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.

Quality

81%

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

71%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.

An exceptionally actionable and accurate SDK reference with executable examples and real validation workflows, weakened by monolithic single-file structure and verbose prose. Splitting the large reference catalogs into bundled reference files and tightening the winding sentences would lift the weaker dimensions.

Suggestions

Split the large inlined catalogs (Effects channel, Charts, Markdown, Templates, Attributes) into one-level-deep reference files under references/ and link to them from SKILL.md so the main file stays a lean overview.

Tighten the long em-dash- and parenthesis-heavy sentences into shorter declarative statements to improve token efficiency without dropping the SDK-specific detail.

Add an explicit quick-start workflow up front (init → write markup → `native markup check` → `native test` → `native automate assert`) as a single numbered sequence with validation checkpoints, separate from the reference sections.

Dimension	Reasoning	Score
Conciseness	The 1288-line body is dense and almost entirely novel SDK-specific content (no padding with concepts Claude already knows), but the prose is noticeably verbose — very long, parenthetical- and em-dash-heavy sentences throughout that could be tightened considerably without losing clarity.	3 / 5
Actionability	Pervasive copy-paste-ready code (Zig, TypeScript, .native markup, bash), exact function signatures, and concrete commands covering the common cases — e.g. the fake-executor feed* signatures, the automation harness verbs, and full statusItem/window bindings.	5 / 5
Workflow Clarity	Clear validation sequences are present ('Validate without building' → model-contract check, and 'Verify live through the automation harness' with `native automate assert` regex polling and `--absent`), but the skill is reference-shaped with multiple embedded workflows rather than one cohesive checklist-driven flow, leaving minor gaps.	4 / 5
Progressive Disclosure	Section structure is good and external references are signaled (delegates to `ts-core` and `zig` skills, points to example apps and the Dynamic Images guide URL), but no bundle files exist and large reference catalogs (Effects channel, Charts, Markdown, Templates) are inlined monolithically in one 1288-line file rather than split into one-level-deep reference files.	3 / 5
	Total	15 / 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, specific description that clearly states both what the skill does and when to use it, with concrete trigger phrases and a distinct niche. It is slightly jargon-laden in places, which keeps trigger-term quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete 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 specific capabilities rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what ('Authoring guide for the Native markup (.native) view tier of native-rendered Native SDK apps') and when ('Use when building or modifying native UI..., writing .native files, wiring views to Model/Msg/update, testing markup views, or verifying a native app through the automation harness') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('native UI', 'widgets', 'layout', 'bindings', 'messages', '.native files', 'automation harness') including the file extension, but it is jargon-heavy ('Model/Msg/update', 'UiApp recipes') and misses some plain synonyms a user might say.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — the Native SDK .native markup view tier — with distinct triggers (.native files, Model/Msg/update, automation harness) that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1289 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
Path: skill-data/native-ui/SKILL.md
Commit: 31663e1

Reviewed: 6 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.