compose-skill — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by aldefy · MCP Server · ★ 561

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is compose-skill safe to install? View the security audit →

About compose-skill

Compose Agent Skill Make your AI coding tool actually understand Compose — Android, Desktop, iOS, and Web. Backed by real source code from androidx/androidx and compose-multiplatform-core — not vibes. The problem AI coding tools generate Compose code that compiles but gets the details wrong. Incorrect usage, unstable recompositions, broken modifier ordering, deprecated navigation patterns, hallucinated APIs that don't exist. They guess at behavior instead of knowing it. This skill fixes that by giving your AI assistant two things:

agent-skillai-agentai-codingandroidandroidxclaude-codeclaude-skillcodexcomposecompose-expert

Quick Facts

Stars561
Forks34
LanguageKotlin
CategoryMCP Server
Quality Score66.578647081444/100
Open Issues1
Last Updated2026-07-23
Created2026-02-28
Platformsclaude-code, cli, codex, gemini, mcp
Est. Tokens~19k

Compatible Skills

These tools work well together with compose-skill for enhanced workflows:

  • claude-android-ninja — semantic(0.55)+complementary+rare_topics+similar_pop+shared_platform (69%)
  • FantasyPremierLeague — semantic(0.44)+complementary+rare_topics+similar_pop (60%)
  • GalwayBus — semantic(0.38)+complementary+rare_topics+similar_pop (57%)
  • Kai — semantic(0.35)+complementary+rare_topics+similar_pop (51%)
  • awesome-android-agent-skills — semantic(0.43)+complementary+similar_pop+shared_platform (50%)

compose-skill alternative? Top 6 similar tools

Looking for a compose-skill alternative? If you're comparing compose-skill with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • Overture by SixHq · ⭐ 641

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • antigravity-workspace-template by study8677 · ⭐ 1.3k

    Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A wi

  • memorix by AVIDS2 · ⭐ 797

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • compose-skill by Meet-Miyani · ⭐ 275

    AI agent skill for Jetpack Compose & Compose Multiplatform (KMP/CMP). MVI architecture, Navigation 3, Koin/Hil

  • pairlet by heypandax · ⭐ 132

    Pairlet (formerly CC Pocket / cc-pocket) — Continue your local AI coding tasks from phone, tablet, or desktop.

  • cc-pocket by heypandax · ⭐ 117

    Drive Claude Code or OpenAI Codex from your phone — resume sessions, stream output, approve tool permissions r

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Kotlin Agent Tools

Frequently Asked Questions

What is compose-skill?

compose-skill is Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, Copilot, Windsurf, and more.. It is categorized as a MCP Server with 561 GitHub stars.

What programming language is compose-skill written in?

compose-skill is primarily written in Kotlin. It covers topics such as agent-skill, ai-agent, ai-coding.

How do I install or use compose-skill?

You can find installation instructions and usage details in the compose-skill GitHub repository at github.com/aldefy/compose-skill. The project has 561 stars and 34 forks, indicating an active community.

What are the best alternatives to compose-skill?

The top alternatives to compose-skill on Agent Skills Hub include Overture, antigravity-workspace-template, memorix. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools