Mobile Instinct V2
- 22 installs
- 60 repo stars
- Updated June 14, 2026
- ahmed3elshaer/everything-claude-code-mobile
mobile-instinct-v2 is a Claude Code skill that performs cross-session observational learning to extract reusable mobile development patterns over time.
About
mobile-instinct-v2 is a Claude Code skill that performs cross-session observational learning for mobile development. At session end it analyzes code changes, problem context, and solution approaches to extract recurring architectural, problem-solution, and code-organization patterns, evolving confidence across sliding session windows. A developer uses it to have the agent learn higher-level patterns over time.
- Cross-session observational learning of mobile patterns
- Extracts architectural, problem-solution, and organization patterns
- Sliding observation windows with confidence that evolves over sessions
Mobile Instinct V2 by the numbers
- 22 all-time installs (skills.sh)
- Ranked #10,169 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
mobile-instinct-v2 capabilities & compatibility
- Capabilities
- observational learning · pattern extraction · confidence scoring
What mobile-instinct-v2 says it does
Cross-session observational learning that extracts patterns from your development workflow over time.
V2 instinct-based observational learning. Analyzes sessions to extract reusable mobile development patterns across time.
npx skills add https://github.com/ahmed3elshaer/everything-claude-code-mobile --skill mobile-instinct-v2Add your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 22 |
|---|---|
| repo stars | ★ 60 |
| Last updated | June 14, 2026 |
| Repository | ahmed3elshaer/everything-claude-code-mobile ↗ |
What it does
Extract recurring architectural and organizational mobile patterns across sessions via end-of-session observational learning.
Who is it for?
Developers who want an agent to learn architectural patterns across many sessions.
Skip if: Immediate single-file pattern capture, which is mobile-instinct-v1's role.
When should I use this skill?
At session end, to observe and extract recurring architectural and organization patterns.
By the numbers
- 4 observation windows (current, last 5, last 20, all time)
- 3 pattern categories (architectural, problem-solution, code organization)
Files
Mobile Instinct v2 - Observational Learning
Cross-session observational learning that extracts patterns from your development workflow over time.
Overview
V2 instincts observe your sessions and extract patterns that emerge across multiple development activities. Unlike V1's immediate capture, V2 looks for:
- Recurring architectural decisions
- Problem-solving approaches
- Code organization patterns
- Testing strategies
Session Analysis
At session end, V2 analyzes: 1. Code changes: What was modified 2. Problem context: What issue was being solved 3. Solution approach: How it was resolved 4. Dependencies: What libraries/techniques were used
Pattern Categories
Architectural Patterns
| Pattern | Detected By | Example |
|---|---|---|
layer-separation | Consistent data/ui/domain separation | Repository + ViewModel + Composable |
dependency-injection | Koin module patterns | factoryOf, viewModel |
navigation-pattern | Compose Navigation usage | NavHost with routes |
state-management | MVI/MVVM consistency | StateFlow + sealed classes |
Problem-Solution Patterns
| Pattern | Detected By | Example |
|---|---|---|
error-boundary | Try-catch with UI feedback | Error state in Composable |
loading-state | isLoading + Content pattern | Box with progress |
pagination | LazyColumn with Pager | Paging 3 integration |
caching-strategy | Repository layer caching | Cached repository pattern |
Code Organization Patterns
| Pattern | Detected By | Example |
|---|---|---|
feature-module | Self-contained feature folders | feature/auth/ structure |
shared-UI | Reusable Composables | ui/components/ |
test-mirroring | Test structure matching src | Parallel test folders |
naming-convention | Consistent naming patterns | XxxViewModel, XxxScreen |
Observation Windows
V2 uses sliding windows for pattern detection:
Window 1 (Current Session): Immediate patterns
Window 2 (Last 5 Sessions): Emerging patterns
Window 3 (Last 20 Sessions): Established patterns
Window 4 (All Time): Core patternsConfidence Evolution
Session 1-3: Experimental (0.1-0.3)
Session 4-10: Validating (0.3-0.6)
Session 11-20: Established (0.6-0.8)
Session 20+: Best Practice (0.8-1.0)Commands
View Observations
/instinct-status --v2
/instinct-status --observationsShows:
- Recent session observations
- Emerging patterns (low confidence)
- Established patterns (high confidence)
- Pattern clusters by domain
Manual Observation
/instinct-observe "Used Ktor with retry pattern for API calls"Manually add an observation for pattern learning.
Integration
V2 instincts are evaluated by: 1. Session hooks: hooks/instinct-hooks.json Stop event 2. Pattern extractor: agents/mobile-pattern-extractor.md 3. Pre-compact preservation: Maintains learning during context compression
Difference from V1
| Aspect | V1 | V2 |
|---|---|---|
| Trigger | Code write | Session observation |
| Scope | Single file | Cross-file patterns |
| Timing | Immediate | End of session |
| Focus | Code patterns | Architectural patterns |
---
Remember: V2 needs multiple sessions to build confidence. The more you develop, the smarter it gets.
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
How is v2 different from v1?
V1 captures code patterns immediately per file; v2 observes at session end and extracts cross-file architectural patterns over multiple sessions.
How does confidence evolve?
Patterns move from experimental (0.1-0.3) in sessions 1-3 to best practice (0.8-1.0) after 20+ sessions as they recur.