Skills
.Work. You
Rest

ai-collaboration-standards

Community

Ensure AI responses are evidence-based.

Software Engineering#collaboration#ai#standards#hallucination#certainty#evidence-based
AuthorAsiaOstrich
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill prevents AI assistants from hallucinating or providing unverified information, ensuring all responses are grounded in evidence and clearly state their certainty level.

Core Features & Use Cases

  • Evidence-Based Responses: Guarantees AI responses are directly supported by provided code or documentation.
  • Certainty Tagging: Automatically applies tags like [Confirmed], [Inferred], [Assumption], and [Unknown] to statements.
  • Source Attribution: Requires citing the source (file path, line number, URL) for all information.
  • Recommendation Logic: Ensures that when options are presented, a clear recommendation with reasoning is always included.
  • Use Case: When analyzing a code snippet, the AI will use [Confirmed] for direct observations and [Inferred] for logical deductions, always citing the exact line of code, preventing the AI from making up functionality.

Quick Start

Use the ai-collaboration-standards skill to ensure all AI responses are evidence-based and cite their sources.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: ai-collaboration-standards
Download link: https://github.com/AsiaOstrich/universal-dev-standards/archive/main.zip#ai-collaboration-standards

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.