一键导入
kiro-cli
Use when the user asks to run Kiro CLI in non-interactive mode or references Kiro for AI chat, shell translation, or agent management.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Use when the user asks to run Kiro CLI in non-interactive mode or references Kiro for AI chat, shell translation, or agent management.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | kiro-cli |
| description | Use when the user asks to run Kiro CLI in non-interactive mode or references Kiro for AI chat, shell translation, or agent management. |
Before running Kiro, follow the shared logging and summary protocol in ../_shared/agent-cli.md.
command -v kiro-cli--no-interactive mode for non-interactive use. Default to untrusted/read-only-style operation for analysis. For implementation tasks, first use superpowers:using-git-worktrees to create a fresh git worktree, then run Kiro there with trusted tools when approved.the current host's user-question or approval mechanism before using --trust-all-tools or executing generated shell commands.--agent <AGENT_NAME> - Use specific agent--model <MODEL> - Model to use--no-interactive - Run without user input (required for non-interactive)-a, --trust-all-tools - Trust all tools without confirmation--trust-tools <TOOL_NAMES> - Trust specific tools only (comma-separated)-r, --resume - Resume most recent conversationfull.md, and require the prompt to write summary.md.| Use case | Command pattern |
|---|---|
| Non-interactive chat | kiro-cli chat "your input" --no-interactive |
| With specific agent | kiro-cli chat --agent <agent> "input" --no-interactive |
| Trust all tools in fresh worktree only | kiro-cli chat "input" --trust-all-tools --no-interactive |
| Trust write tools in fresh worktree only | kiro-cli chat "input" --trust-tools=fs_read,fs_write --no-interactive |
| Resume conversation | kiro-cli chat --resume --no-interactive |
| List models | kiro-cli chat --list-models |
| List sessions | kiro-cli chat --list-sessions |
| Option | Description | Use Case |
|---|---|---|
| (none) | Ask for confirmation | Safest, general use |
--trust-tools <tools> | Trust specific tools | Controlled access; write tools require a fresh worktree |
--trust-all-tools | Trust all tools | Full access in a fresh worktree |
# Non-interactive chat
kiro-cli chat "Explain this code" --no-interactive
# With specific agent and trust all tools in a fresh worktree only
kiro-cli chat --agent builder "Fix the bug" --trust-all-tools --no-interactive
# Resume conversation
kiro-cli chat --resume --no-interactive
# Capture stdout/stderr according to ../_shared/agent-cli.md
kiro-cli command, immediately use the current host's user-question or approval mechanism to confirm next steps, collect clarifications, or decide whether to resume with --resume.kiro-cli --version or a kiro-cli command exits non-zero; request direction before retrying.kiro-cli doctor to debug installation issues if needed.--trust-all-tools) ask the user for permission using the current host's user-question or approval mechanism unless it was already given.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.