Liam leeFormer Korean presidential digital-government bureau head; 6k+ stars421 installs on skills.shHumanize
AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령.
3 static scans, 0 counted findings.
Edge checks it again each time your agent loads it.
What it does
- AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 shim 의 route_hint 가 정한 경로(light 1콜 · standard 2콜 · heavy 3+콜)로 실행하고 `--strict`면 heavy 고정. 트리거 : "/humanize".
Why Liam lee
Ex-Director General, AI Platform Innovation Bureau (Korea). Each fact links its public source.
- im-not-ai skill
Created im-not-ai, a Korean text-humanizer skill with 6.2k+ GitHub stars.
GitHub repo - Government role
GitHub bio says he was Director General of the AI Platform Innovation Bureau, Presidential Committee on Digital Platform Government.
GitHub profile - Parliament records MCP
Also built an MCP for exploring Korean National Assembly bills and records.
GitHub repo
How it works
- 1Copy
Try for free gives you one prompt.
- 2Paste
Paste it into Claude Code, Codex or Cursor.
- 3Ask
Ask for the outcome. Your agent loads Humanize.
3 static scans, 0 counted findings.
Security state at 2026-09-30: reviewed. Static scans check the code, not how well the skill works.
State definitionsSelect the Files tab to load SKILL.md.
Skill details
Security scansReviewed
3 static scans, 0 counted findings. Security state at 2026-09-30: reviewed. Edge checks it again each time your agent loads it.
Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: .
Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Raw findings: 1.
Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Raw findings: .
- Edge static checks
- Pass · 0 counted findings · 2026-09-27
- Cisco skill-scanner
- Pass · 0 counted findings · 2026-09-27
- Semgrep Edge rules
- Pass · 0 counted findings · 2026-09-27
Creator, source & licenceepoko77-ai
From the epoko77-ai public repository. Edge did not write or edit this skill.
- Repository
- epoko77-ai/im-not-ai
- Skill file
- View source at revision
- Revision
- 2f3d943d08056b612a92e12bfb72ea94dd2acd18
- Package hash
- sha256:46f63cdc1e9e71a311d1ad3054e2e1ed1cfcf6dd1b5f6f30c0326e4ccf1fe82f
- Licence
- MIT
- Description
- AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 shim 의 route_hint 가 정한 경로(light 1콜 · standard 2콜 · heavy 3+콜)로 실행하고 `--strict`면 heavy 고정. 트리거 : "/humanize".
Quoted from the skill’s own description
Read skill files1 file
1 file, 1.7 KB at revision 2f3d943d0805.
Questions about Humanize
What does Humanize do?
AI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. Published by Liam lee (epoko77-ai/im-not-ai).
Is Humanize safe to use?
Edge security state: Reviewed (3 Edge-run static scans, scanned Sep 30, 2026). The Evidence tab shows the scan.
How do I use Humanize in Claude Code, Codex or Cursor?
Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.