what+when structure, third-person voice, and good natural trigger coverage for a well-scoped niche. The only weak spot is specificity, which states one core capability rather than enumerating several distinct concrete actions.

DimensionReasoningScore

Specificity

Quotes a single concrete core action — "turns JSON specs into interactive terminal UIs" — with the "Use when" clause restating that one capability as variations (building, creating catalogs, rendering specs) rather than listing multiple distinct actions like the level-3 anchor; not level 1 because the domain and a real action are named, not level 3 because no comprehensive set of distinct operations is enumerated.

2 / 3

Completeness

Explicitly answers both what ("Ink terminal renderer ... that turns JSON specs into interactive terminal UIs") and when ("Use when working with @json-render/ink, building terminal UIs from JSON ..."), matching the level-3 anchor with an explicit trigger clause; not level 2 because the "when" is explicit, not merely implied.

3 / 3

Trigger Term Quality

The "Use when" clause covers natural phrasings a user would say — "building terminal UIs from JSON", "terminal component catalogs", "rendering AI-generated specs in the terminal" — giving good coverage of the domain's common variations; not level 2 because it spans multiple natural trigger phrasings rather than a single keyword.

3 / 3

Distinctiveness Conflict Risk

The scoped "@json-render/ink" package and "Ink terminal renderer" niche make it clearly distinguishable and unlikely to trigger for unrelated skills; not level 2 because the niche is distinct rather than broadly overlapping, and voice is third person so no specificity penalty applies.

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.

Validation16 / 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.