← 返回 Skills 市场
179
总下载
2
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install prompt-improve
功能描述
将模糊的用户请求转化为基于四要素框架的详细、可操作提示。该技能直接根据用户的输入生成结构化提示，无需交互式澄清。技能仅生成用于执行任务的提示文本，不执行实际任务或探索性操作。基于角色设定、任务描述、上下文信息和指令约束四个核心要素构建优秀prompt。
安全使用建议
This skill appears coherent and low-risk: it only generates structured prompts and does not access files, install code, or request secrets. Before using outputs in a real task, quickly review the generated prompt for incorrect assumptions (the skill intentionally infers missing context rather than asking follow-up questions). If you prefer the assistant to ask clarifying questions instead of guessing context, do not invoke this skill for that interaction.
功能分析
Type: OpenClaw Skill
Name: prompt-improve
Version: 1.0.1
The 'prompt-refiner' skill is a utility designed to transform vague user requests into structured, actionable prompts using a four-element framework (Role, Task, Context, and Constraints). The instructions in SKILL.md explicitly and repeatedly forbid the agent from executing actual tasks, exploring the filesystem, or calling external tools, focusing solely on text generation. No indicators of data exfiltration, malicious execution, or obfuscation were found in SKILL.md, _meta.json, or evals/evals.json.
能力评估
Purpose & Capability
Name/description (prompt refinement) match the declared behavior. The skill does not request unrelated binaries, env vars, or config paths and the provided evals align with prompt-generation use cases.
Instruction Scope
SKILL.md explicitly limits the skill to producing prompts and forbids file/system exploration or external calls, which is appropriate. Note: it instructs the agent to 'infer' missing context from patterns rather than clarifying with the user—this is a deliberate design choice (not a security issue) but can lead to incorrect assumptions or overconfident prompts if the inferred context is wrong; users/agents should review generated prompts before using them.
Install Mechanism
No install spec is present (instruction-only). This minimizes disk writes and external code execution risk.
Credentials
The skill requests no environment variables, credentials, or config paths. The lack of secrets or external-service requirements is proportionate to a prompt-generation tool.
Persistence & Privilege
always:false and no special privileges requested. Normal autonomous invocation is allowed by platform default but the skill does not request persistent or system-wide changes.
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-improve - 安装完成后，直接呼叫该 Skill 的名称或使用
/prompt-improve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
v1.0.1
- Skill behavior updated to only generate optimized prompts based on user input, without performing any actual task, exploration, or clarification.
- Clarified "zero exploration" policy: the skill does not read files, analyze codebases, or call tools under any circumstances.
- Enhanced main documentation to emphasize direct prompt conversion, with explicit statements about non-execution.
- Added detailed advanced techniques for further improving prompt quality, including task decomposition, chain-of-thought reasoning, and precise requirements.
- Provided more in-depth examples and new sample scenarios for various user needs.
v1.0.0
prompt-refiner v1.0.0 – Initial Release
- Introduces a skill for transforming vague user requests into detailed, actionable prompts using a four-factor framework: role, task, context, and constraints.
- Provides clear workflow steps: empathize with users, ask clarifying questions, summarize understanding, generate optimized prompts, and invite feedback.
- Includes practical templates and examples for rephrasing ambiguous requests into structured instructions suitable for AI or human collaborators.
- Highlights best practices, advanced techniques for handling cultural/language nuances, and common pitfalls to avoid.
- Outlines success indicators emphasizing improved communication, reduced misunderstandings, and higher quality outputs.
元数据
常见问题
improve your prompt 是什么？
将模糊的用户请求转化为基于四要素框架的详细、可操作提示。该技能直接根据用户的输入生成结构化提示，无需交互式澄清。技能仅生成用于执行任务的提示文本，不执行实际任务或探索性操作。基于角色设定、任务描述、上下文信息和指令约束四个核心要素构建优秀prompt。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 179 次。
如何安装 improve your prompt？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install prompt-improve」即可一键安装，无需额外配置。
improve your prompt 是免费的吗？
是的，improve your prompt 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
improve your prompt 支持哪些平台？
improve your prompt 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 improve your prompt？
由 Flonerze（@flonerze）开发并维护，当前版本 v1.0.1。
推荐 Skills