Composable Agent Skills that help AI agents package Docker/OCI container images and Linux binaries as strictly-confined snaps. Includes snap-oci-container for end-to-end orchestration, analyze-binary-for-snapping for inferring plugs and layouts from syscalls and paths, and snap-iteration-workflow for LXD build, run, and verify cycles.
npx add-skill lorenzo-medici/snapping-skillsComposable Agent Skills that help AI agents package Docker/OCI container images and Linux binaries as strictly-confined snaps. Includes snap-oci-container for end-to-end orchestration, analyze-binary-for-snapping for inferring plugs and layouts from syscalls and paths, and snap-iteration-workflow for LXD build, run, and verify cycles.
54 production principles for AI-assisted coding. The clean-code bible across FastAPI, Next.js 15, and Go. Copy CLAUDE.md + .cursor/rules + .claude/skills into your project — your AI agent builds it right from line one.
Multi-model AI command center: one Coordinator (Chrono — Claude) routes work to 5 Department Leads each running its own CLI (Codex/Claude/Gemini/Claude/Kimi) in dedicated tmux panes. Mailbox-mediated, subscription-billed (Max/ChatGPT/Gemini OAuth/Kimi), vibecoder-friendly.
FlowMux — Agent Workflow Multiplexer Terminal. Go with the agents' flow.
🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design Systems 🖼️ Web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Claude Code / OpenClaw / Codex / Cursor / OpenCode / Qwen / Copilot / Hermes / Kimi & 17+ CLIs.
Agent Skill for building, manipulating, executing, and version-controlling Jupyter notebooks programmatically. Cell CRUD, parameterised execution (papermill), validation, output management, and git-friendly diffing (nbdime). Works with Claude Code, Codex, Cursor, Copilot, and any SKILL.md-compatible agent.
Local-first context hygiene for AI coding agents — Claude Code plugin plus shell helpers for large reads, noisy output, redaction, artifacts, and measured token/cost evidence.