← 返回 Skills 市场
prompt-polisher
作者
Xiaojian Chen
· GitHub ↗
· v1.0.0
· MIT-0
85
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install prompt-polisher1
功能描述
Rewrite rough goals, scattered notes, or vague requests into clear, actionable prompts with explicit objective, constraints, output format, and missing assum...
安全使用建议
This skill appears internally consistent and low-risk: it only contains instructions for rewriting prompts and requires no installs or credentials. Before using, avoid pasting any sensitive information (API keys, passwords, or private data) because the skill will rewrite and return whatever you provide. If you plan to let an autonomous agent use this skill, remember the agent could include user-supplied content in downstream requests — do not feed secrets. If you want extra assurance, test with non-sensitive example prompts first.
功能分析
Type: OpenClaw Skill
Name: prompt-polisher1
Version: 1.0.0
The skill bundle is a straightforward prompt engineering tool designed to refine vague user requests into structured prompts. The instructions in SKILL.md and the configuration in agents/openai.yaml are entirely focused on text transformation and lack any high-risk capabilities such as code execution, network access, or data exfiltration.
能力评估
Purpose & Capability
The skill's name and description match the SKILL.md: it only describes transforming rough requests into clearer prompts. It does not request unrelated credentials, binaries, or system access that would be disproportionate to rewriting prompts.
Instruction Scope
The SKILL.md gives clear, bounded instructions for rewriting prompts (identify goal, extract constraints, list assumptions, produce a structured prompt). It does not instruct the agent to read files, environment variables, system state, or to send data to external endpoints. Note: the skill will echo user-provided text, so avoid submitting secrets.
Install Mechanism
No install spec and no code files are present — the skill is instruction-only, so nothing is written to disk or downloaded during install.
Credentials
No environment variables, credentials, or config paths are required. The agent instructions do not reference any secrets or unrelated services.
Persistence & Privilege
always:false and user-invocable:true (defaults). The skill can be invoked autonomously by the agent (normal platform behavior) but does not request permanent presence, nor does it modify other skills or system configuration. agents/openai.yaml only defines a small interface/default prompt.
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 prompt-polisher1 - 安装完成后，直接呼叫该 Skill 的名称或使用
/prompt-polisher1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
v1.0.0
- Initial release of Prompt Polisher.
- Transforms rough, vague, or scattered user requests into clear, actionable prompts with explicit goals, constraints, output format, and assumptions.
- Ensures prompts are concise, well-structured, and preserve the original user intent.
- Automatically identifies and addresses missing but necessary details, explicitly labeling any assumptions made.
- Provides the option to include follow-up questions when key information is lacking.
元数据
常见问题
prompt-polisher 是什么？
Rewrite rough goals, scattered notes, or vague requests into clear, actionable prompts with explicit objective, constraints, output format, and missing assum... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 85 次。
如何安装 prompt-polisher？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install prompt-polisher1」即可一键安装，无需额外配置。
prompt-polisher 是免费的吗？
是的，prompt-polisher 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
prompt-polisher 支持哪些平台？
prompt-polisher 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 prompt-polisher？
由 Xiaojian Chen（@chenxiaojian985）开发并维护，当前版本 v1.0.0。
推荐 Skills