CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

oma-mobile

Implement Flutter, React Native, native Swift, or native Kotlin Android apps. Use for mobile screens, widgets, platform integrations, and application data flows.

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

Fix and improve this skill with Tessl

tessl review fix ./skills/oma-mobile/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 dense, expert-level instruction set with an unusually strong workflow structure: numbered steps, stack-detection precedence, verification gating, failure recovery, and explicit exit criteria. Its weaknesses are the 20-item Guardrails section inlining platform detail that duplicates the (missing) variant snippets, and a progressive-disclosure design whose referenced files are largely absent from the evaluated bundle, leaving most pointers dead.

Suggestions

Ship the referenced bundle files — `resources/{execution-protocol,checklist,error-playbook,tech-stack,stack-generation}.md`, the eight `variants/<platform>/{tech-stack,snippets}.md` files, and `variants/stack.schema.json` — or remove those references, since currently most pointers in the References section and Guardrails (e.g. `variants/swift-ios/snippets.md` §10) dead-end.

Move the platform-conditional Guardrails 8-20 (Swift concurrency, cache, and navigation rules; Kotlin Compose/OpenAPI rules) into the corresponding variant files, keeping SKILL.md to the cross-platform core so the body tightens toward the lean anchor.

Inline one concrete verification example (e.g., a sample `verify:` block from `stack.yaml`) so workflow step 5 is executable without first loading the stack reference.

DimensionReasoningScore

Conciseness

The body is dense and assumes competence (e.g., "cache DECODED models (never `HTTPBody`), serve stale-while-revalidate on reads, invalidate keys on writes") with no basic-concept padding, matching anchor 4's 'efficient; minor instances of over-explanation that could be trimmed'. It is not 5 because the 20-item Guardrails inlines deep platform-specific detail (e.g., "isolated deinit requires Swift 6.2+") that belongs in the variant snippets, and the Scheduling 'Goal'/'When to use' sections partially restate the 'Intent signature'.

4 / 5

Actionability

Concrete, executable specifics throughout: exact detection files ("`Package.swift` (Swift iOS), `settings.gradle.kts` + `com.android.application` (Kotlin Android), `pubspec.yaml` (Flutter)"), exact tool calls ("`find_file`, `search_for_pattern`, `get_symbols_overview`, `find_symbol`"), and per-platform library mandates, matching anchor 4's 'mostly executable guidance; concrete code or commands with minor gaps'. Not 5 because all code examples are delegated to `snippets.md` files ("see `variants/swift-ios/snippets.md` §10") so nothing copy-paste-ready lives in the body itself.

4 / 5

Workflow Clarity

The "Canonical workflow path" is a clearly sequenced 6-step procedure with explicit validation (step 5 selects and runs the `verify:` commands), a feedback loop for error recovery ("If a check that ran fails, fix it before handoff or report the failing check"), a checklist gate (step 6: "Check the applicable checklist items"), and explicit exit criteria in the Exit section — matching anchor 5's 'clear sequence with explicit validation steps; feedback loops for error recovery; checklists'.

5 / 5

Progressive Disclosure

The References section is well-signaled with per-file purposes, and the four referenced `references/_shared/core/*.md` files (context-loading, clarification-protocol, context-budget, lessons-learned) exist in the bundle. However, most referenced paths do not exist in the actual bundle — `resources/execution-protocol.md`, `resources/checklist.md`, `resources/error-playbook.md`, `resources/tech-stack.md`, all eight `variants/<platform>/{tech-stack,snippets}.md` files, `stack/stack.yaml`, `variants/stack.schema.json`, and `../oma-observability/SKILL.md` — so the disclosure structure does not resolve for the majority of its pointers. This is more than the 'minor organization gaps' of anchor 4, fitting anchor 3's 'some structure but could be better organized' against the real file listing.

3 / 5

Total

16

/

20

Passed

Description

75%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 description: it names the four target stacks, states what the skill does, and includes an explicit 'Use for...' trigger clause covering screens, widgets, platform integrations, and data flows. Its main gaps are the missing 'iOS' trigger term and triggers phrased as abstract capability areas rather than concrete phrases a user would actually say.

DimensionReasoningScore

Specificity

"Implement Flutter, React Native, native Swift, or native Kotlin Android apps. Use for mobile screens, widgets, platform integrations, and application data flows" names several concrete capability areas (screens, widgets, platform integrations, data flows), matching anchor 4's 'several specific actions; minor gaps'. It is not 5 because everything hangs on the single generic verb 'Implement' rather than multiple distinct concrete actions, and not 3 because more than 1-2 specific areas are enumerated.

4 / 5

Completeness

Both parts are explicit: the what is "Implement Flutter, React Native, native Swift, or native Kotlin Android apps" and the when is the explicit "Use for mobile screens, widgets, platform integrations, and application data flows" clause, matching anchor 4 ('when' could be more explicit or specific). Not 5 because the triggers are abstract capability areas rather than concrete user phrases like 'when the user mentions Flutter or needs an iOS app'; not 3 because the when is explicit, not merely implied.

4 / 5

Trigger Term Quality

Strong natural keywords users would say — "Flutter", "React Native", "Swift", "Kotlin", "Android", "widgets" — fitting anchor 4's 'good keyword coverage; a few natural terms missing'. Not 5 because "iOS" (the most natural term for the Swift stack), "Dart", and the phrase "mobile app" are absent; not 3 because coverage goes well beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

Naming four specific stacks carves out a clear mobile-app niche that is easily distinguished from web frontend or backend skills, matching anchor 4's 'mostly distinct; minor overlap risk'. Not 5 because "Swift" and "widgets" also appear in non-mobile contexts (server-side Swift, desktop widgets) and "iOS" is never named as a trigger; not 3 because the named frameworks make it far more distinct than 'somewhat specific'.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository

first-fluke/oh-my-agent

Path

skills/oma-mobile/SKILL.md

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.