raine/skills

auto

Autonomously create a plan, consult Gemini and Codex for improvements, apply feedback, and implement. No user interaction - uses best judgment throughout.

brainstorm

Turn an idea into a concrete design through structured dialogue.

collab

Gemini and Codex collaboratively brainstorm solutions, building on each other's ideas across rounds. Agent synthesizes the best ideas into a plan.

collab-vs

Claude brainstorms with an opponent LLM (Gemini or Codex) in alternating turns, building on each other's ideas. Synthesizes the best ideas into a plan.

commit

Commit the staged changes. If there are no staged changes, stage all changes first.

consult-auto

Consult Gemini and Codex for high-level planning, synthesize into a detailed plan, implement, then get final review. No user interaction.

consult

Consult an external LLM with the user's query.

copy-to-slack

Convert markdown to Slack-ready rich text and copy to clipboard.

cs

Commit all pending changes as separate, logical commits using git-surgeon.

debate

LLMs propose and critique approaches, agent moderates the debate and synthesizes the best solution, then implements.

debate3

Three-way LLM debate (Gemini, Codex, MiniMax) — each proposes, critiques the other two, then agent moderates and implements.

deep-investigate

Orchestrates a multi-phase investigation that produces a directory of deeply-researched section documents instead of one shallow summary.

git-surgeon

Non-interactive hunk-level git staging, unstaging, discarding, undoing, fixup, amend, squash, commit splitting, and commit reordering. Use when selectively staging, unstaging, discarding, reverting, squashing, splitting, or reordering individual diff hunks by…

open

Find dev servers running in tmux panes and open them in the browser. Accepts optional freetext to identify which server, or a path starting with /. Use when the user wants to open a dev server, find running servers, or open localhost.

pilot

Autonomous agent that navigates any task from start to finish. Explores the codebase, classifies complexity, adaptively consults external LLMs for planning or brainstorming, implements with incremental commits, and gets LLM review.

qc

Stage all changes and commit directly without checking status or diff.

rebase

Rebase the current branch.

review

Review pending changes with external LLMs (Gemini, Codex, Claude, or all).

step

Walk through a multi-point topic step by step, pausing after each point to discuss with the user before continuing.

step-verify

Verify review findings one by one, pausing after each to discuss with the user before continuing.

try-all

Delegate each of the proposed options to a separate AI agent in its own git worktree.

update-pr

Update the current PR description based on the latest changes in context.

verify

Manually verify review findings one by one by running code, writing adhoc scripts, and comparing actual behavior instead of implementing blindly.

worktree

Launch one or more tasks in new git worktrees using workmux.

write-plan-consult

Create an implementation plan by brainstorming with Gemini and Codex, synthesizing the best ideas, then getting their review.

write-plan

Create an implementation plan for a multi-step task. Optionally review with external LLMs.

bash-script-writer

Use it when creating a bash script or editing a bash script

blog-media-processor

Use it when user asks to add images, photos, or videos to a blog post

coordinator

Orchestrate multiple worktree agents -- spawn, monitor, communicate, and merge.

debate-vs

Claude debates an opponent LLM (Gemini or Codex) through multi-turn MCP conversation, then synthesizes the best approach and implements.

merge

Commit, rebase, and merge the current branch.

test-writer

Use it when writing or editing test files

tmux-dev

Develop and test TUI/CLI applications by driving a tmux pane as a live test terminal. Use this skill when building interactive terminal apps (TUIs, CLIs with interactive prompts, curses/ratatui apps, REPL tools) so you can start the app, send keystrokes,…