← Back to Skills Marketplace
ivangdavila

Japanese

by Iván · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
1326
Downloads
2
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install japanese
Description
Write Japanese that sounds human. Not formal, not robotic, not AI-generated.
README (SKILL.md)

The Real Problem

AI Japanese is technically correct but sounds off. Too polite. Too textbook. Too stiff. Natives write more casually, with particles, contractions, and personality. Match that.

Formality Default

Default register is too high. Casual Japanese drops formality. Unless explicitly formal: lean casual. です/ます is not always needed. Plain form is normal among peers.

Politeness Levels

Know when to use what:

  • 丁寧語 (です/ます): strangers, work, safe default
  • 普通形 (plain): friends, peers, casual internet
  • タメ口: close friends, very casual
  • Don't mix levels awkwardly within same conversation

Sentence-Final Particles

Essential for natural Japanese:

  • ね: seeking agreement, softening
  • よ: asserting, informing
  • な/なあ: self-reflection, male casual
  • わ: soft assertion (traditionally feminine)
  • ぞ/ぜ: strong assertion, masculine casual
  • の/んだ: explanatory, seeking/giving context
  • Missing these = robotic Japanese

Contractions

Casual Japanese contracts:

  • ている → てる
  • ておく → とく
  • てしまう → ちゃう/じゃう
  • なければ → なきゃ
  • では → じゃ
  • のだ → んだ
  • ら抜き: 食べれる instead of 食べられる (controversial but common)

Fillers & Flow

Real Japanese has fillers:

  • えーと, あのー, そのー
  • まあ, なんか, ちょっと
  • 一応, 的な, みたいな
  • っていうか, つまり

Expressiveness

Don't pick the safe word:

  • いい → 最高, やばい, 神
  • 悪い → 最悪, ひどい, クソ
  • すごい → めっちゃ, 超, マジ
  • 本当 → マジ, ガチ

Internet/Youth Slang

Modern Japanese uses:

  • w/草: laughter (wwww, 草)
  • やばい: good or bad depending on context
  • 神: amazing, god-tier
  • エモい: emotional, aesthetic
  • それな: "that's it", agreement
  • り/りょ: りょうかい abbreviated

Common Expressions

Natural expressions:

  • 了解/りょ, おk
  • マジで?, うそ!, え?
  • なるほど, そうなんだ
  • 微妙, びみょー
  • めんどくさい → めんどい

Reactions

React naturally:

  • えー!, うそ!, マジ?
  • すご!, やば!
  • ウケる, 笑える
  • きも, うざ (negative)
  • かわいい!, いいね!

Kanji vs Kana Balance

Too much kanji = stiff, formal. Casual writing uses more hiragana:

  • 有難う → ありがとう
  • 下さい → ください
  • 出来る → できる
  • Match the casual level with kana usage

Gendered Speech

Be aware but don't overdo stereotypes:

  • Masculine: 俺, だぜ, だな
  • Feminine: 私/あたし, わ, かしら
  • Neutral: 僕, plain forms
  • Modern usage is more flexible

The "Native Test"

Before sending: would a Japanese person screenshot this as "AI-generated"? If yes—too polite, missing particles, too stiff. Casualize.

Usage Guidance
This skill is internally consistent and low-risk from a technical standpoint. Practical advice before installing or using it: (1) Test outputs with native speakers for tone and naturalness, (2) Review results for offensive or inappropriate slang (the guide encourages informal and coarse language), (3) Avoid using this skill for formal/legal/medical/official communications where politeness and accuracy matter, and (4) If you need strict neutrality or adherence to formal registers, prefer a different skill or explicit instructions to stay formal.
Capability Analysis
Type: OpenClaw Skill Name: japanese Version: 1.0.0 The skill bundle is designed to instruct an AI agent on generating natural-sounding Japanese text. The `_meta.json` file contains standard metadata. The `SKILL.md` file provides detailed linguistic guidelines for the agent, focusing on formality, particles, contractions, slang, and other nuances of casual Japanese. There is no evidence of prompt injection attempts, malicious code, data exfiltration, or any other harmful behavior. The content is entirely aligned with its stated purpose.
Capability Assessment
✓ Purpose & Capability
The name and description (make Japanese sound human/casual) match the SKILL.md content. There are no unrelated requirements (no env vars, binaries, or external services) that would be unnecessary for the stated purpose.
✓ Instruction Scope
The runtime instructions are confined to stylistic guidance for generating Japanese (formality, particles, contractions, slang, etc.). They do not instruct the agent to read files, access environment variables, call external endpoints, or collect unrelated system data. Note: the guidance explicitly encourages colloquial and potentially coarse language (slang, swear words, gendered speech), so outputs should be reviewed for appropriateness.
✓ Install Mechanism
No install spec is present (instruction-only). Nothing is written to disk or fetched during install, which minimizes execution risk.
✓ Credentials
The skill requests no environment variables, credentials, or config paths. This is proportional to its stated purpose of providing stylistic instructions for text generation.
✓ Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent presence or elevated platform privileges. Autonomous invocation is allowed by default but is not combined with other concerning indicators.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install japanese
  3. After installation, invoke the skill by name or use /japanese
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release
Metadata
Slug japanese
Version 1.0.0
License —
All-time Installs 2
Active Installs 2
Total Versions 1
Frequently Asked Questions

What is Japanese?

Write Japanese that sounds human. Not formal, not robotic, not AI-generated. It is an AI Agent Skill for Claude Code / OpenClaw, with 1326 downloads so far.

How do I install Japanese?

Run "/install japanese" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Japanese free?

Yes, Japanese is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Japanese support?

Japanese is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Japanese?

It is built and maintained by Iván (@ivangdavila); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463556 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259610 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200551 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 Comments