← Back to Skills Marketplace
Smart Prompt Builder
by
yuzhihui886
· GitHub ↗
· v2.0.0
· MIT-0
112
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install smart-prompt-builder
Description
智能提示构建器 - 根据语料库检索结果生成优化的写作提示。当需要为小说创作场景生成结构化提示词时使用,支持描写/对话/动作/情感 4 种场景类型,可注入 Voice Profile 和上下文信息。
Usage Guidance
This skill appears to implement the advertised prompt-building features, but the LLM-backed script will send your style/context/corpus to an external service and requires an environment variable DASHSCOPE_API_KEY — neither of which are declared in the skill metadata or SKILL.md. Before installing or running: (1) decide whether you will use the LLM script; if not, avoid running build_prompt_llm.py or remove it. (2) If you do use it, verify and trust the endpoint (coding.dashscope.aliyuncs.com) and the owner, and only provide an API key you are willing to send prompt/context to that service. (3) Fix the dependency list (add requests and PyYAML) and ensure SKILL.md and manifest are updated to declare required env vars and the external endpoint. (4) Consider auditing or running the scripts in a sandbox to see what data would be transmitted. If you cannot verify the endpoint or owner, treat the LLM mode as high-risk and avoid supplying sensitive corpus or context.
Capability Analysis
Type: OpenClaw Skill
Name: smart-prompt-builder
Version: 2.0.0
The skill bundle is a legitimate tool for generating structured writing prompts for fiction, supporting both template-based and LLM-powered generation. The Python scripts (`build_prompt.py` and `build_prompt_llm.py`) are well-structured, use safe parsing methods like `yaml.safe_load`, and their behaviors—including network calls to the Alibaba DashScope API—are fully aligned with the stated purpose. No evidence of malicious intent, secret exfiltration, or prompt injection was found.
Capability Assessment
Purpose & Capability
The included scripts implement prompt-building functionality that matches the description (build_prompt.py). However, there is an additional script (build_prompt_llm.py) that acts as a client to an external LLM service (POST to coding.dashscope.aliyuncs.com) and requires an environment variable DASHSCOPE_API_KEY. The registry metadata declared no required env vars and SKILL.md does not document the need for this API key or the external endpoint, which is an incoherence.
Instruction Scope
SKILL.md documents CLI usage for scripts/build_prompt.py and general integration examples but does not describe the LLM client behavior or the required DASHSCOPE_API_KEY. The LLM script will transmit the provided style/context/prompt to a remote service — this is outside what the SKILL.md declares and could expose user-supplied context/corpus to an external endpoint.
Install Mechanism
There is no install spec (instruction-only), which is low-risk. However, scripts/requirements.txt only lists 'rich' while both scripts import PyYAML and build_prompt_llm.py imports requests; SKILL.md also mentions PyYAML. The mismatch between declared dependencies and requirements.txt is inconsistent and may lead users to install the wrong set of packages.
Credentials
build_prompt_llm.py reads DASHSCOPE_API_KEY from the environment and will abort if not set. The skill manifest declares no required env vars and SKILL.md doesn't mention this secret. Requesting an API key (and sending prompts/context) to an external service is a sensitive operation; declaring and justifying that credential in the manifest would be expected but is missing.
Persistence & Privilege
The skill does not request permanent presence (always:false) and does not modify other skills or system-wide settings. It runs as simple CLI tools and has no install hook that would persist or elevate privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install smart-prompt-builder - After installation, invoke the skill by name or use
/smart-prompt-builder - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
v2.0 LLM 版本:新增 build_prompt_llm.py,通过 LLM 构建高质量写作提示词,默认 qwen3.6-plus
v1.0.0
初始版本:支持 4 种场景类型(描写/对话/动作/情感),Voice Profile 注入,上下文注入,语料库结果格式化
Metadata
Frequently Asked Questions
What is Smart Prompt Builder?
智能提示构建器 - 根据语料库检索结果生成优化的写作提示。当需要为小说创作场景生成结构化提示词时使用,支持描写/对话/动作/情感 4 种场景类型,可注入 Voice Profile 和上下文信息。 It is an AI Agent Skill for Claude Code / OpenClaw, with 112 downloads so far.
How do I install Smart Prompt Builder?
Run "/install smart-prompt-builder" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Smart Prompt Builder free?
Yes, Smart Prompt Builder is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Smart Prompt Builder support?
Smart Prompt Builder is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Smart Prompt Builder?
It is built and maintained by yuzhihui886 (@yuzhihui886); the current version is v2.0.0.
More Skills