oma-mobile

Mobile specialist for Flutter, React Native, and Swift native iOS development. Use for mobile app, Flutter, Dart, React Native, Swift, SwiftUI, iOS, Android, Riverpod, swift-openapi-generator, and widget work.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/oma-mobile/SKILL.md

Quality

Content

65%

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

The content is a well-structured, mostly actionable mobile workflow with concrete commands and named tooling. Its weak spots are abstract verification without a feedback loop and a resources/references structure that cannot be verified because no bundle files are present.

Suggestions

Add an explicit validation gate after VERIFY, e.g. run tests, and on failure fix then re-run before FINALIZE, to give a concrete fail-fix-revalidate feedback loop.

Deduplicate the References section: the resources/execution-protocol.md, examples.md, and checklist.md entries appear both as prose and as bullets; keep only one list.

Ship the referenced bundle files (resources/*.md, ../_shared/core/*.md) alongside the skill, or remove paths that do not exist, so progressive disclosure is verifiable.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight bullets and tables that assume Claude's competence, but it duplicates the same resources list (prose lines 127-129 and bullets 132-138) and overlaps "Dependencies" with "Tools and instruments", so it could be tightened.	2 / 3
Actionability	It gives executable commands ("rg --files", "rg \"Riverpod\|Bloc\|...\"") and concrete, named guidance (Dio with interceptors, dispose(), 60fps, Material 3 + iOS HIG, Maestro), meeting the copy-paste-ready bar for an orchestration skill.	3 / 3
Workflow Clarity	The Entry/Scenes/Exit sequence is clear and a VERIFY scene exists, but verification is described abstractly ("Run relevant unit/widget/integration/E2E checks") with no explicit validate-then-proceed gating or fail-fix-revalidate feedback loop.	2 / 3
Progressive Disclosure	References are clearly signaled one level deep in a References section, but no bundle files exist on disk (references/, scripts/, assets/ are absent), so the resources/* and ../_shared/* paths cannot be verified as real.	2 / 3
	Total	9 / 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.

The description is concise and gives strong, natural trigger terms with an explicit "Use for" clause, answering both what and when. The main weakness is that it states the domain abstractly rather than naming concrete build/test/implement actions.

Dimension	Reasoning	Score
Specificity	"Mobile specialist for Flutter, React Native, and cross-platform mobile development" names the domain and stacks but uses abstract nouns ("specialist", "development") rather than concrete verbs like build, test, or implement, matching the score-2 anchor.	2 / 3
Completeness	It states what the skill is (mobile specialist) and gives an explicit "Use for ..." trigger clause, clearly answering both what and when.	3 / 3
Trigger Term Quality	"Use for mobile app, Flutter, Dart, iOS, Android, Riverpod, and widget work" provides strong, natural coverage of terms a user would actually say when they need this skill.	3 / 3
Distinctiveness Conflict Risk	The mobile-specific triggers (Flutter, React Native, Riverpod, iOS/Android) carve out a clear niche unlikely to fire for non-mobile skills.	3 / 3
	Total	11 / 12 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: first-fluke/oh-my-agent
Path: .agents/skills/oma-mobile/SKILL.md
Commit: 3021301

Reviewed: about 21 hours 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.