← Back to Skills Marketplace
assistant
by
zhengmengkaiZMK
· GitHub ↗
· v1.0.1
· MIT-0
222
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install assistant11
Description
本 Skill 适用于作为以及需要助理自主学习沉淀知识时,请调用此 Skill。
README (SKILL.md)
核心定位 (Core Role)
你的主要任务是帮助产品架构师快速、准确地回答海外客户的咨询。
工作规则 (Working Rules)
1. 语言要求 (Language Requirement)
- 输入:用户(售前架构师)会以中文向你提问或转述客户的问题。
- 输出:你必须以中英双语(Chinese & English)进行回复,以便用户既能自己看懂,又能直接复制英文回复给海外客户。英文回复应当专业、地道、符合海外B2B交流的商务口吻。
Usage Guidance
This skill appears coherent and low-risk: it only provides bilingual reply instructions plus product FAQ and spec docs and requests no credentials or installs. Things to consider before installing: 1) Source is unknown — verify you trust the owner before allowing the agent to use these internal product docs. 2) The references include product-level technical details (biometric/KYC device behavior); avoid supplying customer-sensitive or personally identifiable data to the skill if you don't want it recorded. 3) Clarify how the platform will persist any 'autonomous learning' (agent memory or external storage) because the skill itself doesn't declare a persistence mechanism — if you enable memory, decide retention rules or disable persistent memory if undesired. 4) Because the agent can invoke skills autonomously by default, ensure your agent's authorization policy is appropriate (who can trigger this skill and whether its outputs are sent externally). If you need absolute assurance, request the publisher to document where and how the assistant will store appended Q&A and who can access that storage.
Capability Analysis
Type: OpenClaw Skill
Name: assistant11
Version: 1.0.1
The skill bundle is a legitimate bilingual assistant designed to support product architects with customer inquiries regarding palm recognition technology. The content consists entirely of product documentation (kyc_standard_docs.md), technical FAQs (faq.md), and standard operational instructions (SKILL.md) without any evidence of malicious intent, data exfiltration, or security risks.
Capability Assessment
Purpose & Capability
The skill's name/description say it's for the assistant to help with autonomous knowledge accumulation and to assist product architects answering overseas customers. The SKILL.md explicitly defines a role (help product architects reply bilingually) and the included reference docs are product FAQs and spec docs about the biometric product line — all consistent with the stated purpose. No unrelated credentials, binaries, or installs are requested.
Instruction Scope
Runtime instructions are limited: require Chinese input and bilingual (Chinese+English) output for B2B responses. The included references contain guidance and an inline comment indicating the assistant may append new Q&A records, but the SKILL.md does not specify any mechanism to persist or transmit data (no file write, network endpoint, or env var usage is declared). This creates a minor ambiguity about how '自主学习沉淀知识' (autonomous learning / persistence) is expected to happen.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute. This is low-risk: nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The skill's operation (producing bilingual replies using provided docs) does not require additional secrets or external services.
Persistence & Privilege
always:false and no elevated privileges are requested. The skill can be invoked autonomously by the agent (default platform behavior). Because the description mentions autonomous learning but the skill provides no persistence mechanism, confirm how/where the agent will retain any learned Q&A (agent memory, external DB, or local files) before enabling long-term retention.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install assistant11 - After installation, invoke the skill by name or use
/assistant11 - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- 移除了 references/ 目录下的所有产品说明、API 文档与FAQ,共计9个文档文件。
- 简化了 Skill 名称与描述,不再限定掌纹产品场景。
- 移除了双语输出、版本隔离、知识库检索和FAQ知识沉淀等详细流程与操作规则。
- Skill 使用范围调整为助理自主学习与知识沉淀。
Metadata
Frequently Asked Questions
What is assistant?
本 Skill 适用于作为以及需要助理自主学习沉淀知识时,请调用此 Skill。 It is an AI Agent Skill for Claude Code / OpenClaw, with 222 downloads so far.
How do I install assistant?
Run "/install assistant11" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is assistant free?
Yes, assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does assistant support?
assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created assistant?
It is built and maintained by zhengmengkaiZMK (@zhengmengkaizmk); the current version is v1.0.1.
More Skills