sebastienrousseau/dotfiles/dotfiles-bootstrap

dotfiles-bootstrap

Provision a new workstation from a public dotfiles repository through the `sebastienrousseau/dotfiles` harness.

This skill is for Claude Code to invoke dot config init <user> on the user's behalf — most useful when the user says "set me up like Alice" or "bootstrap a fresh laptop using my GitHub dotfiles."

What this skill does

When invoked, it:

1. Verifies the target argument is one of:

• a GitHub username (e.g. alice → expands to github.com/alice/dotfiles)
• an owner/repo pair (e.g. alice/configs)
• a full HTTPS or git@host:path clone URL

1. Refuses plain http:// URLs (no transit integrity).
2. Reads the user's current agent profile from $DOT_AGENT_PROFILE (defaults to ask):

• ask → run dot config init <user> --dry-run (read-only preview)
• plan → run dot config init <user> --dry-run and explain the plan
• apply → run dot config init <user> --yes (full apply with chezmoi apply), only after the user has confirmed they trust the repository
• audit → run dot config init <user> --no-apply --yes (clone only, no chezmoi apply), after the same confirmation

An agent has no terminal, so dot config init refuses to clone without --yes. Pass it only once the user has said yes to this repository.

1. Surfaces the trust prompt warnings before any clone runs — the target repo's scripts execute with the user's privileges.
2. Reports the outcome (success / failed / aborted-by-trust-prompt) so the user can decide next steps.

Invocation pattern

# canonical
dot config init <user>                       # github.com/<user>/dotfiles
dot config init <owner>/<repo>               # github.com/<owner>/<repo>
dot config init <https-or-ssh-url>           # explicit URL
 
# safety flags
dot config init <user> --dry-run             # preview only
dot config init <user> --no-apply            # clone, skip chezmoi apply
dot config init <user> --force               # overwrite existing chezmoi source dir
dot config init <user> --yes                 # consent without a terminal (required by agents)

Profile-aware defaults

Failure modes the skill surfaces

• chezmoi not installed → instruct user to run install.sh first
• URL refuses HTTPS check → ask user for explicit confirmation if SSH
• Target chezmoi source dir already exists → ask user about --force
• Trust prompt aborted → return cleanly, no state mutation
• chezmoi init non-zero exit → surface the chezmoi stderr to the user

Why this skill exists

Closes the round-1 audit's adoption gap "bootstrap a foreign dotfiles repo through this framework's harness." Without the skill, a Claude Code session has to remember the right flag set for the user's current trust posture; with the skill, the profile dictates the safe default.

References

• dot config init source: `plugins/config/libexec/init.sh`
• Roadmap entry: ROADMAP_2026 §B2
• AGENTS.md / CLAUDE.md sync: dot agent context apply