CLAUDE

Shift+Enter, Option+Enter, or backslash+Enter for multi-line prompts.

Context-aware follow-up suggestions derived from git history.

Ask quick side questions without derailing the main task.

Read file contents with line limiting, offset, and binary support.

Create or overwrite files; requires permission for existing paths.

Targeted edits to specific sections without rewriting entire files.

Batch edit multiple files in a single atomic operation.

Modify Jupyter notebook cells directly without touching JSON.

File discovery via pattern matching across the repository.

Search file contents by pattern with regex support.

Jump to definitions, find references, and type-check via language servers.

Execute shell commands with persistent working directory in project bounds.

Native PowerShell execution on Windows and optionally Unix hosts.

Background monitoring of logs, files, and long-running processes.

SessionStart hooks can persist env vars across Bash tool calls.

Stage, commit, branch, and open PRs without leaving the session.

Isolated git worktrees for parallel Claude Code sessions.

A practical walk-through of how to design, write, and ship a Claude Code skill - from choosing when to trigger, through allowed-tools, to the steps the agent will actually follow.

Clickable PR link in the footer with review state color coding.

A concrete step-by-step guide to moving your development workflow from Cursor to Claude Code - settings, rules, keybindings, and the habits that transfer.