Skills
.Work. You
Rest

literal-answers

Community

Answer questions literally and STOP to clarify.

Content & Communication#conversational-safety#clarification-prompting#prompt-injection-safety#honest-responses#stop-after-answer#user-questions#literal-answering
Authorjagreehal
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill ensures Claude answers questions literally, avoiding inference of hidden instructions and preventing prompt hijacking, thereby improving accuracy and safety.

Core Features & Use Cases

  • Literal answering: respond to user questions exactly as asked, with no inferred directives.
  • STOP after answering: halt actions after providing the answer and prompt for next steps.
  • Clarification prompts: request direction when the user's intent is unclear.
  • Safety and honesty: clearly communicate confidence and potential risks when appropriate.

Quick Start

Ask a user a question, provide a literal answer, then prompt for what the user wants to do next.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: literal-answers
Download link: https://github.com/jagreehal/jagreehal-claude-skills/archive/main.zip#literal-answers

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.