From bolster
Andrew Bolster's development environment — toolchain, aliases, shell setup, and key patterns
How this skill is triggered — by the user, by Claude, or both
Slash command
/bolster:dev-environmentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
| Tool | Role | Notes |
| Tool | Role | Notes |
|---|---|---|
| yadm | Dotfiles manager | yadm status, yadm add, yadm push |
| zsh + Oh My Zsh | Shell | Starship prompt; aliases in ~/.config/zsh/aliases.zsh |
| Neovim (LazyVim) | Editor | nv or vim alias; LazyVim config |
| tmux / byobu | Terminal multiplexer | Ctrl-A prefix; byo, byos, byoa aliases |
| mamba/miniforge3 | Python env manager | macOS: ~/miniforge3; Linux: ~/miniconda3 |
| bun | Node.js package manager | ~/.bun/bin in PATH |
| uv | Python tool/script runner | Always use uv run — see uv-run skill |
| bob | Neovim version manager | ~/.local/share/bob/nvim-bin in PATH |
# Git
gs='git status' ga='git add' gc='git commit'
gp='git push' gl='git log --oneline --graph'
# Yadm (dotfiles)
ys='yadm status' ya='yadm add' yc='yadm commit' yp='yadm push'
# Dev
nv='nvim' vim='nvim' py='python3'
# Claude
claude='claude-titled --dangerously-skip-permissions'
# Byobu
byo='byobu' byos='byobu new-session' byoa='byobu attach'
# Safety (confirm before destructive ops)
rm='rm -i' cp='cp -i' mv='mv -i'
$HOME/bin
$HOME/.local/bin
$HOME/.cargo/bin
/usr/local/bin
$HOME/.claude/local # Claude Code local bin
$HOME/.local/share/bob/nvim-bin
$HOME/.bun/bin
/opt/homebrew/opt/ruby/bin
When searching with filesystem tools, never search the entire home directory — it can trigger security systems. Restrict searches to:
~/scratch and subdirectories~/src/<project>)~/.claude/)Loaded from ~/google-cloud-sdk/ if present. Completion available for zsh.
/opt/homebrew/share/zsh/site-functions/opt/homebrew/opt/ruby/bin if installed~/.docker/completionsnpx claudepluginhub bd-vitalstatistix/claude-marketplace --plugin bolsterProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.