CtrlK
BlogDocsLog inGet started
Tessl Logo

native-ui

Authoring guide for the Native markup (.native) view tier of native-rendered Native SDK apps. TypeScript cores are the default and use this skill together with ts-core; Zig cores are an explicit alternative and this guide labels their lower-level UiApp recipes. Use when building or modifying native UI (widgets, layout, bindings, messages), writing .native files, wiring views to Model/Msg/update, testing markup views, or verifying a native app through the automation harness.

71

Quality

89%

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

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 thorough, highly actionable authoring reference with strong executable examples and explicit validation/testing checkpoints. Its main weakness is progressive disclosure: nearly everything lives in one monolithic SKILL.md with no bundle files, and the prose could be tightened.

Suggestions

Split the large reference blocks (the Elements/Attributes tables and the Effects channel catalog) into separate files under references/ and point to them from SKILL.md to reduce the monolithic wall of text.

Trim recurring emphatic filler ('the honest behavior', 'never silent', repeated 'teaching error' framing) to lower token cost while preserving the rules themselves.

Add a short top-of-file quick-start workflow that sequences author -> `native markup check` -> `native test` -> automation verify, so the validation checkpoints form one explicit end-to-end path.

DimensionReasoningScore

Conciseness

The body is information-dense and skill-specific (no padding with concepts Claude already knows), but the 1287-line prose carries recurring emphatic qualifiers and parenthetical asides ('the honest behavior', 'teaching error', 'never silent') that could be trimmed without losing clarity.

4 / 5

Actionability

Provides fully executable, copy-paste-ready TypeScript and Zig code blocks, concrete commands ('native markup check', 'native automate widget-click'), exact function signatures, and attribute vocabularies covering the common cases.

5 / 5

Workflow Clarity

Validation and verification are explicit and present — 'native markup check', the model-contract step, and the rebuild-and-assert testing pattern with its 'rebuild before pressing again' feedback loop — though the guide is organized as topical reference sections rather than one end-to-end numbered workflow.

4 / 5

Progressive Disclosure

Section headers are well organized and sibling-skill references (ts-core, zig, the Dynamic Images URL) are clearly signaled, but the file is a monolithic 1287-line document with no bundle files; large reference blocks (the Elements/Attributes tables, the multi-hundred-line Effects section) are inlined where a file this size would benefit from separate reference files.

3 / 5

Total

16

/

20

Passed

Description

100%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 precise, third-person description that concretely states what the skill does and when to use it, with natural trigger terms and a file extension. It cleanly separates itself from related core skills.

DimensionReasoningScore

Specificity

Lists multiple concrete authoring actions — 'building or modifying native UI (widgets, layout, bindings, messages)', 'writing .native files', 'wiring views to Model/Msg/update', 'testing markup views', 'verifying a native app through the automation harness' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both: what ('Authoring guide for the Native markup (.native) view tier of native-rendered Native SDK apps') and when (an explicit 'Use when ...' clause enumerating concrete trigger phrases).

5 / 5

Trigger Term Quality

Covers natural user-facing terms with synonyms and a file extension — 'native UI', 'native app', '.native files', 'widgets, layout, bindings, messages', 'automation harness' — matching the comprehensive-synonyms-plus-extension anchor.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Native markup view tier) and explicitly disambiguates from the sibling ts-core and Zig-core skills, so it is unlikely to trigger for the wrong skill.

5 / 5

Total

20

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1288 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

16

Passed

Repository
vercel-labs/native
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.