talk-normal

Inject bilingual English/Chinese conciseness rules into AGENTS.md.

1.8k|60|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/hexiecs/talk-normal --skill talk-normal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: talk-normal
Source: https://github.com/hexiecs/talk-normal/tree/main/skill
Command: npx skills add https://github.com/hexiecs/talk-normal --skill talk-normal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill stops verbose, corporate-sounding LLM output by injecting an always-on talk-normal block into your workspace's AGENTS.md, preserving essential information.

Core Features & Use Cases

  • Install or update an always-on talk-normal block in AGENTS.md to reduce filler, hedging, and overly verbose patterns.
  • Apply bilingual English/Chinese rules so responses stay concise without sacrificing meaning.
  • Marked changes allow safe uninstall and simple updates, keeping existing rules intact.

Quick Start

Install talk-normal to inject concise, bilingual rules into your workspace's AGENTS.md.

Frequently Asked Questions about talk-normal

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

FAQPage Schema
How do I reduce LLM verbosity in workspace responses without losing essential information?

You reduce LLM verbosity by injecting an always-on talk-normal block into AGENTS.md, applying bilingual English and Chinese rules that trim filler while preserving essential information across standard agent workspaces.

What's the best way to enforce concise reply rules for bilingual English and Chinese agent outputs?

Enforce concise bilingual rules by installing a system prompt block into your workspace's AGENTS.md, applying English and Chinese verbosity reduction constraints that deliver concise replies without sacrificing meaning.

Can I update AGENTS.md rules without overwriting my existing workspace configurations?

You can update AGENTS.md rules safely because the installer places new rules between explicit markers, keeping existing rules intact and supporting idempotent updates via install.sh without duplicating blocks.

Does the talk-normal installer work with standard agent workspaces that don't use external dependencies?

The installer works with standard agent workspaces requiring no external dependencies, using a one-time install.sh script to inject bilingual verbosity rules directly into AGENTS.md for immediate concise output.

Why does my LLM still produce verbose corporate-sounding output after setting workspace prompts?

Verbose output persists when standard workspace prompts lack explicit verbosity constraints; injecting an always-on talk-normal block into AGENTS.md stops corporate-sounding filler by enforcing concise bilingual English and Chinese rules.

How do I uninstall concise output rules from AGENTS.md if I need longer LLM responses?

Uninstall concise output rules by removing the marked talk-normal block from AGENTS.md; explicit markers allow safe uninstall, deleting only the injected verbosity rules while keeping your original configurations intact.