Skills speak in actions ("dispatch a subagent", "create a todo", "read a file"). On Gemini CLI these resolve to the tools below.
技能用行動來表達（「派遣子代理」、「建立 todo」、「讀取檔案」）。在 Gemini CLI 上，這些會對應到下方的工具。
| Action skills request | Gemini CLI equivalent |
|---|---|
| Read a file | read_file |
| Read multiple files at once | read_many_files |
| Create a new file | write_file |
| Edit a file | replace |
| Run a shell command | run_shell_command |
| Search file contents | grep_search |
| Find files by name | glob |
| List files and subdirectories | list_directory |
| Fetch a URL | web_fetch |
| Search the web | google_web_search |
| Invoke a skill | activate_skill |
Dispatch a subagent (Subagent (general-purpose): template) |
invoke_agent with agent_name: "generalist" (invocable via @generalist chat syntax — see Subagent support) |
| Multiple parallel dispatches | Multiple invoke_agent calls in the same response |
| Task tracking ("create a todo", "mark complete") | write_todos (statuses: pending, in_progress, completed, cancelled, blocked) |
| 技能要求的行動 | Gemini CLI 的對應 |
|---|---|
| 讀取檔案 | read_file |
| 一次讀取多個檔案 | read_many_files |
| 建立新檔案 | write_file |
| 編輯檔案 | replace |
| 執行 shell 指令 | run_shell_command |
| 搜尋檔案內容 | grep_search |
| 依名稱尋找檔案 | glob |
| 列出檔案與子目錄 | list_directory |
| 擷取 URL | web_fetch |
| 搜尋網路 | google_web_search |
| 呼叫技能 | activate_skill |
派遣子代理（Subagent (general-purpose): 範本） |
使用 agent_name: "generalist" 的 invoke_agent（可經由 @generalist 聊天語法呼叫——見 子代理支援） |
| 多次平行派遣 | 在同一個回應中多次 invoke_agent 呼叫 |
| 任務追蹤（「建立 todo」、「標記完成」） | write_todos（狀態：pending、in_progress、completed、cancelled、blocked） |
When a skill mentions "your instructions file", on Gemini CLI this is GEMINI.md. Gemini CLI loads GEMINI.md hierarchically: global at ~/.gemini/GEMINI.md, project-level files in workspace directories and their ancestors, and sub-directory GEMINI.md files when a tool accesses files in those directories.
當技能提到「你的指令檔」時，在 Gemini CLI 上它是 GEMINI.md。Gemini CLI 階層式載入 GEMINI.md：全域在 ~/.gemini/GEMINI.md，專案層級的檔案在 workspace 目錄及其上層，而當工具存取某目錄中的檔案時，會載入該目錄下的 GEMINI.md。
User-level skills live at ~/.gemini/skills/, with ~/.agents/skills/ as a cross-runtime alias (shared with Codex and Copilot CLI). When both directories exist at the same scope, .agents/skills/ takes precedence. Each skill is a subdirectory containing a SKILL.md (with name and description frontmatter).
使用者層級的技能位於 ~/.gemini/skills/，而 ~/.agents/skills/ 是跨執行環境的別名（與 Codex 和 Copilot CLI 共用）。當同一個作用域同時存在兩個目錄時，.agents/skills/ 優先。每個技能是包含 SKILL.md（帶有 name 與 description frontmatter）的子目錄。
Gemini CLI dispatches subagents through the invoke_agent tool, which takes agent_name and prompt parameters. The same dispatch is also surfaced as a chat-syntax shortcut: typing @generalist <prompt> is equivalent to calling invoke_agent with agent_name: "generalist". Built-in agent names include generalist, cli_help, codebase_investigator, and (with browser tooling enabled) browser_agent.
Gemini CLI 透過 invoke_agent 工具派遣子代理，該工具接受 agent_name 與 prompt 參數。同樣的派遣也以聊天語法捷徑呈現：輸入 @generalist <prompt> 等同於以 agent_name: "generalist" 呼叫 invoke_agent。內建代理名稱包括 generalist、cli_help、codebase_investigator，以及（啟用瀏覽器工具時）browser_agent。
Skills dispatch with Subagent (general-purpose): and either reference a prompt-template file (e.g., superpowers:subagent-driven-development's ./implementer-prompt.md) or supply an inline prompt. On Gemini CLI:
技能以 Subagent (general-purpose): 派遣，並參照 prompt 範本檔（例如 superpowers:subagent-driven-development 的 ./implementer-prompt.md）或提供內嵌 prompt。在 Gemini CLI 上：
| Skill dispatch form | Gemini CLI equivalent |
|---|---|
References a *-prompt.md template (implementer, task-reviewer, code-reviewer, etc.) |
Fill the template, then invoke_agent with agent_name: "generalist" and the filled prompt |
References superpowers:requesting-code-review's ./code-reviewer.md |
invoke_agent with agent_name: "generalist" and the filled review template |
| Inline prompt (no template referenced) | invoke_agent with agent_name: "generalist" and your inline prompt |
| 技能派遣形式 | Gemini CLI 的對應 |
|---|---|
參照 *-prompt.md 範本（implementer、task-reviewer、code-reviewer 等） |
填入範本，然後以 agent_name: "generalist" 與填入後的 prompt 呼叫 invoke_agent |
參照 superpowers:requesting-code-review 的 ./code-reviewer.md |
以 agent_name: "generalist" 與填入後的審查範本呼叫 invoke_agent |
| 內嵌 prompt（未參照範本） | 以 agent_name: "generalist" 與你的內嵌 prompt 呼叫 invoke_agent |
Skills provide prompt templates with placeholders like {WHAT_WAS_IMPLEMENTED} or [FULL TEXT of task]. Fill all placeholders before passing the complete prompt to invoke_agent. The prompt template itself contains the agent's role, review criteria, and expected output format — the subagent will follow it.
技能提供帶有 {WHAT_WAS_IMPLEMENTED} 或 [FULL TEXT of task] 這類佔位符的 prompt 範本。在把完整 prompt 傳給 invoke_agent 之前，先填入所有佔位符。prompt 範本本身包含代理的角色、審查準則與預期輸出格式——子代理會遵循它。
Gemini CLI supports parallel subagent dispatch. Issue multiple invoke_agent calls in the same response (or multiple @generalist invocations in one prompt) to run independent subagent work in parallel. Keep dependent tasks sequential, but do not serialize independent subagent tasks just to preserve a simpler history.
Gemini CLI 支援平行子代理派遣。在同一個回應中發出多次 invoke_agent 呼叫（或在一個 prompt 中多次 @generalist 呼叫），即可平行執行獨立的子代理工作。相依的任務保持循序，但不要只是為了維持更簡單的歷史而把獨立的子代理任務序列化。
These tools are unique to Gemini CLI:
這些工具是 Gemini CLI 獨有的：
| Tool | Purpose |
|---|---|
save_memory (legacy) |
Persist facts across sessions when experimental.memoryV2 = false |
get_internal_docs |
Look up Gemini CLI's bundled documentation |
ask_user |
Pose structured questions to the user (text / single-select / multi-select) |
enter_plan_mode / exit_plan_mode |
Switch into and out of read-only plan mode |
update_topic |
Update the current conversation's topic / strategic-intent metadata |
complete_task |
Signal that a Gemini subagent has completed and return its result to the parent agent |
tracker_create_task, tracker_update_task, tracker_get_task, tracker_list_tasks, tracker_add_dependency, tracker_visualize |
Rich task tracker with dependency and visualization support |
read_mcp_resource, list_mcp_resources |
MCP resource access |
| 工具 | 用途 |
|---|---|
save_memory（legacy） |
當 experimental.memoryV2 = false 時，跨 session 持久化事實 |
get_internal_docs |
查閱 Gemini CLI 內建的說明文件 |
ask_user |
向使用者提出結構化問題（文字／單選／多選） |
enter_plan_mode / exit_plan_mode |
進入與離開唯讀 plan 模式 |
update_topic |
更新目前對話的主題／策略意圖中繼資料 |
complete_task |
告知某個 Gemini 子代理已完成，並把結果回傳給父代理 |
tracker_create_task、tracker_update_task、tracker_get_task、tracker_list_tasks、tracker_add_dependency、tracker_visualize |
具備相依與視覺化支援的豐富任務追蹤器 |
read_mcp_resource、list_mcp_resources |
MCP 資源存取 |