Iterating With AI And MCP

Iterating With AI And MCP is an AI Engineering skill for Claude Code, published by skydoves in compose-performance-skills.

492 stars17 forkson skydoves/compose-performance-skillsAdded 2026/08/26+1% in starsRepository updated 2026/06/16

View source on GitHub Download repo ZIP

agent-skillsandroidclaudeclaude-codecomposecompose-performancejetpack-composekotlinllm-toolsrecompositionskydoves

Install in seconds

Install Iterating With AI And MCP

Copy Iterating With AI And MCP into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/skydoves/compose-performance-skills/tree/main/hot-reload/iterating-with-ai-and-mcp ~/.claude/skills/iterating-with-ai-and-mcp

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/skydoves/compose-performance-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: hot-reload/iterating-with-ai-and-mcp/SKILL.md in skydoves/compose-performance-skills
Installs to: ~/.claude/skills/iterating-with-ai-and-mcp
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Iterating With AI And MCP does

Iterating With AI And MCP lets an AI agent edit a Kotlin file, hot reload the app, take screenshots, and compare results to a design intent. Use it for autonomous Compose UI iteration, snapshot rollback, and full-install fallback when schema changes break reloads.

Iterating With AI And MCP is cataloged under AI Engineering on DirSkills. Iterating With AI And MCP comes from a repository tagged agent-skills, android, claude, claude-code and compose.

Documentation

README

Excerpt

Iterating with AI and MCP: let the agent edit, reload, screenshot, and iterate

Compose HotSwan ships an embedded HTTP MCP server inside the IntelliJ plugin. Any MCP-compatible AI client (Claude Code, Cursor, any tool that speaks Model Context Protocol) can call its tools to drive the iteration loop. The agent edits a Kotlin file, calls hotswan_reload, captures a screenshot of the running device, evaluates the result against the design intent, and decides the next change. Cycle time is comparable to the human loop, a few seconds per iteration, so the agent can converge on a UI tweak without a human steering each step.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Iterating With AI And MCP

What else does skydoves publish alongside Iterating With AI And MCP?
Iterating With AI And MCP is one of 25 skills that DirSkills catalogs from skydoves/compose-performance-skills, the repository it ships in. Its siblings there include Auditing Compose Performance, Avoiding Subcomposition Pitfalls and Choosing DerivedStateOf. Each one is a separate skill with its own page in this directory, installs the same way Iterating With AI And MCP does, and is maintained by skydoves in that same repository. The rest of the collection is listed on the skydoves/compose-performance-skills page.
How does Iterating With AI And MCP compare to other AI Engineering skills?
Iterating With AI And MCP ranks #2180 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Iterating With AI And MCP against them. Open each page to compare what they document and how they install.