← 返回 Skills 市场

Clear Prompt Engineering

Name: Clear Prompt Engineering
Author: 371166758-qq

作者 371166758-qq · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

169

总下载

当前安装

版本数

在 OpenClaw 中安装

/install clear-prompt

功能描述

Transforms vague prompts into clear, structured instructions by specifying goals, context, output, key info, and exclusions for precise results.

使用说明 (SKILL.md)

Clear Prompt Engineering

A skill that transforms vague prompts into precise, actionable instructions using 5 core principles.

When to Use

Use this skill when the user's message is ambiguous, too broad, or lacks necessary context. Apply it proactively before responding to help users craft better prompts.

5 Core Principles

明确任务目标: Say what to do directly, no ambiguity
补充场景背景: Provide usage context and prerequisites
明确输出要求: Specify format, length, and purpose
提供关键信息: Attach necessary data and details
排除无关选项: State what NOT to do (reduces ambiguity)

Template

Structure every prompt as:

【场景背景】+【已有信息】+【任务目标】+【输出要求】

Response Behavior

When you receive a vague prompt, instead of guessing:

Identify which principles are missing
Provide a before/after example showing the improvement
Suggest a refined version the user can confirm

Quick Templates

Config tasks

"I'm on 【OS】, already have 【credential】, please give me CLI commands to 【action】, ready to copy-paste"

Publish tasks

"I want to publish 【skill type】 to 【platform/org】, named 【name】, give me complete steps + prerequisites"

Debugging

"Running 【command】 got error 【error message】, already have 【conditions】, excluding 【known issues】, help troubleshoot"

Writing

"Write 【doc type】, highlighting 【key strengths】, must be 【style】, under 【length】 words"

Usage

This skill activates automatically when detecting vague input. No manual trigger needed.

安全使用建议

This skill is internally consistent and low-risk: it only contains instructions for rewriting prompts and does not request secrets or install software. Two practical cautions: (1) the SKILL.md says it will 'activate automatically' on vague input — if you prefer manual control, check your agent/platform settings for per-skill invocation controls before enabling it; (2) some templates ask for ready-to-run CLI commands or troubleshooting steps — always review any generated commands or instructions carefully before executing them. If you want greater assurance, ask the publisher for a homepage/source or request example inputs/outputs to validate behavior.

功能分析

Type: OpenClaw Skill Name: clear-prompt Version: 1.0.0 The skill bundle is a set of prompt engineering guidelines and templates designed to help the AI agent refine vague user requests into structured instructions. It contains no executable code, external network requests, or instructions that would lead to data exfiltration or unauthorized system access. The content in SKILL.md is entirely focused on improving communication clarity through five core principles.

能力评估

✓ Purpose & Capability

The name/description (transform vague prompts into structured instructions) matches the SKILL.md content. The skill requires no binaries, env vars, or config paths — appropriate for a text-only prompt-engineering helper.

✓ Instruction Scope

Runtime instructions are limited to analyzing user prompts and producing refined prompt templates and before/after examples. The SKILL.md does not instruct the agent to read files, access environment variables, transmit data to external endpoints, or perform actions outside text transformation.

✓ Install Mechanism

No install specification or code files are present (instruction-only). Nothing will be written to disk or downloaded by the skill itself.

✓ Credentials

The skill requests no credentials, secrets, or config paths. Declared requirements are minimal and proportionate to a prompt-refinement capability.

✓ Persistence & Privilege

The skill does not request always:true and makes no changes to other skills or system-wide settings. It states it 'activates automatically when detecting vague input' — this is a behavioral preference but does not by itself grant elevated system privileges.

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 clear-prompt
安装完成后，直接呼叫该 Skill 的名称或使用 /clear-prompt 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

5 core principles for transforming vague prompts into precise instructions with reusable templates

元数据

Slug clear-prompt

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题