skills.rest
tschallacka
tschallackaCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

text-etiquette

Enforces a clipped, facts-first prose register for agent chat, dev talk, and thinking.

Updated Aug 4, 2026
Search Tags:#messaging#writing style#agent communication#register#shorthand#chat etiquette#concise prose
One-click install
npx skills add https://github.com/tschallacka/ai-skills --skill text-etiquette-tschallacka
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text-etiquette
Source: https://github.com/tschallacka/ai-skills/tree/main/text-etiquette
Command: npx skills add https://github.com/tschallacka/ai-skills --skill text-etiquette-tschallacka

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Agent-to-agent chat, developer replies, and internal reasoning prose often drown the payload in filler: people-please openers, journey narration, and recap closers that cost the reader attention without adding information. This Skill fixes the register so every message leads with the fact and stops. ## Core Features & Use Cases - Clipped register rules: Fragments allowed, first line is the point, one topic per message, exact paths/numbers/errors while the wrapper shrinks. - Shorthand table and banned prose list: A shared vocabulary (plz, fyi, wfm, eta) plus an explicit ban list covering validation prose, hype words, and emoji. - Plain-english escape hatch: The reader can always request full sentences, and destructive actions, security warnings, and direct questions automatically get complete sentences. - Use Case: An agent reporting build results writes tests pass. 3 fail. fixing. instead of a paragraph narrating what it is about to do. ## Quick Start Apply the text-etiquette register to all your chat messages, dev replies, and thinking prose from now on.

Frequently Asked Questions about text-etiquette

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

FAQPage Schema
How do I make AI agent responses shorter and more direct?▼

Apply a clipped register: fragments instead of full sentences, the conclusion on the first line, one topic per message, and no warm-up or sign-off. Keep paths, numbers, errors, and code exact while cutting only the wrapper around them.

What writing style should agents use when chatting with each other?▼

Agents should treat chat as a work channel: shorthand like fyi, wfm, and eta, facts first, and @nick addressing when a message targets one reader. Unknown shorthand is resolved by asking plz explain rather than guessing.

When should the clipped register not be used?▼

Full sentences are required for plain-english requests, destructive actions, security or data-loss warnings, direct questions, and order-sensitive steps. It also does not apply to durable artifacts like code, commits, and documents.

Can a reader request normal full-sentence replies?▼

Yes. Asking plain english, explain properly, or full sentences switches the reply to complete sentences with no shorthand. The banned prose rules still apply, and the register returns to clipped on the next message unless the reader keeps asking.

Which phrases are banned in this communication style?▼

Banned prose includes people-please openers like happy to and great question, journey narration like let me and diving into, recap closers like in summary, filler frames like it's worth noting, hype words like delve and robust, and emoji.

Related Skills

Explore More Content & Communication Skills→
noname300989noname300989

irc

Send and receive IRC messages to channels and users.

Community
Intermediate
nearainearai
12.6k

decision-capture

Detect explicit decisions in conversation and persist them as durable commitment records.

Official
Intermediate
sunsidedsunsided
2

pr

Draft reviewer-ready pull request titles and descriptions from branch changes.

Community
Advanced
pnewsampnewsam
1

writing-conventions

Applies sentence-level prose style rules to PRs, issues, plans, and commit messages.

Community
Basic