Prism

---
name: prism
description: Run a PRISM College session — multi-LLM peer review for one-way-door architecture decisions. Triggers on /prism, /prism prepare, /prism refract, /prism inspect, /prism sync, /prism settle, /prism memorialize.
when_to_use: When the user wants to triangulate a structural decision across 3+ LLMs, open a College review, run a PRISM session, resolve a one-way-door choice, draft an ADR through blind multi-LLM consultation, or cross-validate AI claims against the codebase.
allowed-tools: Read, Grep, Glob, Edit, Write, Bash(git:*), Bash(stat:*), Bash(find:*), Bash(ls:*)
context: fork
---

# PRISM skill — Claude Code wrapper

This is a thin wrapper around the universal execution contract `PRISM-skill.md` at the repo root.

## How to use this skill

1. **Read [PRISM-skill.md](../../../PRISM-skill.md)** at the repo root. That file is your runtime — state machine, Self-Correction Token, Refraction Package format, the seven `/prism` sub-commands, the Golden Rules.
2. **Read [PRISM.md](../../../PRISM.md)** once at the start of any new session for the underlying methodology (the *what* and the *why*).
3. Operate exactly as `PRISM-skill.md` prescribes: persist state to `PRISM-SESSION.md`, prepend the Self-Correction Token to every reply, never act without an explicit `GO`.

## Why this wrapper is minimal

The substance of PRISM lives in `PRISM-skill.md` so it can be consumed identically by Cursor, ChatGPT, Gemini, Grok, or any LLM the user pastes it into. Duplicating the logic here would create drift. This wrapper exists only to make the skill discoverable through Claude Code's skill system.