Incinerate — Anti‑Distillation Defense

What it does

This skill helps individuals produce structured "pollution" content (persona configs, trap snippets, and execution plans) from personal data sources (chat logs, Git commits, documents) to make automated model distillation less reliable. It guides intake, selects a pollution mode (subtle/aggressive/chaos), and outputs actionable files intended for manual use.

When to use it

Use when you want to protect your personal knowledge and communication style from being copied into organizational models — for example before leaving a job, when exporting chat logs or repos, or when you want to introduce ambiguity into public artifacts. Not for automated modifications of company data; outputs are manual suggestions.

What's included

• Scripts: none packaged, but the repo contains prompt templates and tools for generating persona/traps (has_scripts=false).
• References: none included.
• Instructions: step-by-step intake questions, data-source selection (chat, git, docs, direct), pollution persona and traps templates, and a weekly execution plan. Outputs are written to a pollutions/{slug}/ directory for review.

Compatible agents

Likely usable by general-purpose chat/coding agents that can run Bash and file Read/Write tools; compatible with agents that support prompts and file operations (e.g., Copilot-style assistants, Claude/ChatGPT integrations).