oma-mobile

Mobile specialist for Flutter, React Native, and cross-platform mobile development. Use for mobile app, Flutter, Dart, iOS, Android, Riverpod, and widget work.

Quality

70%

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 ./benchmarks/runs/oma/.agents/skills/oma-mobile/SKILL.md

Quality

Content

67%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.

The body is a well-structured orchestration guide with a clear sequenced workflow, validation checkpoint, and failure-recovery loop, and it appropriately delegates detail to one-level-deep resource files. It is weakest on standalone actionability, since actual mobile code lives in referenced files rather than inline.

Suggestions

Add one or two inline copy-paste mobile snippets (e.g. a minimal Riverpod provider or a `flutter test` / `maestro test` command) so the body is actionable without opening referenced files.

Make the VERIFY checkpoint concrete by naming specific commands (e.g. `flutter test`, `maestro test flows/`) instead of the generic "run relevant checks" phrasing.

De-duplicate the References section — keep a single clearly-labeled bullet list and drop the repeated prose mentions of the same files.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows (no "what is Flutter/Riverpod" padding) and uses terse tables and lists, but has minor redundancy between the Intent signature, When to use, and When NOT to use sections that could be trimmed, fitting the efficient-with-minor-trim anchor rather than the lean top anchor.	4 / 5
Actionability	It provides some concrete executable guidance (the `rg --files` and `rg "Riverpod\|Bloc\|..."` commands and the screen-template reference) but the bulk of mobile code is deferred to referenced files, and the Actions table maps to abstract primitives (READ/WRITE/VALIDATE) rather than executable Dart/JSX, leaving it incomplete as standalone guidance.	3 / 5
Workflow Clarity	The Entry → Scenes (PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE) → Failure and recovery → Exit sequence is clear with a VERIFY checkpoint and an explicit "if tests fail, fix before handoff" feedback loop, but the validation steps are described generically ("run relevant unit/widget/integration/E2E checks") rather than with specific commands, leaving minor gaps versus the explicit-checkpoint top anchor.	4 / 5
Progressive Disclosure	The References section signals one-level-deep resources clearly (execution-protocol, examples, snippets, checklist, screen-template) and the body acts as an overview, but the referenced resources/* files are absent from the review bundle and the same paths are listed twice (prose lines plus a bullet list), giving good-but-not-clean organization.	4 / 5
	Total	15 / 20 Passed

Description

73%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.

The description clearly answers what the skill does and when to use it with a strong natural trigger-term list, and carves out a distinct mobile niche. Its main weakness is specificity: it relies on a generic role label rather than naming concrete actions.

Suggestions

Replace the generic "Mobile specialist for ... development" role label with concrete actions, e.g. "Build, modify, and verify Flutter and React Native mobile apps with clean architecture, state management, and E2E coverage."

Add platform-feature trigger terms users actually say (camera, GPS, push notifications, offline-first) and file extensions (.dart, pubspec.yaml) to raise trigger-term coverage to comprehensive.

Add an explicit disambiguating clause (e.g. "not for web frontends") to reduce overlap with a generic Frontend Agent.

Dimension	Reasoning	Score
Specificity	The phrase "Mobile specialist for Flutter, React Native, and cross-platform mobile development" names the domain and frameworks but uses a generic role label ("specialist for ... development") with no concrete action verbs like build, modify, or verify, matching the anchor for minimal/generic actions rather than the entirely-vague anchor below it.	2 / 5
Completeness	It explicitly states both what ("Mobile specialist for Flutter, React Native, and cross-platform mobile development") and when ("Use for mobile app, Flutter, Dart, iOS, Android, Riverpod, and widget work") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"Use for mobile app, Flutter, Dart, iOS, Android, Riverpod, and widget work" covers strong natural keywords users say, but omits common synonyms/extensions (.dart, pubspec) and platform-feature terms (camera, GPS, push notifications) that appear only in the body, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The mobile niche (iOS, Android, cross-platform mobile) is clear and distinct, but "React Native" shares ecosystem overlap with web React and "widgets" is a generic term also used in frontend, creating minor overlap risk rather than the minimal-risk top anchor.	4 / 5
	Total	15 / 20 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: benchmarks/runs/oma/.agents/skills/oma-mobile/SKILL.md
Commit: 032c988

Reviewed: 2 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.