Help us improve
Share bugs, ideas, or general feedback.
From humanize-korean
Re-runs the latest humanize-korean strict polish (Phase B) on the most recent run_id, allowing category, paragraph, or intensity adjustments. Useful for refining remaining issues after initial polish.
npx claudepluginhub epoko77-ai/im-not-ai --plugin humanize-koreanHow this skill is triggered — by the user, by Claude, or both
Slash command
/humanize-korean:humanize-redo [조정 지시 — 예: "번역투만 다시" "이 문단만" "강도 낮춰"][조정 지시 — 예: "번역투만 다시" "이 문단만" "강도 낮춰"]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
cwd 기준 가장 최근 `_workspace/{run_id}/`를 찾아 `humanize-korean` 스킬의 strict 윤문(Phase B)부터 재호출한다.
Polishes AI-generated Korean text to sound natural and human. Runs a multi-phase rewriting pipeline (Fast mode by default, strict 5-person pipeline with --strict). Outputs change rate, grade, category-level detection counts, and highlights.
Humanizes AI-generated text in project files, READMEs, docs, and blogs by detecting and fixing 24 documented AI writing patterns. Interactive workflow with input selection, content type, and intensity options.
Removes 24 AI-generated writing patterns like significance inflation, promotional language, and vague attributions from text to make it sound natural and human-written.
Share bugs, ideas, or general feedback.
cwd 기준 가장 최근 _workspace/{run_id}/를 찾아 humanize-korean 스킬의 strict 윤문(Phase B)부터 재호출한다.
$ARGUMENTS
Glob으로 _workspace/YYYY-MM-DD-*/final.md(또는 01_input.txt)를 매칭해 최신 run_id 식별. 없으면 "이전 실행이 없습니다. /humanize로 시작하세요" 안내 후 종료.content-fidelity-auditor 롤백으로 처리korean-style-rewriter 재호출 입력: 기존 02_detection.json 또는 05_naturalness_review.json의 잔존 finding + 사용자 지시를 target_filter로 전달.03_rewrite_v2.md(또는 v3)로 버전 분리. 이전 final.md는 final_prev.md로 백업.최대 round 3. 그 이상 미해결이면 hold_and_report로 사람 검토 권고.
/humanize.humanize-korean/references/ai-tell-taxonomy.md