CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

80%

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 well-structured, lean skill body that assumes Claude's competence, gives concrete commands and specific guardrails, and uses clean one-level-deep progressive disclosure. Main weakness is some templated verbosity in the Scheduling section and abstract scene labels in the workflow.

Suggestions

Tighten the Scheduling section (Goal/Intent signature/When to use/Expected inputs-outputs) which reads as generic templating and partially duplicates the description's trigger terms.

Make the workflow scenes more concrete by pairing each PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE label with the specific command or file operation it maps to, rather than leaving them as abstract scene names.

Consolidate the 16 guardrails so the most generic ones (e.g. '60fps target', 'Clean Architecture: domain -> data -> presentation') do not dilute the high-value platform-specific rules.

DimensionReasoningScore

Conciseness

Dense and assumes Claude's intelligence (no explanations of what Flutter or Riverpod are), with every guardrail earning its place; minor templating padding in the Scheduling section (Goal/Intent signature/When to use) could be trimmed.

4 / 5

Actionability

Provides concrete commands ('rg --files', 'rg "Riverpod|Bloc|..."') and specific actionable guardrails ('dispose()', 'swipeBackDestination wrapper', 'Drift offline-first cache'), with the bulk of code deferred to referenced snippet files.

4 / 5

Workflow Clarity

Clear PREPARE->ACQUIRE->ACT->VERIFY->FINALIZE sequence with an explicit VERIFY checkpoint, a failure-and-recovery feedback loop, and a referenced checklist; the scene labels are somewhat abstract relative to literal per-step commands, a minor gap.

4 / 5

Progressive Disclosure

The body is an overview pointing to a well-signaled, one-level-deep References section (snippets.md, tech-stack.md, screen/api templates, execution-protocol.md, checklist.md, variant READMEs), with content appropriately split across variant files.

5 / 5

Total

17

/

20

Passed

Description

82%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, third-person description that explicitly covers both capability and trigger conditions with a distinct mobile niche. It is slightly weak on concrete action verbs, leaning on 'specialist' and 'work' rather than naming specific operations.

DimensionReasoningScore

Specificity

Names the mobile domain richly across three platforms and 10+ technologies, but the actual actions are generic ('specialist for ... development', 'Use for ... work') with no concrete verbs like build, test, or deploy.

3 / 5

Completeness

Explicitly answers both 'what' ('Mobile specialist for Flutter, React Native, and Swift native iOS development') and 'when' ('Use for mobile app, Flutter ... widget work') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural-term coverage (mobile app, Flutter, Dart, React Native, Swift, SwiftUI, iOS, Android, Riverpod, widget work) a user would say, but missing file extensions/synonyms and includes the jargony 'swift-openapi-generator'.

4 / 5

Distinctiveness Conflict Risk

Clear mobile-only niche with platform/framework-specific triggers, well separated from web frontend and backend skills, giving minimal conflict risk.

5 / 5

Total

17

/

20

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
first-fluke/oh-my-agent
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.