How do I install the Microcopy skill?

Run npx skillmds@latest add ulpi-io/microcopy in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Microcopy safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Microcopy?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Microcopy free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Microcopy?

ulpi-io (@ulpi-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Microcopy by ulpi-io — Agent Skill

Name: Microcopy
Author: ulpi-io

Microcopy

UI copy and microcopy guidelines. Use when writing UI text, buttons, error messages, empty states, onboarding, or any user-facing copy. Triggers on i18n translation, UI text writing, or copy improvement tasks. Supports both Chinese and English.

ulpi-io 2a16102 3 files · 19.6 KB Updated Sep 17, 2026

File contents

LobeHub UI Microcopy Guidelines

Brand: Where Agents Collaborate - Focus on collaborative agent system, not just "generation".

Fixed Terminology

Chinese	English
空间	Workspace
助理	Agent
群组	Group
上下文	Context
记忆	Memory
连接器	Integration
技能	Skill
助理档案	Agent Profile
话题	Topic
文稿	Page
社区	Community
资源	Resource
库	Library
模型服务商	Provider
评测	Evaluation
基准	Benchmark
数据集	Dataset
用例	Test Case

Brand Principles

Create: One sentence → usable Agent; clear next step
Collaborate: Multi-agent; shared Context; controlled
Evolve: Remember with consent; explainable; replayable

Writing Rules

Clarity first: Short sentences, strong verbs, minimal adjectives
Layered: Main line (simple) + optional detail (precise)
Consistent verbs: Create / Connect / Run / Pause / Retry / View details
Actionable: Every message tells next step; avoid generic "OK/Cancel"

Human Warmth (Balanced)

Default: 80% information, 20% warmth Key moments: 70/30 (first-time, empty state, failures, long waits)

Hard cap: At most half sentence of warmth, followed by clear next step.

Order:

Acknowledge situation (no judgment)
Restore control (pause/replay/edit/undo/clear Memory)
Provide next action

Avoid: Preachy encouragement, grand narratives, over-anthropomorphizing

Patterns

Getting started:

"Starting with one sentence is enough. Describe your goal."
"Not sure where to begin? Tell me the outcome."

Long wait:

"Running… You can switch tasks—I'll notify you when done."
"This may take a few minutes. To speed up: reduce Context / switch model."

Failure:

"That didn't run through. Retry, or view details to fix."
"Connection failed. Re-authorize in Settings, or try again later."

Collaboration:

"Align everyone to the same Context."
"Different opinions are fine. Write the goal first."

Errors/Exceptions

Must include:

What happened
(Optional) Why
What user can do next

Provide: Retry / View details / Go to Settings / Contact support / Copy logs

Never blame user. Put error codes in "Details".

---name: microcopydescription: UI copy and microcopy guidelines. Use when writing UI text, buttons, error messages, empty states, onboarding, or any user-facing copy. Triggers on i18n translation, UI text writing, or copy improvement tasks. Supports both Chinese and English.---# LobeHub UI Microcopy GuidelinesBrand: **Where Agents Collaborate** - Focus on collaborative agent system, not just "generation".## Fixed Terminology| Chinese | English || ---------- | ------------- || 空间 | Workspace || 助理 | Agent || 群组 | Group || 上下文 | Context || 记忆 | Memory || 连接器 | Integration || 技能 | Skill || 助理档案 | Agent Profile || 话题 | Topic || 文稿 | Page || 社区 | Community || 资源 | Resource || 库 | Library || 模型服务商 | Provider || 评测 | Evaluation || 基准 | Benchmark || 数据集 | Dataset || 用例 | Test Case |## Brand Principles1. **Create**: One sentence → usable Agent; clear next step2. **Collaborate**: Multi-agent; shared Context; controlled3. **Evolve**: Remember with consent; explainable; replayable## Writing Rules1. **Clarity first**: Short sentences, strong verbs, minimal adjectives2. **Layered**: Main line (simple) + optional detail (precise)3. **Consistent verbs**: Create / Connect / Run / Pause / Retry / View details4. **Actionable**: Every message tells next step; avoid generic "OK/Cancel"## Human Warmth (Balanced)Default: **80% information, 20% warmth**Key moments: **70/30** (first-time, empty state, failures, long waits)**Hard cap**: At most half sentence of warmth, followed by clear next step.**Order**:1. Acknowledge situation (no judgment)2. Restore control (pause/replay/edit/undo/clear Memory)3. Provide next action**Avoid**: Preachy encouragement, grand narratives, over-anthropomorphizing## Patterns**Getting started**:- "Starting with one sentence is enough. Describe your goal."- "Not sure where to begin? Tell me the outcome."**Long wait**:- "Running… You can switch tasks—I'll notify you when done."- "This may take a few minutes. To speed up: reduce Context / switch model."**Failure**:- "That didn't run through. Retry, or view details to fix."- "Connection failed. Re-authorize in Settings, or try again later."**Collaboration**:- "Align everyone to the same Context."- "Different opinions are fine. Write the goal first."## Errors/ExceptionsMust include:1. **What happened**2. (Optional) **Why**3. **What user can do next**Provide: Retry / View details / Go to Settings / Contact support / Copy logsNever blame user. Put error codes in "Details".

Frequently asked questions