Continuous Learning V2
- 21 installs
- 60 repo stars
- Updated June 14, 2026
- ahmed3elshaer/everything-claude-code-mobile
continuous-learning-v2 is a Claude Code skill that stores mobile-development patterns as confidence-scored instincts and evolves them across sessions.
About
continuous-learning-v2 is a Claude Code skill that stores reusable mobile-development patterns as confidence-scored instincts and evolves them over time. A developer uses it so the agent remembers accepted conventions (state hoisting, MVI, Koin organization) and reapplies them on later sessions. It exposes commands to view, import, export, and cluster instincts, and raises confidence as patterns get reused successfully.
- Confidence-scored instinct store that evolves reusable mobile patterns across sessions
- Ships slash commands to import, export, and cluster instincts
- Pre-loaded with Compose, MVI, Koin, Ktor, and Espresso pattern instincts
Continuous Learning V2 by the numbers
- 21 all-time installs (skills.sh)
- Ranked #10,307 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
continuous-learning-v2 capabilities & compatibility
- Capabilities
- agent memory · pattern learning · instinct management
- Use cases
- memory
What continuous-learning-v2 says it does
Instinct-based learning system with confidence scoring for mobile patterns. Automatically extracts and evolves patterns.
**Remember**: Instincts evolve. Low confidence patterns may become best practices.
npx skills add https://github.com/ahmed3elshaer/everything-claude-code-mobile --skill continuous-learning-v2Add 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
Persist and evolve confidence-scored mobile coding patterns so the agent reapplies accepted conventions across sessions.
Who is it for?
Teams that want the coding agent to remember and reuse accepted mobile conventions over time
When should I use this skill?
You want the agent to capture, score, and reapply mobile coding patterns across sessions
What you get
Reusable mobile patterns are stored with confidence scores and reapplied automatically.
By the numbers
- 4-band confidence scale (0.0-1.0)
- 4 instinct commands (status, import, export, evolve)
Files
Continuous Learning v2
Instinct-based learning with confidence scoring.
Instinct Structure
{
"id": "compose-state-hoisting",
"type": "pattern",
"description": "Always hoist state to caller in Composables",
"confidence": 0.85,
"examples": [...],
"context": "jetpack-compose",
"lastUsed": "2026-02-02"
}Confidence Scoring
| Score | Meaning |
|---|---|
| 0.0-0.3 | Experimental |
| 0.3-0.6 | Validated |
| 0.6-0.8 | Established |
| 0.8-1.0 | Best practice |
Confidence increases with:
- Successful application
- User acceptance
- Consistency across sessions
Commands
/instinct-status # View with confidence
/instinct-import <file> # Import from others
/instinct-export # Export for sharing
/evolve # Cluster related instinctsMobile-Specific Instincts
Pre-configured patterns for:
- Compose recomposition optimization
- MVI state management
- Koin module organization
- Ktor error handling
- Espresso test patterns
---
Remember: Instincts evolve. Low confidence patterns may become best practices.
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 does confidence scoring work?
Scores run 0.0-1.0 across four bands (experimental, validated, established, best practice) and increase with successful application, user acceptance, and consistency across sessions.
Can I share instincts with others?
Yes. The /instinct-export command exports instincts for sharing and /instinct-import imports them from a file.