القائمة
Use when the user asks to run Qwen CLI in non-interactive mode or references Qwen Code for AI-assisted coding tasks.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use when installing, reinstalling, auditing, or preparing Brain-managed Superpowers, Spec Kit, and OpenSpec workflow arsenals under a project-local `.brain/vendor` directory so Brain can inspect and route them without exposing their raw Codex skills/prompts at the project root.
Use when the user asks to check, add, or manage macOS Calendar events.
Use when the user asks to send an email via the macOS Mail app.
Use when the user asks to send a text message or iMessage via the macOS Messages app.
Use when a task involves web search, current information, source verification, citations, or entity/person/paper/project disambiguation.
Use when the task involves `exec_command` escalation, `prefix_rule`, sandbox permissions, writable roots, or Codex platform-specific operational patterns.
| name | qwen |
| description | Use when the user asks to run Qwen CLI in non-interactive mode or references Qwen Code for AI-assisted coding tasks. |
Before running Qwen, follow the shared logging and summary protocol in ../_shared/agent-cli.md.
command -v qwenplan for read-only analysis. For implementation/editing tasks, first use superpowers:using-git-worktrees to create a fresh git worktree, then run Qwen there with auto-edit or yolo when approved.the current host's user-question or approval mechanism before using -y, --yolo or --approval-mode yolo.-m, --model <model> - Model to use-y, --yolo - Automatically accept all actions--approval-mode <plan|default|auto-edit|yolo> - Approval mode-c, --continue - Resume most recent session-r, --resume <session-id> - Resume specific session-o, --output-format <text|json|stream-json> - Output format--sandbox - Run in sandboxfull.md, and require the prompt to write summary.md.| Use case | Command pattern |
|---|---|
| One-shot prompt | qwen "your prompt here" |
| Plan only (read-only) | qwen "prompt" --approval-mode plan |
| Auto-edit mode in fresh worktree only | qwen "prompt" --approval-mode auto-edit |
| Yolo mode in fresh worktree only (auto-approve all) | qwen "prompt" --yolo |
| Continue last session | qwen --continue "follow-up" |
| Use specific model | qwen --model <model> "prompt" |
| JSON output | qwen "prompt" -o json |
| Sandbox mode | qwen "prompt" --sandbox |
| Mode | Permissions | Use Case |
|---|---|---|
plan | Read-only, no edits | Code analysis, planning |
default | Ask for approval | General use |
auto-edit | Auto-approve edit tools | Making code changes in a fresh worktree |
yolo | Auto-approve all tools | Full access in a fresh worktree |
# One-shot prompt
qwen -p "Review src/ for bugs"
# Plan only mode
qwen -p "Analyze the codebase architecture" --approval-mode plan
# Yolo mode in a fresh worktree only
qwen -p "Fix bug in file.py. Apply now." --yolo
# Continue last session
qwen --continue -p "What else can you improve?"
# Capture stdout/stderr according to ../_shared/agent-cli.md
qwen command, immediately use the current host's user-question or approval mechanism to confirm next steps, collect clarifications, or decide whether to resume with --continue.qwen --version or a qwen command exits non-zero; request direction before retrying.--yolo, --approval-mode yolo) ask the user for permission using the current host's user-question or approval mechanism unless it was already given.the current host's user-question or approval mechanism.