Mobile Instinct V1
- 21 installs
- 60 repo stars
- Updated June 14, 2026
- ahmed3elshaer/everything-claude-code-mobile
mobile-instinct-v1 is a Claude Code skill that captures mobile development patterns as code is written, with confidence scoring and immediate feedback.
About
mobile-instinct-v1 is a Claude Code skill that captures mobile development patterns as code is written. It automatically extracts Compose, MVI, Koin, Ktor, and coroutine patterns with confidence scoring, boosting confidence when a pattern is reused, accepted, or passes review. A developer uses it to have the agent learn and reinforce coding patterns in real time.
- Immediate pattern capture as mobile code is written
- Captures Compose, MVI, Koin, Ktor, and coroutine patterns
- Confidence scoring that boosts when patterns are reused or accepted
Mobile Instinct V1 by the numbers
- 21 all-time installs (skills.sh)
- Ranked #10,289 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
mobile-instinct-v1 capabilities & compatibility
- Capabilities
- pattern capture · confidence scoring · hook integration
What mobile-instinct-v1 says it does
Immediate pattern capture during mobile development with real-time feedback.
V1 instinct-based pattern capture for mobile development. Captures patterns as code is written with immediate feedback.
npx skills add https://github.com/ahmed3elshaer/everything-claude-code-mobile --skill mobile-instinct-v1Add your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 21 |
|---|---|
| repo stars | ★ 60 |
| Last updated | June 14, 2026 |
| Repository | ahmed3elshaer/everything-claude-code-mobile ↗ |
What it does
Automatically capture and score mobile coding patterns (Compose, MVI, Koin, Ktor, coroutines) as an agent writes code.
Who is it for?
Developers who want an agent to capture and reinforce coding patterns as code is written.
Skip if: Cross-session architectural learning, which is the domain of mobile-instinct-v2.
When should I use this skill?
Writing Compose screens, ViewModels, Koin modules, Ktor clients, or coroutine code.
By the numbers
- 5 pattern categories (Compose, MVI, Koin, Ktor, Coroutine)
- Maximum confidence 1.0
Files
Mobile Instinct v1 - Pattern Capture
Immediate pattern capture during mobile development with real-time feedback.
Overview
V1 instincts capture mobile development patterns as you write code. When you create Composables, ViewModels, or repositories, relevant patterns are automatically extracted and stored with confidence scoring.
Triggers
Automatic capture on:
- Creating
.ktfiles in Compose screens - Writing ViewModel code
- Adding Koin modules
- Configuring Ktor clients
- Writing coroutine code
Pattern Categories
Compose Patterns
| Pattern ID | Description | Initial Confidence |
|---|---|---|
compose-state-hoisting | State hoisted to caller | 0.5 |
compose-remember-key | Stable keys in lazy lists | 0.6 |
compose-side-effect | Proper LaunchedEffect usage | 0.5 |
compose-immutable | Immutable data classes | 0.7 |
MVI Patterns
| Pattern ID | Description | Initial Confidence |
|---|---|---|
mvi-sealed-state | Sealed interface for state | 0.7 |
mvi-intent-handler | onIntent pattern | 0.6 |
mvi-reduce-function | State reduction | 0.5 |
mvi-single-event | One-time event handling | 0.6 |
Koin Patterns
| Pattern ID | Description | Initial Confidence |
|---|---|---|
koin-viewmodel-injection | koinViewModel() in Compose | 0.7 |
koin-module-factory | Module definition with factory | 0.6 |
koin-scoped-deps | Scoped dependencies | 0.5 |
Ktor Patterns
| Pattern ID | Description | Initial Confidence |
|---|---|---|
ktor-safe-request | runCatching wrapper | 0.7 |
ktor-plugin-install | ContentNegotiation setup | 0.6 |
ktor-timeout-config | Request timeout handling | 0.5 |
Coroutine Patterns
| Pattern ID | Description | Initial Confidence |
|---|---|---|
coroutine-viewmodel-scope | viewModelScope.launch | 0.8 |
coroutine-structured | Proper scope hierarchy | 0.7 |
coroutine-dispatcher | Correct dispatcher selection | 0.6 |
Usage
Patterns are captured automatically. To review captured patterns:
/instinct-statusConfidence Boosting
When a pattern is:
- Detected: Initial confidence (0.3-0.5)
- Used again: +0.1
- User accepted: +0.2
- Passes review: +0.1
Maximum confidence: 1.0
Integration with Hooks
Works with hooks/instinct-hooks.json for:
- Post-tool-use pattern detection
- Session-end pattern consolidation
- Pre-compact instinct preservation
---
Remember: V1 is about immediate capture. V2 provides observational learning across sessions.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
When are patterns captured?
Automatically when creating Compose screen .kt files, writing ViewModels, adding Koin modules, configuring Ktor clients, or writing coroutine code.
How does confidence change?
Detected patterns start at 0.3-0.5, gaining +0.1 on reuse, +0.2 on user acceptance, and +0.1 on passing review, up to a maximum of 1.0.