NutriSport: Skill for Claude Code

.claude/skills/compose-screen-splitter/SKILL.md

compose-screen-splitter is a skill for Claude Code from satanyakiv/NutriSport. It costs 228 tokens per session (4,111 once invoked), scanned A, original, MIT.

A skill for reviewing and splitting oversized Jetpack Compose screen files in the NutriSport Kotlin Multiplatform project. Jetpack Compose is Android's code-based UI toolkit.

In plain words
What is it for?
Use it in audit mode for a read-only report, or in execution mode to extract components while preserving routing, dependency injection, previews, compilation, and tests.
Why use it?
It makes screens easier to navigate, review, test, and reuse when too many UI sections or responsibilities have accumulated in one file.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; names the AskUserQuestion tool.

This is satanyakiv/NutriSport's own configuration. It tells Claude Code how to work on NutriSport itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NutriSport configures →

Reuse

Borrowing it

Nothing to install: this file belongs to satanyakiv/NutriSport. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/satanyakiv/NutriSport/main/.claude/skills/compose-screen-splitter/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/satanyakiv/NutriSport

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for compose-screen-splitter

README.md
[![agentmods](https://agentmods.dev/badge/skills/satanyakiv/nutrisport/compose-screen-splitter/github.svg)](https://agentmods.dev/skills/satanyakiv/nutrisport/compose-screen-splitter)
Your own site
<a href="https://agentmods.dev/skills/satanyakiv/nutrisport/compose-screen-splitter"><img src="https://agentmods.dev/badge/skills/satanyakiv/nutrisport/compose-screen-splitter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for compose-screen-splitter

Your own site · 80×15
<a href="https://agentmods.dev/skills/satanyakiv/nutrisport/compose-screen-splitter"><img src="https://agentmods.dev/badge/skills/satanyakiv/nutrisport/compose-screen-splitter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 228 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00228 $0.04111
Opus 5 $0.00114 $0.02056
Sonnet 5 $0.00046 $0.00822
Haiku 4.5 $0.00023 $0.00411

Measured 9d ago against content hash 5386c1b51fce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

compose-screen-splitter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/compose-screen-splitter/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compose Screen Splitter

Why this skill exists

Compose Screens accumulate UI sections (header, list, summary, dialog, sheet, …) until the file becomes hard to navigate, hard to review, and hard to preview. The Medium article "How to split Compose screens before they become unmanageable" names the symptoms (600-800 lines, 3-4 levels of nesting, six concerns sharing one file) and the cure (Screen↔Content split, name-driven extraction, feature-local component packages).

The NutriSport project has already adopted most of the cure as rules — Route↔Screen separation in conventions.md, :core:<name> for cross-feature reuse in architecture.md Rule 12, design-system primitives in :shared:ui/component/, Preview discipline in preview.md. What's missing is an executor: nobody is responsible for noticing when a Screen crossed the threshold and applying these rules without breaking the contract surface (DI in Routes, no DI in Screens, Preview light+dark for Screens, internal reuse never public).

This skill is that executor. It works in two modes — audit-only (read-only report) and execute (run the full split with compile + test verification).

When to invoke

Trigger phrases (English + Ukrainian, dictation-friendly):

  • "split this Screen", "розпиляй цей екран", "decompose this composable file"
  • "DetailsScreen is too long", "файл занадто довгий"
  • "audit screen size", "перевір розмір екрана"
  • "extract sections from XxxScreen", "винеси секції в окремі файли"
  • After the feature pipeline finishes and the new Screen is ≥300 lines (Phase 4 wires this in automatically — see feature/SKILL.md Step 19.5).

If the user mentions a *Screen.kt file in any of these contexts, invoke the skill.

Read the full file on GitHub · 207 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 207 lines · 228 tokens per session scan A 5386c1b51fce

Subscribe to this mod's changes

compose-screen-splitter is a skill published in the GitHub repository satanyakiv/NutriSport (11 stars, last pushed 3mo ago), licensed MIT. It adds 228 tokens to every session and 4,111 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

wear-compose-m3

Expert guidance for working with Wear OS Compose Material3. Use this skill when creating, updating, or migrating Wear OS projects. This includes the androidx.wear.compose.material3, androidx.wear.compose.foundation, and androidx.wear.compose.navigation3 libraries. Also working with core components such as AppScaffold…

android/skills · 101 tokens

kotlin-specialist

Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…

Jeffallan/claude-skills · 86 tokens

build-android-binary

Compile a PAM control's Android Kotlin module into the runtime-loadable DEX for a .ppmplugin. Creates a staged Gradle build with the pinned wrapper and react-android compile dependency, verifies manifest/module/package alignment and runtime-loading constraints, builds the release AAR, then runs d8 --min-api 24. Writes…

microsoft/power-platform-skills · 150 tokens

swiftui-dev

Use this skill for SwiftUI development, architecture, structure, performance, and Apple native app profiling. It combines.

Orkas-AI/Orkas · 3 tokens

android-navigation-3

Install and migrate to Jetpack Navigation 3. Use when implementing Navigation 3 patterns including NavDisplay, NavKey routes, deep links, multiple backstacks, scenes (dialogs, bottom sheets), or migrating from Navigation 2.

HoangNguyen0403/agent-skills-standard · 52 tokens

mobiai-kmp

Use when working on a Kotlin Multiplatform project — shared code, expect/actual declarations, platform-specific implementations, building and testing.

ArisGuimera/MobiAI-Core · 32 tokens