CF humanize-korean
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 85개 AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스러운 한국어로 재작성한다. shim의 route_hint(light|standard|heavy)로 경로를 정해 잘 쓴 글은 1콜, 표준은 2콜, 중증·장문만 3+콜(진단→겨냥 윤문→finalize)로 처리한다. 트리거 — "AI 티 없애줘", "AI 같은 글 자연스럽게", "GPT/ChatGPT 문체", "AI 번역투 고쳐", "사람이 쓴 것처럼 윤문", "AI 윤문", "ChatGPT 티 제거", "한글 AI 탐지·윤문", "AI 글 사람처럼", "번역투 제거", "영어 인용 많은 글 윤문", "AI 글 티 안 나게", "휴머나이저", "humanize Korean", "AI detector bypass 한글". 후속 작업 — "특정 카테고리만 다시", "윤문 강도 조정", "장르 바꿔서", "이 문단만", "2차 윤문" 도 모두 이 스킬. 단순 맞춤법·오탈자 교정은 직접 처리, 번역은 번역 스킬, 내용 추가·삭제를 동반한 재작성은 별도 집필 스킬.
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬.
As a process F 39/100 · Will not run — References files that are not bundled: references/ai-tell-taxonomy.md, references/*, scripts/*.py
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: references/ai-tell-taxonomy.md - warning
missing-refreference to a missing file: references/* - warning
missing-refreference to a missing file: scripts/*.py
Process rating: all ten parameters 39/100
- 0Tools and files. 3 referenced file(s) missing: references/ai-tell-taxonomy.md, references/*, scripts/*.py
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 4351 tokens
- 100Steps. 91 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. No mutating operations
- low 17 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 17 example trigger phrases
- +3Description length 668: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 91 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (6 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.