メニュー
Use this skill when you need to know what keybindings are available in mandelbot, or the user asks about keyboard shortcuts. Read-only reference — to change prefix modifiers, use the mandelbot-config skill instead.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | mandelbot-keybindings |
| description | Use this skill when you need to know what keybindings are available in mandelbot, or the user asks about keyboard shortcuts. Read-only reference — to change prefix modifiers, use the mandelbot-config skill instead. |
| allowed-tools | ["Read"] |
This skill is a read-only reference for the keybindings available in mandelbot. All bindings use configurable modifier prefixes set in ~/.mandelbot/config.json (see the mandelbot-config skill to change them).
| Prefix | Config key | Default |
|---|---|---|
| Control | control_prefix | ctrl+shift |
| Movement | movement_prefix | alt+shift |
To know the user's actual prefixes, read ~/.mandelbot/config.json. If the file doesn't exist or a key is absent, use the default.
| Key | Action | Description |
|---|---|---|
control + t | New shell tab | Opens a plain shell tab |
control + Space | Spawn agent | Creates a new agent tab (project-level or task under current project) |
control + ↓ | Spawn agent | Same as Space — alternate binding |
control + → | Spawn child task | Creates a child task tab under the current agent |
control + w | Close tab | Closes the focused tab |
control + c | Copy | Copies the current terminal selection to clipboard |
control + v | Paste | Pastes clipboard contents into the terminal |
control + Click | Open link | Opens the URL under the cursor in the system browser |
| Key | Action | Description |
|---|---|---|
movement + ↓ | Next sibling | Focus the next tab at the same tree level |
movement + ↑ | Previous sibling | Focus the previous tab at the same tree level |
movement + → | First child | Navigate deeper into the tab tree |
movement + ← | Parent | Navigate up to the parent tab |
movement + Space | Next idle | Jump to the next idle agent (priority: blocked → needs review → idle task → idle project) |
movement + - | Previous tab | Toggle back to the previously focused tab |
movement + 0-9 | Select by index | Focus the tab at position 0–9 in display order |
Use this skill from a project or task tab to map the user's open PRs onto a tree of tabs — one tab per conceptual group of authored PRs (with per-PR leaf tabs), plus a separate subtree for PRs awaiting the user's review. Good for starting the day, triaging in-flight work, or catching up after being away.
Use this skill when you have work that can be broken into parallel subtasks and delegated to child agents. Activates when you need to coordinate multiple agents working on different parts of a plan simultaneously.
Use this skill when your prompt references a coordination file and assigns you a task. You are a subtask agent — part of a larger coordinated effort. Follow the protocol to read your assignment, do your work, and report progress.
Use this skill from a project tab when the user wants to be notified about GitHub PR activity in this project's repo — a PR newly requests their review, or a PR they authored gets a review decision change. Polls `gh` in the background and raises one toast per affected PR via the `notify` MCP tool; the Open button spawns a task-tab child in this project's worktree.
Use this skill when correctness is adversarial — a persistent builder agent writes code while fresh breaker agents each round probe it and report what's broken, looping until the breaker reports clean or a round cap is hit. Good fit for algorithm-heavy, parser, or security-adjacent work where "what could go wrong" is the real risk and a single implementer is likely to miss cases.
Use this skill for iterative build-refactor-build loops where a parent agent delegates work to generation tabs, harvests ideas, and spawns another generation acting on the best ones. Activates when the user wants to "keep improving X", run "another pass", do "iterative refinement", or loop until some fitness signal is met. Not for one-shot feature work — use mandelbot-delegate for that.
