Meet-Miyani/compose-skill
Compose Skill (Compose Kit): agent skills for Jetpack Compose & Compose Multiplatform. Makes Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode write better Compose: MVI, Koin, Navigation 3, Ktor, Room. Tested blind on 5 models in
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit Meet-Miyani/compose-skill/skills ./rig-compose-skill/skills MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit Meet-Miyani/compose-skill/skills/compose-architecture .claude/skills/compose-architecture $ npx degit Meet-Miyani/compose-skill/skills/compose-data .claude/skills/compose-data $ npx degit Meet-Miyani/compose-skill/skills/compose-feature .claude/skills/compose-feature $ npx degit Meet-Miyani/compose-skill/skills/compose-platform .claude/skills/compose-platform $ npx degit Meet-Miyani/compose-skill/skills/compose-project .claude/skills/compose-project $ npx degit Meet-Miyani/compose-skill/skills/compose-ui .claude/skills/compose-ui $ npx degit Meet-Miyani/compose-skill/skills/compose .claude/skills/compose
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (7)
Cursor rules (1)
reference-file-standards
Similar rigs
drader/researcher_agent
An LLM-driven research assistance framework for Claude Code (CC BY-NC 4.0)
Pragmatist 1.9k tok ·
abmach/maestro
Agent Skills bundle that gives AI coding agents a plan → parallel-implement → test → document workflow. Works with Oh My Pi, Claude Code and OpenCode.
Skill Collector 818 tok ·
JeremiahM37/lectern
Self-hosted control plane for coding agents. Run Claude Code, Codex, Gemini and other agents across your workstations, SSH servers and sandboxes; supervise from your terminal or phone.
Skill Collector 1.1k tok ·
cacardinal/laila
Laila is an operating system for a life run with AI agents. Your world as plain files: domains, memory, hard autonomy lines, background loops. Works on any harness that can read a repo. Private by design; reference implementation on Claude
Orchestrator 5.7k tok ·