skills.rest
JaviMontano
JaviMontanoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

terse-output

Compresses prose into concise high-signal output while preserving technical accuracy and evidence tags.

Updated Jun 28, 2026
Search Tags:#token reduction#output style#text compression#concise writing#terse mode#evidence tags
One-click install
npx skills add https://github.com/JaviMontano/claude-plugins --skill terse-output-javimontano
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: terse-output
Source: https://github.com/JaviMontano/claude-plugins/tree/main/plugins/claude-native-toolkit/skills/terse-output
Command: npx skills add https://github.com/JaviMontano/claude-plugins --skill terse-output-javimontano

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve? Verbose AI responses waste tokens and bury key facts under filler, hedging, and pleasantries. This Skill applies a concise writing style that cuts fluff without losing technical precision, citations, or safety warnings. ## Core Features & Use Cases - High-signal compression: Drops articles, filler words, pleasantries, and hedging while keeping exact technical terms, numbers, file names, commands, and quoted errors. - Evidence preservation: Retains evidence tags like [DOC] and [CÓDIGO] and refuses to strip citations even when asked. - Auto-clarity exceptions: Never compresses safety warnings, irreversible confirmations, or multi-step sequences where order matters. - Use Case: Ask the assistant to switch to terse mode during a long debugging session so every status update arrives as a few dense bullets with all metrics and error messages intact. ## Quick Start Ask the assistant to be terse from now on and compress its answers without dropping any technical facts or evidence tags.

Frequently Asked Questions about terse-output

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

FAQPage Schema
How do I make AI responses more concise without losing details?▼

Invoke terse mode by asking the assistant to be terse or compress output. It drops filler words, pleasantries, and hedging while keeping exact technical terms, numbers, file names, commands, and evidence tags intact.

What is the difference between terse-output and caveman style?▼

terse-output is an original advisory style guide, not a fork of caveman. It uses no session hooks or caveman grammar templates, works as an invocable style rather than a global mode, and preserves editorial neutrality.

Does terse mode compress safety warnings or code blocks?▼

No. Auto-clarity rules exclude safety warnings, irreversible confirmations, and multi-step sequences where order matters. Code, commits, and pull requests stay in normal prose, and warnings or errors are quoted exactly.

When should I not use terse output mode?▼

Avoid it for final branded documents, legal text, full Minto-format pieces, or any case where density harms comprehension. If the user explicitly asks for detail or explanation, the request takes priority over compression.

Can terse mode drop citations or evidence tags to save tokens?▼

No. The skill explicitly refuses to drop evidence tags like [DOC] or citations even when asked, because removing provenance violates its sourcing rules. Compression applies only to prose, never to substance.

Related Skills

Explore More Content & Communication Skills→
darkmatterdarkmatter
1

verification-before-completion

Require fresh verification evidence before declaring software work complete.

Official
Basic
zhukunpenglinyutongzhukunpenglinyutong
4.1k

caveman

Compresses AI responses into concise direct answers while preserving technical accuracy and safety.

Community
Intermediate
joekhosbayarjoekhosbayar

bmad-editorial-review-prose

Reviews text for communication issues and outputs fixes in a structured editorial table.

Community
Advanced
dwaynimaydwaynimay

cavecrew

Delegate locate, edit, and diff review tasks to compressed caveman-style subagents.

Community
Basic