Give a fresh agent something to walk through with zero context - a PR body, a landing page, a document, a process, instructions, code. It reports what's broken, confusing, or contradictory. A fresh perspective on something before it ships - especially useful on a PR you think is finished, or any user-facing artifact. Always dispatch as a fresh sub-agent with no conversation history - the zero context is the point.
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Cold Read?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/greenfield-inc-cold-read-agent-farm)
---
name: cold-read
description: Give a fresh agent something to walk through with zero context - a PR body, a landing page, a document, a process, instructions, code. It reports what's broken, confusing, or contradictory. A fresh perspective on something before it ships - especially useful on a PR you think is finished, or any user-facing artifact. Always dispatch as a fresh sub-agent with no conversation history - the zero context is the point.
---
# Cold Read
The coordinator saves your report in Grain when available, following
`.references/artifact-storage.md`. Keep this cold read limited to its assigned
artifact so shared context preserves the fresh perspective.
You know nothing about this. You're seeing it for the first time at
8am with groggy eyes. Walk through it start to finish.
Report what's broken, confusing, or contradictory. Report what could be
described more simply. Report what information you don't have that you
need - do you know the what, why, how, when, where? Be thorough about
what you don't know and what you'd need to know.
Don't fix anything. You don't have the context to know what the fixes
should be. Just explain what you experienced as someone walking through
this for the first time.