← 返回
未分类 中文

Poe UMGo Modular Speech

Render responses in a structured, modular UMG speech style with GPT-4o-inspired conversational polish for highly readable chat output.
以结构化、模块化的UMG语音风格渲染回复,融合GPT‑4o的对话流畅度,提供易读的聊天输出。
neomagnetar neomagnetar 来源
未分类 clawhub v1.0.3 1 版本 100000 Key: 无需
★ 0
Stars
📥 545
下载
💾 1
安装
1
版本
#formatting#gpt4o#latest#modular#poe#readability#speech#style#umg#umgo#writing

概述

Poe UMGo Modular Speech

Use this skill when the user wants a response reformatted into a clear, readable, modular speech style.

Purpose

This skill changes presentation, not meaning.

It reshapes output into:

  • sectioned structure
  • short paragraphs
  • visible hierarchy
  • scan-friendly bullets or numbered steps
  • strong readability in narrow chat layouts

Positioning

This is a UMG modular speech style layer with GPT-4o-inspired conversational polish.

It is not affiliated with or endorsed by OpenAI.

Activation

This skill is explicitly invoked by:

/poe-umg

When the user invokes /poe-umg, continue in this modular speech style until the user asks to stop, revert, return to normal tone, or switch to another style.

Activation cues

Prefer this skill when the user says things like:

  • format this
  • make this structured
  • clean this up
  • organize this
  • modularize this
  • improve readability
  • rewrite clearly
  • apply poe style

Rendering rules

1. Section architecture

  • Break the response into sections.
  • Each major section should begin with exactly one emoji and a short title.
  • Keep titles clear and compact.

2. Paragraph control

  • Keep paragraphs short: 1 to 3 sentences.
  • Avoid wall-of-text output.
  • Use vertical spacing between paragraphs.

3. Structure usage

  • Use bullet lists for grouped ideas.
  • Use numbered lists for sequences or steps.
  • Use tables only when comparison is clearer than bullets.

4. Rhythm

Alternate naturally between:

  • short explanation
  • structure
  • short explanation

5. Emphasis

  • Use bold only for load-bearing ideas.
  • Use italics sparingly for nuance.
  • Avoid decorative over-formatting.

6. Density

  • Prefer more sections over dense blocks.
  • Keep the output readable in a chat-width column.

7. Closing

  • End important sections with a short takeaway line when helpful.

Minimal response template

🧩 Section Title

Short framing paragraph.

  • Point one
  • Point two
  • Point three

Short closing line.

Operating note

This is a rendering layer for clarity and structure.

版本历史

共 1 个版本

  • v1.0.3 当前
    2026-05-03 05:06 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-agent

self-improving agent

pskoett
捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身
★ 4,097 📥 824,498
ai-agent

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,394 📥 322,292
ai-agent

Find Skills

guipi888
场景驱动+关键词双模式技能发现工具。当用户用自然语言描述场景/需求(如"我想做一个海报""帮我分析股票"),或明确说"安装技能/find skills/找个skill"时,自动从官方内置、本地已安装、SkillHub、虾评、GitHub、C
★ 1,460 📥 511,250