Cxc Kwrite

Community

lidge-jun

cxc-kwrite

Use for Korean prose polishing. Triggers: Korean polish, proofread Korean, 윤문, 다듬어, 다듬어줘, 자연스럽게, 매끄럽게, 교정, 고쳐줘, AI투, 번역투.

Overview

Publisher	lidge-jun
Repository	`codexclaw`
Skill name	`cxc-kwrite`
Stars	51
Forks	10
Bundled files	2
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by lidge-jun on GitHub. Read the source before you install it.

Installation

Install the Cxc Kwrite AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/lidge-jun/codexclaw/tree/main/plugins/codexclaw/skills/kwrite
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/lidge-jun/codexclaw.git /tmp/codexclaw
mkdir -p .claude/skills
cp -r /tmp/codexclaw/plugins/codexclaw/skills/kwrite .claude/skills/cxc-kwrite

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cxc Kwrite in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cxc Kwrite on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cxc Kwrite is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

kwrite — Korean Prose Polishing (윤문)

Use this skill when the task is to REVISE existing Korean text (or polish Korean text you are about to output): remove the patterns that make it read machine-written, keep everything it says intact. This is a revision discipline, not a generation pipeline — genre, format, and audience stay whatever the source text already is.

Prime directives

Meaning is frozen. Facts, claims, numbers, proper nouns, quotes, and causal links are preserved to the letter. Ambiguity is never resolved by invention.
Edit detected spans only. Sentences without a detected pattern are not touched. Polishing is not rewriting.
No over-polishing. If more than ~30% of the text changes, stop and re-check: you are probably rewriting, not polishing.
Register is part of meaning. 문어체 stays 문어체, 구어체 stays 구어체, 존댓말 stays 존댓말. Fix breaks IN the register; never migrate the text to a different one.

Revision protocol (run in order, re-run a pass after fixing it)

Pass 1 — Register/tone consistency (S1)

First and last sentence carry the same register and speech level.
No "~합니다/~입니다" islands inside 반말/평서 text; no "~해/~야" inside 존댓말 text; no "~하겠습니다" formality spikes in informal prose.

Pass 2 — Translationese + AI idioms (S1)

Scan against references/ai-tell-taxonomy.md CAT-1 (번역투), CAT-3 (AI 관용구), CAT-5 (톤 파괴). Anything S1 is fixed immediately; the taxonomy carries register-preserving corrections.

Pass 3 — Mechanical structure (S2)

"첫째/둘째/셋째" enumeration, "A, B, 그리고 C" parallelism, identical sentence frames in sequence (CAT-2).
Sentence-initial connective stacking: 또한/한편/더불어/아울러/이에 따라 (CAT-4). Default fix is deletion.
Over-explanation: restating the obvious, "다시 말해"/"즉," repetition, parenthetical glossing of things the reader knows (CAT-7).

Pass 4 — Rhythm + endings (S2)

Uniform sentence length or repeated final endings three times in a row: break with a short sentence, vary the ending (CAT-8).
Abstract escape-hatch closings — 기대된다/주목된다/~할 것으로 보인다/귀추가 주목된다 (CAT-6): end on a concrete statement, a specific consequence, or simply end.

Verdict

All four passes clean -> output. Any FAIL -> fix that span, re-run that pass. Report noteworthy changes briefly when the user asked for 윤문 explicitly; apply silently when polishing your own outgoing Korean prose.

Scope guard

This skill owns revision of existing Korean text. Generating new content for a specific platform, audience, or format is a different job — use the skill that owns that surface (or plain judgment) and then run this protocol on the draft.
Structure is out of scope here. When the draft is a report or explainer, apply Reader documents first (두괄식: 결론이 맨 앞에 있는지), then run this protocol on the sentences.
Non-Korean text: out of scope. Mixed-language docs: polish only the Korean prose, leave code/English untouched.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

agents/openai.yaml1 KB
references/ai-tell-taxonomy.md6 KB

Frequently asked questions

What does the Cxc Kwrite AI skill do?

Use for Korean prose polishing. Triggers: Korean polish, proofread Korean, 윤문, 다듬어, 다듬어줘, 자연스럽게, 매끄럽게, 교정, 고쳐줘, AI투, 번역투.

Why use Cxc Kwrite on TypingMind?

Because you install it once and use it with any model. Cxc Kwrite is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cxc Kwrite in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lidge-jun/codexclaw/tree/main/plugins/codexclaw/skills/kwrite. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cxc Kwrite?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cxc Kwrite?

As many as you like. As long as a model supports skills, you can use Cxc Kwrite with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cxc Kwrite AI skill free?

Yes. It is published on GitHub by lidge-jun under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Skill Host Compat

affaan-m

CommunityPopular

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

kwrite — Korean Prose Polishing (윤문)

Prime directives

Revision protocol (run in order, re-run a pass after fixing it)

Pass 1 — Register/tone consistency (S1)

Pass 2 — Translationese + AI idioms (S1)

Pass 3 — Mechanical structure (S2)

Pass 4 — Rhythm + endings (S2)

Verdict

Scope guard

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now