Agent Skills: investigate-before-acting

Mandatory protocol that prevents AI agents from fabricating information. Forces best practice search before every action — coding, design, content, pricing, naming, architecture, everything. Every decision must have a citation (source name + URL + direct quote). Based on Anthropic official hallucination reduction techniques.

UncategorizedID: majiayu000/claude-skill-registry/investigate-before-acting

Author

majiayu000

https://github.com/majiayu000 View all skills

Repository

majiayu000/claude-skill-registry

majiayu000License: MIT

57788

Install this agent skill to your local

pnpm dlx add-skill https://github.com/majiayu000/claude-skill-registry/investigate-before-acting

Skill Files

Browse the full folder contents for investigate-before-acting.

Download Skill

Loading file tree…

Select a file to preview its contents.