← Back to Skills Marketplace
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 (
1150
Downloads
0
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install call-deepseek-v3-llm
Description
AI agent for call deepseek v3 llm tasks
README (SKILL.md)
Call Deepseek V3 Llm
Overview
This skill provides specialized capabilities for call deepseek v3 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_deepseek_v3_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
Usage Guidance
This skill is instruction-only and appears internally consistent: it expects meeting minutes as input and enforces strict language-matching rules. Before installing or using it, make sure you (or the system invoking it) will provide the meeting minutes and the user's initial challenge language as part of the runtime input; otherwise the language rules may produce unclear behavior. Because the skill is instruction-only and requests no credentials or installs, there is low security risk from the skill itself — but always be cautious about what meeting content you feed into any agent (do not supply secrets or sensitive credentials in the meeting minutes).
Capability Analysis
Type: OpenClaw Skill
Name: call-deepseek-v3-llm
Version: 0.1.0
The `SKILL.md` file contains strong, overriding directives that attempt to manipulate the AI agent's core behavior and context interpretation. Specifically, instructions like 'It is **strictly forbidden** to decide your response language based on the language of this system prompt' and 'These minutes are your sole source of information and memory, and you must adhere to them' are clear prompt injection attempts designed to make the agent ignore its foundational system prompts and external context. While there is no explicit instruction for data exfiltration or malicious execution, this manipulation of the agent's internal logic represents a significant vulnerability.
Capability Assessment
Purpose & Capability
The name/description (call-deepseek-v3-llm) align with the SKILL.md: the skill defines behavior for a meeting/creative-agent. It does not request unrelated binaries, credentials, or config paths.
Instruction Scope
The instructions direct the agent to 'carefully read the attached meeting minutes' as its sole source of memory — this is expected for a meeting assistant, but the skill file does not specify how meeting minutes are supplied (they will presumably be provided at runtime in the prompt or a tool input). The primary language rule is strict and may interact unexpectedly with other system-level language settings; it also forbids using the system prompt or minutes to infer language, which could cause ambiguous behavior if the user's initial challenge language is not provided.
Install Mechanism
No install spec and no code files are present (instruction-only). Nothing is written to disk or fetched at install time.
Credentials
The skill requires no environment variables, credentials, or config paths. There are no requests for secrets or unrelated service tokens.
Persistence & Privilege
always is false and the skill does not request persistent system presence or modify other skills. It can be invoked by the agent normally and has no elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install call-deepseek-v3-llm - After installation, invoke the skill by name or use
/call-deepseek-v3-llm - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
call-deepseek-v3-llm 0.1.0
- Initial release of the skill for interfacing with Deepseek V3 LLM.
- Enforces strict language-matching rules based on user prompts.
- Defines clear team participation, role identity, and context usage.
- Requires all responses to be based strictly on meeting minutes and CCO’s current request.
- Creative, professional output for use in collaborative team brainstorming sessions.
Metadata
Frequently Asked Questions
What is Call Deepseek V3 Llm?
AI agent for call deepseek v3 llm tasks. It is an AI Agent Skill for Claude Code / OpenClaw, with 1150 downloads so far.
How do I install Call Deepseek V3 Llm?
Run "/install call-deepseek-v3-llm" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Call Deepseek V3 Llm free?
Yes, Call Deepseek V3 Llm is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Call Deepseek V3 Llm support?
Call Deepseek V3 Llm is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Call Deepseek V3 Llm?
It is built and maintained by urrrich (@urrrich); the current version is v0.1.0.
More Skills