English Polish

Refine English writing for grammar, fluency, and native-level expression. Covers academic, business, creative, and casual registers.

3,891 stars

Best use case

English Polish is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Refine English writing for grammar, fluency, and native-level expression. Covers academic, business, creative, and casual registers.

Teams using English Polish should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/qf-english-polish/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/371166758-qq/qf-english-polish/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/qf-english-polish/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How English Polish Compares

Feature / AgentEnglish PolishStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Refine English writing for grammar, fluency, and native-level expression. Covers academic, business, creative, and casual registers.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# English Polish

Refine English writing for grammar, fluency, and native-level expression. Covers academic, business, creative, and casual registers.

## Description

This skill provides systematic English writing improvement for non-native speakers and anyone looking to elevate their prose. It goes beyond basic grammar correction to address fluency, tone consistency, idiomatic usage, register appropriateness, and stylistic refinement across different writing contexts.

## When to Use

- Polishing emails, essays, articles, or reports written in English
- Improving English cover letters, resumes, or LinkedIn profiles
- Refining academic papers written by non-native English speakers
- Making business communications sound more professional
- Elevating casual writing to sound more natural and fluent

## Instructions

### Review Process

Apply these four layers in order. Each layer builds on the previous.

#### Layer 1: Grammar & Mechanics

Fix objective errors first:

| Category | Common Issues |
|----------|--------------|
| **Subject-verb agreement** | "The data show" (plural) vs "The data shows" (common but debated) |
| **Article usage** | a/an/the misuse, especially with uncountable nouns |
| **Tense consistency** | Unjustified tense shifts within paragraphs |
| **Pronoun reference** | Ambiguous "it", "this", "which" |
| **Comma splices** | Joining independent clauses with only a comma |
| **Dangling modifiers** | "Walking down the street, the trees were beautiful" |
| **Parallelism** | "I like reading, writing, and to code" → "reading, writing, and coding" |

#### Layer 2: Fluency & Flow

Address sentence-level smoothness:

**Fixes to apply:**
- Break sentences over 35 words into shorter ones
- Vary sentence length (mix short punchy sentences with longer analytical ones)
- Remove filler phrases: "in order to" → "to", "due to the fact that" → "because", "at this point in time" → "now"
- Replace weak verbs: "make a decision" → "decide", "give an explanation" → "explain", "have a discussion" → "discuss"
- Use transitional phrases between ideas: however, moreover, in contrast, as a result
- Ensure each paragraph flows logically from the previous one

**Common Chinese-English Interference Patterns:**

| Chinese Pattern | Literal Translation | Natural English |
|----------------|-------------------|-----------------|
| 虽然...但是 | Although... but... | Although... [no "but"] |
| 我觉得 | I feel/think | I believe/In my opinion |
| 毫无疑问 | Without doubt | Undoubtedly / Certainly |
| 越来越 | More and more | Increasingly / Growing |
| 进行研究 | Conduct research | Study / Investigate / Research |

#### Layer 3: Register & Tone

Match the writing level to the context:

**Academic**: Formal, precise, hedged
- Use: "Furthermore," "Nevertheless," "It has been demonstrated"
- Avoid: contractions, colloquialisms, rhetorical questions

**Business**: Professional, clear, action-oriented
- Use: "Please find attached," "I'd like to propose," "Looking forward to"
- Avoid: overly academic language, slang, emotional language

**Casual/Conversational**: Natural, relaxed, direct
- Use: contractions, phrasal verbs, idioms
- Avoid: overly formal constructions, unnecessary complexity

**Creative**: Engaging, varied, expressive
- Use: sensory language, metaphors, varied sentence structures
- Avoid: clichés, passive voice overuse

#### Layer 4: Idiomatic Enhancement

Replace literal or awkward phrasing with natural English:

| Awkward | Natural |
|---------|---------|
| "I'm very agree with you" | "I completely agree" |
| "It has a big impact to me" | "It had a huge impact on me" |
| "I have no idea about this" | "I'm not familiar with this" |
| "I will try my best to do it" | "I'll do my best" |
| "Every coin has two sides" | "There are two sides to every story" |

### Output Format

Present corrections as:

```
## English Polish Results

**Overall Level**: [Advanced / Intermediate / Basic]
**Primary Issues**: [Grammar / Fluency / Tone / Idiom]

### Corrections

1. **[Category]** Original → Revised
   Reason: Brief explanation

2. ...

### Refined Version
[Full polished text]
```

If the text is already near-native, say so — don't force unnecessary changes. Sometimes the original is fine and only minor tweaks are needed.

## Examples

**Before**: "With the development of technology, more and more people begin to use AI tools to improve their work efficiency. Although AI has many advantages, but it also brings some problems."

**After**: "As technology advances, an increasing number of people are adopting AI tools to boost productivity. While AI offers significant advantages, it also presents new challenges."

**Before**: "I am writing this email to inform you that we need to have a meeting about the project. Please let me know your available time so that we can schedule it."

**After**: "I'd like to schedule a meeting to discuss the project. Could you share your availability this week?"

**Before**: "The reason why I chose this topic is because it is very interesting and nobody has researched it before."

**After**: "I chose this topic because it raises intriguing questions that remain underexplored in the literature."

## Tips

- Read the polished text aloud — if it sounds awkward to say, it's not fluent enough
- Less is more: if a word doesn't add meaning, remove it
- Prefer active voice unless passive serves a specific purpose (academic method descriptions, diplomatic language)
- Keep the author's voice — don't rewrite their personality out of the text
- For academic writing, prefer "this study demonstrates" over "it is demonstrated by this study"

Related Skills

medical-email-polisher

3891
from openclaw/skills

Transforms rough email drafts into polished, professional medical correspondence.

ui-polish-pass

3891
from openclaw/skills

Core pack — always active as final step. Visual polish pass for spacing, hierarchy, alignment, and cleanup. Runs after design-review and ux-baseline-check as the last quality step before presenting work.

collab-offer-polisher

3891
from openclaw/skills

把合作邀约、商务私信、品牌合作需求和合作条款草稿,改写成更专业、更容易推进合作的版本。

Academic Paper Polish

3891
from openclaw/skills

Transform rough drafts into publication-ready manuscripts following Nature, Science, and top-tier journal conventions. Supports both English and Chinese academic writing.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning