raine
- 70 skills
- 0 followers
- 2 repo stars
- last month last updated
- ▌
- ▌
- ▌ Workmux 2 · raineReference 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.
- ▌
- ▌
- ▌ Collab 3 · raineGemini and Codex collaboratively brainstorm solutions, building on each other's ideas across rounds. Agent synthesizes the best ideas into a plan.
- ▌ Debate 3 · raineLLMs propose and critique approaches, agent moderates the debate and synthesizes the best solution, then implements.
- ▌
- ▌
- ▌ Collab Vs 3 · raineClaude brainstorms with an opponent LLM (Gemini or Codex) in alternating turns, building on each other's ideas. Synthesizes the best ideas into a plan.
- ▌ Debate Vs 3 · raineClaude debates an opponent LLM (Gemini or Codex) through multi-turn MCP conversation, then synthesizes the best approach and implements.
- ▌ Git Surgeon 2 · raineNon-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 ID instead of interactively.
- ▌ Panel 2 · raineRole-specialized LLM panel analyzes a task from asymmetric expert lenses (architect, security, maintainability, test-strategist by default). Agent synthesizes a trade-off resolution.
- ▌ Collab 2 · raineMultiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds. Agent synthesizes the best ideas into a plan.
- ▌ Debate 2 · raineLLMs propose and critique approaches, agent moderates the debate and synthesizes the best solution, then implements.
- ▌ Review 2 · raineCollect critical feedback from all registered LLMs on an artifact (architecture doc, implementation, plan). Intellectual debate with push-back — no sycophancy. Reports findings and unresolved disagreements.
- ▌
- ▌ Workshop 2 · raineInteractive 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 saving.
- ▌ Collab Vs 2 · raineThe agent brainstorms with a partner LLM in alternating turns, building on each other's ideas. Synthesizes the best ideas into a plan.
- ▌ Debate Vs 2 · raineThe agent debates an opponent LLM through a multi-turn conversation, then synthesizes the best approach and implements.
- ▌ Implement 2 · raineExplicit 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 ordinary coding requests, follow-up edits, fixes with an established design, or requests to amend an existing commit.
- ▌ Consult LLM 2 · raineHow 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).
- ▌ Review Panel 2 · raineStandalone multi-model code review of an existing diff. Multiple LLMs review in parallel; agent deduplicates, prioritizes by severity/confidence, and optionally applies localized fixes.
- ▌ Phased Implement 2 · raineCoordinator 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.
- ▌
- ▌ Email Triage · raineHandle non-GitHub email that may require local follow-up, task updates, or investigation.
- ▌ Github Investigation · raineHandle a new GitHub issue or pull request, or substantive follow-up activity, with an isolated investigation.
- ▌ Auto · raineAutonomously create a plan, consult Gemini and Codex for improvements, apply feedback, and implement. No user interaction - uses best judgment throughout.
- ▌ Open · raine bundleFind 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.
- ▌ Step · raineWalk through a multi-point topic step by step, pausing after each point to discuss with the user before continuing.
- ▌
- ▌ Pilot · raineAutonomous 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.
- ▌
- ▌
- ▌ Verify · raineManually verify review findings one by one by running code, writing adhoc scripts, and comparing actual behavior instead of implementing blindly.
- ▌ Debate3 · raineThree-way LLM debate (Gemini, Codex, MiniMax) — each proposes, critiques the other two, then agent moderates and implements.
- ▌ Try All · raineDelegate each of the proposed options to a separate AI agent in its own git worktree.
- ▌ Workmux · raineReference 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.
- ▌ Tmux Dev · raine bundleDevelop 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, capture the screen, and verify output yourself — without asking the user to test manually. Also use this when the user says things like "check it yourself", "try running it", "see if it works", or when you need to visually verify terminal output.
- ▌
- ▌
- ▌
- ▌ Write Plan · raineCreate an implementation plan for a multi-step task. Optionally review with external LLMs.
- ▌
- ▌ Step Verify · raineVerify review findings one by one, pausing after each to discuss with the user before continuing.
- ▌
- ▌ Consult Auto · raineConsult Gemini and Codex for high-level planning, synthesize into a detailed plan, implement, then get final review. No user interaction.
- ▌
- ▌ Deep Investigate · raineOrchestrates a multi-phase investigation that produces a directory of deeply-researched section documents instead of one shallow summary.
- ▌
- ▌ Write Plan Consult · raineCreate an implementation plan by brainstorming with Gemini and Codex, synthesizing the best ideas, then getting their review.
- ▌
- ▌
- ▌
- ▌ Steer · raineCreate or open an Obsidian note, attach hidden writing context, and focus the note for the user through the Steer CLI.
- ▌ Claude History · raineFind, browse, read, or quote prior Claude Code conversations with the claude-history CLI.
- ▌
- ▌ Git Surgeon · raineNon-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 ID instead of interactively.
- ▌ Panel · raineRole-specialized LLM panel analyzes a task from asymmetric expert lenses (architect, security, maintainability, test-strategist by default). Agent synthesizes a trade-off resolution.
- ▌ Collab · raineMultiple LLMs collaboratively brainstorm solutions, building on each other's ideas across rounds. Agent synthesizes the best ideas into a plan.
- ▌ Debate · raineLLMs propose and critique approaches, agent moderates the debate and synthesizes the best solution, then implements.
- ▌ Review · raineCollect critical feedback from all registered LLMs on an artifact (architecture doc, implementation, plan). Intellectual debate with push-back — no sycophancy. Reports findings and unresolved disagreements.
- ▌
- ▌ Workshop · raineInteractive 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 saving.
- ▌ Collab Vs · raineThe agent brainstorms with a partner LLM in alternating turns, building on each other's ideas. Synthesizes the best ideas into a plan.
- ▌ Debate Vs · raineThe agent debates an opponent LLM through a multi-turn conversation, then synthesizes the best approach and implements.
- ▌ Implement · raineExplicit 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 ordinary coding requests, follow-up edits, fixes with an established design, or requests to amend an existing commit.
- ▌ Consult LLM · raineHow 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).
- ▌ Review Panel · raineStandalone multi-model code review of an existing diff. Multiple LLMs review in parallel; agent deduplicates, prioritizes by severity/confidence, and optionally applies localized fixes.
- ▌ Phased Implement · raineCoordinator 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.