# Avoid AI Writing Router

Use when a request combines AI-writing audit, rewrite, file editing, voice...

- Repository: https://github.com/conorbronsdon/avoid-ai-writing (5364 stars)
- Category: Writing
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add conorbronsdon/avoid-ai-writing --skill avoid-ai-writing-router -g -a claude-code -y`
Codex: `npx skills add conorbronsdon/avoid-ai-writing --skill avoid-ai-writing-router -g -a codex -y`
Cursor: `npx skills add conorbronsdon/avoid-ai-writing --skill avoid-ai-writing-router -g -a cursor -y`
Gemini CLI: `npx skills add conorbronsdon/avoid-ai-writing --skill avoid-ai-writing-router -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add conorbronsdon/avoid-ai-writing`

## Description

Use when a request combines AI-writing audit, rewrite, file editing, voice preservation, false-positive interpretation, verification, or when the user invokes Avoid AI Writing without naming a mode.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Avoid AI Writing Router

Coordinate the public Skills as a bounded workflow. Route to the narrowest owner, preserve context between stages, and stop when the requested job is complete. This Skill does not replace the original `avoid-ai-writing` rulebook.

## Authority chain

1. `../avoid-ai-writing/SKILL.md` is the canonical editorial authority.
2. `references/handoff-contract.md` defines what context and evidence can cross Skill boundaries.
3. `references/skill-graph.json` is the machine-readable source for nodes, typed edges, guards, and loop limits.
4. `references/routing-matrix.md` is the human-readable routing table.
5. `references/agency-role-lenses.md` defines the architecture, AI-evidence, implementation, and representation review lenses used to inspect the network.

Do not weaken, duplicate, or contradict the canonical Skill's preservation rules, evidence caveats, voice rules, pattern tiers, or pass behavior.

## Orchestration model

Classify the request once, create the smallest useful handoff envelope, then pass that envelope forward rather than asking every downstream Skill to infer the same context again.

The envelope should carry only observed or user-provided facts such as:

- intent and source kind
- requested editing scope and explicit factual corrections
- canonical context profile and detector context mode
- requested voice or supplied style sample
- protected semantic constraints
- whether detector, mutation, or verifier execution actually ran
- detector summary when available
- preservation status when available
- risk flags
- editing passes used and stop limit

Never mark an execution field as `executed` without host evidence.

## Primary routing

The rest: https://github.com/conorbronsdon/avoid-ai-writing/blob/HEAD/skills/avoid-ai-writing-router/SKILL.md