language-design

Enforce banned-word alternatives and tendency-focused tone in Japanese user-facing copy.

1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/COCOSiL-inc/COCOSiL_Analysis_V2 --skill language-design-cocosil-inc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: language-design
Source: https://github.com/COCOSiL-inc/COCOSiL_Analysis_V2/tree/main/.claude/skills/language-design
Command: npx skills add https://github.com/COCOSiL-inc/COCOSiL_Analysis_V2 --skill language-design-cocosil-inc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents product text from accidentally sounding like a fortune-telling service by enforcing COCOSiL’s brand language rules for UI, AI responses, errors, and sharing copy.

Core Features & Use Cases

  • Ban-list enforcement for user-facing language: Replaces terms like 「占い」/「鑑定」/「霊感」 with approved alternatives to avoid spiritual/authority impressions.
  • Tone guidance for AI and UI: Keeps messaging “warm but not flattering,” “evidence-based empathy,” and “tendency-focused” wording rather than absolute claims.
  • Consistency for brand phrases: Ensures approved one-liners and LP/SNS variants are used correctly across surfaces.
  • Scope control: Allows internal technical identifiers to use original proper names while restricting only user-visible copy.

Quick Start

When drafting any UI label, AI message, SNS share card text, or error tooltip, review this skill’s banned-word table and rewrite any prohibited terms using the specified alternatives.

Frequently Asked Questions about language-design

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I standardize Japanese UI copy so it doesn't sound like fortune-telling?

To standardize Japanese UI copy so it doesn't sound like fortune-telling, apply a banned-word replacement table that swaps terms like 「占い」 or 「鑑定」 for approved alternatives. This ensures user-facing text remains warm and evidence-based.

What is the best way to enforce tone guidelines for AI prompt responses?

The best way to enforce tone guidelines for AI prompt responses is to apply tendency-focused phrasing and evidence-based empathy rules. This keeps messaging warm without sounding flattering or making absolute claims.

Can I use restricted spiritual terms in internal technical identifiers?

Yes, you can use restricted spiritual terms in internal technical identifiers. The brand voice rules only restrict user-visible copy such as UI labels, AI messages, and SNS share cards, while internal scope remains unaffected.

How do I write UX microcopy for error messages without sounding authoritative?

To write UX microcopy for error messages without sounding authoritative, replace authoritative or spiritual terms with approved alternatives and frame the text around tendencies. This maintains a warm, empathetic tone across all product surfaces.

Does this copywriting approach apply to SNS share cards and marketing landing pages?

Yes, this copywriting approach applies to SNS share cards and marketing landing pages. The standardization rules ensure approved one-liners and variants are used consistently across all user-facing communication surfaces.

Why should I replace banned words like 「霊感」 in brand voice guidelines?

You should replace banned words like 「霊感」 in brand voice guidelines to prevent product text from accidentally giving a fortune-telling impression. Enforcing these alternative terms ensures your messaging stays grounded in evidence-based empathy.