playbooks

home / skills / lobehub / lobe-chat / microcopy

microcopy skill

/.agents/skills/microcopy

This skill helps you craft clear, user-friendly UI copy and microcopy that aligns with brand guidelines and improves onboarding and error messaging.

npx playbooks add skill lobehub/lobe-chat --skill microcopy

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.5 KB
---
name: microcopy
description: 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 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 |

## Brand Principles

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

## Writing Rules

1. **Clarity first**: Short sentences, strong verbs, minimal adjectives
2. **Layered**: Main line (simple) + optional detail (precise)
3. **Consistent verbs**: Create / Connect / Run / Pause / Retry / View details
4. **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/Exceptions

Must include:
1. **What happened**
2. (Optional) **Why**
3. **What user can do next**

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

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

Overview

This skill provides UI copy and microcopy guidelines tailored for collaborative agent interfaces. It helps authors write clear, actionable, and consistent UI text for buttons, errors, empty states, onboarding, and translations. The guidance supports both English and Chinese terminology and emphasizes collaboration-focused language and user control.

How this skill works

The skill inspects UI copy requests and suggests concise main lines plus optional detail lines, consistent verbs, and human-warmth levels. It flags terminology mismatches, offers localized equivalents (Chinese ↔ English), and produces ready-to-use microcopy for common patterns like onboarding, failures, long waits, and empty states. It also supplies next-step actions and error remediation text with structured details.

When to use it

  • Writing or refining UI text for buttons, menus, labels, and tooltips
  • Drafting error messages, retry flows, or diagnostic details
  • Creating empty states, onboarding prompts, and first-time user tips
  • Preparing i18n translation pairs or ensuring consistent terminology
  • Designing multi-agent collaboration prompts, shared Context copy

Best practices

  • Put clarity first: short sentences, strong verbs, minimal adjectives
  • Use layered copy: main line (simple) plus optional detail (precise)
  • Prefer consistent verbs: Create, Connect, Run, Pause, Retry, View details
  • Make every message actionable: show the next step or control
  • Keep human warmth minimal: ~20% warmth in tone, more only for key moments
  • Errors must state what happened, why (if known), and clear next actions

Example use cases

  • A button label: 'Create agent' with tooltip: 'One sentence → usable Agent; describe the goal.'
  • Error prompt: 'Connection failed. Re-authorize in Settings, or try again later.' with 'View details' option
  • Long-wait notice: 'Running… You can switch tasks — I’ll notify you when done.' plus speed-up tips
  • Empty state: 'Starting with one sentence is enough. Describe your goal.' with a clear CTA
  • i18n check: convert '空间' → 'Workspace' and ensure consistent use across screens

FAQ

Does this cover translations between Chinese and English?

Yes. It provides preferred terminology pairs and guidance to keep terms consistent across languages.

How should errors be formatted?

State what happened, optionally why, and present clear next actions like Retry, View details, or Go to Settings.