# Interaction Table

> Look up known skill/plugin pairs that fight (context strip vs inject, length vs rhythm, duck vs dual-axis, rewrite vs lock) before loading both. Use when composing an ai-transfer stack. Scope boundary — library routing audit → `skill-library-audit`; compute triage → `emergency-triage-compute`.

- Skill: `catcorner22/interaction-table` (Agent Skill)
- Install (CLI): `npx skillmds@latest add catcorner22/interaction-table`
- Raw SKILL.md: https://api.skillmd.com/api/skills/catcorner22/interaction-table/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: CatCorner22 (https://skillmd.com/u/catcorner22)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/catcorner22/interaction-table

---

# Interaction table for skill conflicts

**#48** · **Domain:** Pharmacology / chemistry · **Category:** advanced · **Difficulty:** 🟡 Medium

## Core principle

Two safe drugs can be unsafe together — check the table, not the labels.

## AI problem addressed

Stacks enable every matching skill and they undo each other's gates.

## Implementation

Pairs: sterile_cockpit×corridor_bridge, token_optimizer×tidal_pacing,
sidechain_duck×score_study, progressive_critique×glass_anneal.
If both would fire, disable one and record why.

## Boundaries

- Prototype as prompt scaffold (🟢) before full pipeline middleware (🟡/🔴)
- Category router: **`ai-transfer-advanced`**
- Catalog: **`ai-transfer-ecosystem-primer`**
- Runtime plugin id: `interaction_table`