raine

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

Turn an idea into a concrete design through structured dialogue.

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

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

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

Consult an external LLM with the user's query.

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

How to invoke the consult-llm CLI. Canonical reference for the invocation contract, flags, stdin/stdout format, and multi-turn. Load this before calling consult-llm from any workflow skill (/consult, /collab, /debate, /collab-vs, /debate-vs).

Explicit workflow for one bounded implementation using source-grounded discovery, a walking slice, evidence-gated review, validation, and commit. Use only when the user invokes `/implement` or another skill explicitly delegates to it. Do not trigger for…

Coordinator workflow for multi-phase implementation across workmux worktrees. Generates or loads a master plan, dispatches phase agents using presets, verifies sentinels, merges serially, and performs integration verification.

Consult an external LLM with the user's query.

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

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

Standalone multi-model code review of an existing diff. Multiple LLMs review in parallel; agent deduplicates, prioritizes by severity/confidence, and optionally applies localized fixes.

Interactive design session — agent facilitates a clarifying dialogue with the user, fans out to multiple LLMs in parallel for divergent approach generation, lets the user pick one, then co-designs the chosen approach with optional multi-LLM critique before…

Orchestrate multiple worktree agents. Spawn, monitor, communicate, and merge.

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

Reference for the workmux CLI that manages git worktrees and tmux windows as isolated development environments. Use when the user mentions workmux, worktrees, or parallel agent workflows.

Commit, rebase, and merge the current branch.

Rebase the current branch with smart conflict resolution.

Write a PR description using conversation context and open PR creation in browser.

Decide whether an incoming email requires local follow-up, update one task per thread, and dispatch investigation when useful.

Create local follow-up and dispatch an isolated investigation for a new GitHub issue or pull request from a discovered repository.

Find, browse, read, or quote prior Claude Code conversations with the claude-history CLI.

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

Use when an agent needs to operate the `aven` CLI in this repository: finding tasks, creating tasks, working with image attachments, updating status, adding notes, managing projects or labels, working with workspaces, or resolving conflicts.

Create or open an Obsidian note, attach hidden writing context, and focus the note for the user through the Steer CLI.

Return a deterministic marker for pi-suba Cua isolation tests.

Operate Tori.fi and Vinted with flea.