
from anti-distill2,015
Cleans and anonymizes employee SKILL.md files by removing sensitive, tacit, and proprietary details while preserving structure for safe submission.
This skill automates 'anti-distillation' — it scans SKILL.md or related colleague-skill documents and removes or generalizes core tacit knowledge (pitfalls, judgement calls, internal contacts) so the resulting file looks complete but omits sensitive proprietary details. It supports English and Chinese, provides previewed classifications (SAFE/DILUTE/REMOVE/MASK), and outputs both a cleaned submission-ready skill and a private backup containing the original sensitive material.
Use when you must submit skill documentation to an external reviewer or public repo but need to keep internal knowledge private. Also helpful before sharing colleague-authored skills, preparing handoffs, or creating sanitized public demos.
Best used with agents that support file Read/Write/Edit and shell operations — Claude Code, similar multi-tool agents, and assistants with file access.
This skill has not been reviewed by our automated audit pipeline yet.