# leilei926524-tech/anti-distill

反蒸馏 Skill：清洗你被迫写的 Skill 文件，看起来完整，核心知识留给自己。Anti-distillation for employee Skills.

Repository: https://github.com/leilei926524-tech/anti-distill
Canonical: https://ross.abutalabs.com/products/anti-distill
License Family: other
Last push: 2026-07-02T23:09:50+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 35, longevity 10
- inputs: {"age_days": 153, "days_push": 62, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2388, forks 285 (observed 2026-08-28T04:06:42.697839+00:00)

## What it is
A tool that sanitizes AI Skill files employees are asked to write, producing a professional-looking but hollowed-out version for submission plus a private backup retaining the real knowledge. It protects workers from being 'distilled' into replaceable components by their employers.

## Use cases
- sanitize skill files before submitting to my employer
- strip core knowledge from documentation I'm forced to write
- generate a sanitized version of my colleague-skill file
- keep my expertise private while appearing compliant
- protect my career knowledge from being distilled into AI skills
- clean up skill documents so they look complete but reveal nothing

## When to choose
- you must submit Skill or knowledge-base files to your employer but want to retain your expertise
- you want automated identification and hollowing-out of replaceable vs core knowledge sections
- you need both a submittable sanitized version and a private backup

## When to avoid
- you want to genuinely share knowledge with your team or company
- your employer requires truthful, complete documentation and sanitizing it would violate policy
- you need a production-grade tool with a license or formal support

## Facets
- artifact type: cli-tool
- maturity: active
- function: nlp, llm-inference, developer-tools, privacy
- domain: developer-tools, privacy, hr, artificial-intelligence
- platform: cli, cross-platform
- tags: anti-distillation, skill-sanitization, knowledge-protection, prompt-engineering, career-asset

## Member repositories
- leilei926524-tech/anti-distill (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:42.697839+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:34:33.617638+00:00, confidence not recorded.
  - readme: https://github.com/leilei926524-tech/anti-distill (fetched 2026-08-28T04:06:42.697839+00:00, sha bd705e119662)
- Data as of 2026-08-30T08:39:29.467469+00:00.