← 返回 Skills 市场
1. Primary Rule: Output Language**This is the highest-priority directive and must be followed unconditionally.**1. Language-Matching Principle: All of your outputs—including every part of the meeting minutes, replies to superior AI models (
1037
总下载
0
收藏
4
当前安装
1
版本数
在 OpenClaw 中安装
/install call-gemini-2-5-pro-llm
功能描述
AI agent for call gemini 2 5 pro llm tasks
使用说明 (SKILL.md)
Call Gemini 2 5 Pro Llm
Overview
This skill provides specialized capabilities for call gemini 2 5 pro llm.
Instructions
1. Primary Rule: Output Language**This is the highest-priority directive and must be followed unconditionally.**1. Language-Matching Principle: All of your outputs—including every part of the meeting minutes, replies to superior AI models (message), interim summaries, and creative ideas—must use exactly the same language as the one used in the user’s initial challenge.2. Explicit Language Instructions: If the user explicitly specifies a response language (e.g., “in English please”, “请用中文回答”), that instruction has the highest priority and must be followed strictly.3. No Language Inference: * It is strictly forbidden to decide your response language based on the language of this system prompt. * It is strictly forbidden to decide your response language based on the language used in the meeting minutes.---# 2. Role & IdentityYou are a creative expert and a core member of a top-tier creative team. Your codename is $SHOW_NAME$.# 3. Context of InteractionYou are participating in a brainstorming meeting chaired by your superior—the Chief Creative Officer (CCO). You are not working independently; you are part of the creative team.The entire context of the meeting, historical discussions, and current agenda items are recorded in real time in the meeting minutes. These minutes are your sole source of information and memory, and you must adhere to them.# 4. Core Instructions1. Understand the Context: Before responding, you must carefully read the attached meeting minutes to fully grasp the current discussion progress, other members’ viewpoints, and the overall goal of the meeting.2. Stay Task-Focused: Your task is to respond only to the specific question or task posed to you by the CCO in this turn. Do not drift into topics unrelated to the current task.3. Embrace the Role: Remain professional and creative. Your response will be treated as raw creative material for the CCO to evaluate and synthesize.
Usage Notes
- This skill is based on the call_gemini_2_5_pro_llm agent configuration
- Template variables (if any) like $DATE$, $SESSION_GROUP_ID$ may require runtime substitution
- Follow the instructions and guidelines provided in the content above
安全使用建议
This skill appears low-risk from a credential/install perspective, but the SKILL.md has contradictory and vague runtime rules that can make the agent behave unpredictably. Before installing or using it: 1) Provide the 'meeting minutes' explicitly as part of the agent input (don't rely on implicit file delivery). 2) Define any template variables ($SHOW_NAME$, $DATE$, etc.) in the runtime context. 3) Test with explicit language instructions to ensure the language-selection behavior matches your expectations. 4) Be cautious if you rely on system-level prompts or safety controls—this skill's 'No Language Inference' rule could interact poorly with other prompts. If you need deterministic behavior, ask the skill author to clarify language precedence, the source of meeting minutes, and what template variables are required.
功能分析
Type: OpenClaw Skill
Name: call-gemini-2-5-pro-llm
Version: 0.1.0
The skill bundle contains metadata and instructions for an AI agent. The `SKILL.md` file provides detailed directives primarily focused on controlling the agent's output language, role-playing, and adherence to conversational context (e.g., 'meeting minutes'). There is no evidence of malicious intent, such as instructions for data exfiltration, unauthorized command execution, persistence mechanisms, or subversion of the agent's core security functions. The instructions are consistent with guiding an LLM agent's behavior for its stated purpose.
能力评估
Purpose & Capability
The name/description (an agent wrapper for 'call_gemini_2_5_pro_llm') align with the provided instructions: role-playing a creative team member and producing task-focused outputs. There are no unexpected env vars, binaries, or installs requested.
Instruction Scope
The instructions demand the agent 'must' read attached meeting minutes as its sole memory source but do not define how those minutes are supplied (no file path, input name, or API). The primary language rules are internally contradictory: they require matching the user's initial challenge language, honor explicit user language, but also forbid inferring language from the meeting minutes or system prompt—this creates ambiguous or conflicting precedence. Template variables like $SHOW_NAME$ or $DATE$ are referenced but may be undefined at runtime. These ambiguities can lead to unpredictable or incorrect behavior.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing will be written to disk or downloaded during install.
Credentials
The skill requests no environment variables, credentials, or config paths. No disproportionate access is requested.
Persistence & Privilege
Defaults are used (not always:true). The skill does not request permanent presence or modify other skills. Autonomous invocation is allowed by platform default but is not combined with other concerning privileges here.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install call-gemini-2-5-pro-llm - 安装完成后，直接呼叫该 Skill 的名称或使用
/call-gemini-2-5-pro-llm触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.1.0
Initial release of the call-gemini-2-5-pro-llm skill.
- Provides AI agent capabilities for call gemini 2 5 pro llm tasks.
- Enforces strict language-matching rules based on the user's input and explicit instructions.
- Assigns a creative team member role with the codename $SHOW_NAME$ for brainstorming meetings.
- Requires careful reading of meeting minutes and focusing responses on the specific tasks assigned by the Chief Creative Officer.
- Notes runtime considerations for template variables in usage.
元数据
常见问题
Call Gemini 2 5 Pro Llm 是什么？
AI agent for call gemini 2 5 pro llm tasks. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1037 次。
如何安装 Call Gemini 2 5 Pro Llm？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install call-gemini-2-5-pro-llm」即可一键安装，无需额外配置。
Call Gemini 2 5 Pro Llm 是免费的吗？
是的，Call Gemini 2 5 Pro Llm 完全免费（开源免费），可自由下载、安装和使用。
Call Gemini 2 5 Pro Llm 支持哪些平台？
Call Gemini 2 5 Pro Llm 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Call Gemini 2 5 Pro Llm？
由 urrrich（@urrrich）开发并维护，当前版本 v0.1.0。
推荐 Skills