Menu
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/diegosouzapw/awesome-omni-skill --skill makefileThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Showing SKILL.md
| name | makefile |
| description | Makefile structure and install workflow |
| metadata | {"globs":"Makefile"} |
Installation constraint: Always use the Makefile for installing tools and applications. Never run brew install, npm install -g, or other package manager commands directly — the Makefile is the single source of truth for what is installed and how it is configured.
Structure targets to be self-documenting: the target name should clearly indicate its purpose, avoiding the need for comments.
terminal: Shell and terminal tools (fish, tmux, nvim, wezterm...)work: Development tools (cursor, docker, gh, terraform...)personal: Personal apps (obsidian, rust, spotify...)utils: Utility applications (cleanshot, keycast...)brew and the binary path~/.dotfiles/ to ~/.config/ or ~/${BREW_BIN} and ${APP_BIN} variables for paths.app) are macOS-only; CLI tools should work on both macOS and Linuxnewtool: brew ${BREW_BIN}/newtool
${BREW_BIN}/newtool:
brew install newtool
Note: Homebrew works on both macOS and Linux. For Linux-only alternatives, consider adding conditional targets.
When adding a new tool: (1) add it to the Makefile in the right section, (2) run make <tool-name>. Do not install via brew install or npm install -g outside the Makefile.
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
AshAi extension guidelines for integrating AI capabilities with Ash Framework. Use when implementing vectorization/embeddings, exposing Ash actions as LLM tools, creating prompt-backed actions, or setting up MCP servers. Covers semantic search, LangChain integration, and structured outputs.
This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claude analysis needs deeper reasoning or extended context windows.
Based on SOC occupation classification
