askill
mobile-instinct-v2

mobile-instinct-v2Safety 100Repository

V2 instinct-based observational learning. Analyzes sessions to extract reusable mobile development patterns across time.

19 stars
1.2k downloads
Updated 2/4/2026

Package Files

Loading files...
SKILL.md

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

PatternDetected ByExample
layer-separationConsistent data/ui/domain separationRepository + ViewModel + Composable
dependency-injectionKoin module patternsfactoryOf, viewModel
navigation-patternCompose Navigation usageNavHost with routes
state-managementMVI/MVVM consistencyStateFlow + sealed classes

Problem-Solution Patterns

PatternDetected ByExample
error-boundaryTry-catch with UI feedbackError state in Composable
loading-stateisLoading + Content patternBox with progress
paginationLazyColumn with PagerPaging 3 integration
caching-strategyRepository layer cachingCached repository pattern

Code Organization Patterns

PatternDetected ByExample
feature-moduleSelf-contained feature foldersfeature/auth/ structure
shared-UIReusable Composablesui/components/
test-mirroringTest structure matching srcParallel test folders
naming-conventionConsistent naming patternsXxxViewModel, 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 patterns

Confidence 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 --observations

Shows:

  • 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

AspectV1V2
TriggerCode writeSession observation
ScopeSingle fileCross-file patterns
TimingImmediateEnd of session
FocusCode patternsArchitectural patterns

Remember: V2 needs multiple sessions to build confidence. The more you develop, the smarter it gets.

Install

Download ZIP
Requires askill CLI v1.0+

AI Quality Score

88/100Analyzed 2/13/2026

A detailed specification for an observational learning system ('Mobile Instinct v2') that analyzes development sessions to extract architectural and problem-solving patterns. It includes clear definitions of pattern categories, confidence scoring, and interaction commands.

100
95
60
90
85

Metadata

Licenseunknown
Version-
Updated2/4/2026
Publisherahmed3elshaer

Tags

apici-cdgithub-actionssecuritytesting