{"slug":"chrono-meta-ko-tech-writer","name":"ko-tech-writer","description":"Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\".","long_description":"---\nname: ko-tech-writer\ndescription: 'Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\".'\nuser-invocable: true\nallowed-tools: [\"Read\", \"Write\", \"Edit\", \"Bash\", \"Grep\", \"Glob\", \"WebFetch\"]\nmodel: sonnet\n---\n\n# ko-tech-writer — 한국어 기술문서 집필·개고 파이프라인\n\n독자 대면 한국어 기술 산출물(테크블로그 글 · 기술문서 · 발표 파생 자산)을 쓰거나 개고한다.\n핵심 전제: **좋은 문장은 취향이 아니라 절차다** — 실물 표본으로 톤을 캘리브레이션하고,\n번역투를 패턴 목록으로 제거하고, 수치는 근거와 창을 달고, 렌더 결과를 눈으로 확인한다.\n\n> 출처: 2026-08-10 발표 기술문서 세션에서 실측으로 벼려진 규율의 자산화. 이 문서의 규칙\n> 클래스는 그 세션의 개고에서 실제로 검출·수리된 것들이다 — 근거 원장은 그 세션 기록\n> (`fh_completed_2026-08-10` 및 해당 개고 커밋 이력. 비공개 세션 기록이라 외부 배포본\n> 독자에게는 도달하지 않는 내부 포인터다). **실측 근거가 없는 클래스를 추가하지 않는 것**이\n> 이 문서의 유지 규칙이다. 이 SKILL.md 자체는 독자 대면 문서가 아니라 하네스 자산이므로\n> 이 파이프라인의 적용 대상이 아니다(FH 하우스 스타일을 따른다).\n\n## Step 0 — 대상 판별 (레지스터 분기)\n\n같은 내용도 매체에 따라 규율이 다르다. 먼저 셋 중 무엇인지 정한다:\n\n| 대상 | 레지스터 | 이 스킬의 적용 |\n|---|---|---|\n| **독자용 문서** (블로그 글·기술문서) | 문어 존댓말 (습니다체) | Step 1~5 전체 |\n| **낭독 대본** (발표 스크립트) | 구어 발표체 | Step 2~4 만 — 구어 리듬 유지, 줄표는 «쉼»으로만 실현되므로 소리로 안 들리는 동격·재진술 줄표 제거 |\n| **파생 압축 자산** (티저·요약 이미지·1장 슬라이드) | 자립형 평문 | Step 2~**5** + **자립성 검사**: 화면·본문 맥락 없이 서야 하므로 정본 어휘·주장 범위·은어를 따로 대조. 렌더 산출물을 만들면 Step 5 지각 QA 필수 |\n\n검증된 원문에서 파생 자산을 만들 때도 재검사한다 — 압축은 주장 범위를 움직일 수 있다\n(예: «지점 앞에서 벼려졌다» → «도메인에서 확인해 온»으로 줄면 담당 범위가 넓어져 읽힌다).\n\n## Step 1 — 실물 캘리브레이션 (표본 없이 톤 단정 금지)\n\n게재 매체가 지정되지 않았으면 **먼저 묻는다**(한 줄). 답을 받을 수 없는 환경이면 일반\n규율로 진행하고 그 사실을 이력에 명기한다.\n\n게재 목표 매체의 **실제 표본을 1편 이상** 확인(WebFetch)하고 세 가지를 기록한다:\n\n1. **문체**: 존댓말 변형(습니다/해요), 도입 형식(질문형/선언형)\n2. **구성**: 소제목 밀도, 마무리 관행(일반화 + 트레이드오프 + 실무 조언 등)\n3. **시각물**: 다이어그램/그래프/표를 어느 밀도로 쓰는가\n\n캘리브레이션 기록은 **산출물 이력**(작업 로그·PR 본문·문서 frontmatter)에 남긴다 — 게재\n본문에는 노출하지 않는다. 표본을 확인할 수 없으면 **무엇을 시도했고 왜 안 됐는지**(호출\n실패·매체 미상 등)를 같은 이력에 명기하고 일반 규율(습니다체·소제목 세분화)로 진행한다 —\n확인 안 된 톤을 확정처럼 쓰지 않는다. **시도 기록 없는 «확인 불가»는 Done When 1조를\n충족하지 않는다.**\n\n## Step 2 — 문체 규율 (번역투 클래스 목록)\n\n아래는 실측으로 검출된 클래스다. **기계 스캔 + 눈 판정**으로 제거한다\n(grep은 후보를 표시할 뿐, 남길지 판정은 문맥으로):\n\n| 클래스 | 검출 힌트 | 수리 |\n|---|---|---|\n| 줄표 이어붙임 「~다 — ~고,」 | `grep \"다 — \\|것 — \\|음 — \"` | 문장 분리. 줄표는 **일을 하는 곳만** 남긴다(열거 매달기·리듬 결속 — 남긴 이유를 적는다) |\n| 용어-머리 «**X** — 설명» | 글머리 기호 뒤 `** — ` | «**X**: 설명» 콜론형 |\n| 콜론 나열투 («관측된 분업은: …») | 서술어 없는 `:` 도입 | 완결 문장으로 («…분업은 ~라는 것입니다») |\n| 조각문 («걸리는 층.») | 서술어 없는 마침 | 서술어 복원 («걸리는 층입니다») |\n| 소유 직역 「~을 갖다/가지다」 | `grep -nE \"을 갖|를 갖|을 가지|를 가지\"` | 존재문으로 (**«이전 상태를 갖지 않는다» → «이전 상태가 없다»**). 영어 `have`의 직역이고, 한국어는 소유보다 존재로 말한다. 소유가 실제 논점인 자리(권한·지분)는 남긴다 |\n| 내부 조어·은어 | 팀 밖에서 안 쓰는 단어 (예: 렌더하다, 초록/빨강을 CI 결과 뜻으로) | 청중 어휘로 평문화. 단, **화면이 어휘를 받치면**(실제 빨간 화면을 가리키는 발화) 유지 가능 — 근거를 적는다 |\n| 레지스터 드리프트 | 습니다↔해요↔평어 혼재 | 표본 기준 단일화 |\n\n클래스의 성격이 갈린다: 앞 다섯 줄(줄표·용어-머리·콜론·조각문·소유 직역)은 **기계 검출\n가능**(grep 후보 + 눈 판정)이고, 뒤 두 줄(내부 조어·레지스터)은 **판정 클래스**다 —\nDone When에서 서로 다른 check-class로 채점된다.\n\n### Step 2-b — 부분 개고 전용: 기존 본문과의 리듬 대조\n\n**문서 전체를 새로 쓰는 경우가 아니라 기존 문서에 문단·문장을 끼워 넣는 경우**, 위 클래스가\n전부 0이어도 **삽입분만 이질적으로 읽힐 수 있다.** 클래스 목록은 «틀린 표현»을 잡지\n«튀는 표현»을 못 잡기 때문이다. 삽입·개고분에 한해 두 가지를 **수치로** 대조한다:\n\n1. **문장 길이 분포** — 본문 평문 문장의 길이 중앙값·상위 10%를 먼저 구하고, 삽입분의 각\n   문장이 상위 10% 안에 드는지 본다. 넘으면 끊는다. (본문에 더 긴 문장이 있어도 근거가\n   못 된다 — 그건 그 문단의 리듬이지 삽입분의 것이 아니다.)\n2. **어휘 반복** — 삽입분 안에서, 그리고 **직전·직후 문장까지 포함해** 같은 어간이 3회\n   이상 연달아 나오는지. 특히 같은 글자가 뜻이 다른 채로 반복되면(«검사를 더 **붙**여도 …\n   지점 쪽에 **붙**습니다») 읽는 눈이 걸린다.\n\n> 실측(2026-08-11, 기술문서 v2.1 작업): 클래스 스캔 잔여 0인 삽입분이 본문 112문장 중\n> 유일한 소유 직역 1건을 들여왔고, 문장 길이 **124자**(본문 중앙값 40자 · 상위 10% 78자),\n> 「내려가」 앞 문장 포함 4회 연속 · 「붙」 한 문장 안 2회였다. 셋 다 기존 클래스 목록으로는\n> 안 잡혔고, **읽는 사람이 «톤이 다르다»로 먼저 알아챘다.** 의도 보존으로 제외하는 항목은 **명명된 사유**(열거\n매달기·리듬 결속·화면 받침)에 한하며, 제외 목록은 Step 5 콜드리드 짝에게 **통독이 끝난\n뒤** 별도 패스로 전달해 대조받는다 — 사전 전달은 첫-읽기 눈을 오염시키고, 자기가 쓴\n사유만으로 무제한 제외하지 않는다.\n\n## Step 3 — 정직 수위 층 분리\n\n정직함에는 두 층이 있고, 독자 문서에는 한 층만 싣는다:\n\n- **싣는다 — 논지를 받치는 정직**: 한계 절, 소표본 명시, 자기 철회 사례, \"측정 중\".\n  이걸 빼면 글의 등뼈가 빠진다.\n- **뺀다 — 내부 감사 어휘**: 검증 원장의 자기감사 디테일(\"실적은 X만 주장한다\",\n  \"도달만·채택 아님\" 같은 규율-말투), 내부 등급/게이트 상태 세부. 내부 기록에는 남기고\n  독자 본문에서는 뺀다.\n\n판단 기준 한 줄: **\"이 문장이 독자의 다음 행동이나 판단을 바꾸는가?\"** — 바꾸면 정보,\n안 바꾸면 자기감사다. **문장 단위로 적용**하고, 한 절의 문장 대부분이 걸리면 절 단위로\n제거를 검토한다. 경계 예시: «실패 3건은 내부 전용 API 의존이라 외부 재현이 안 된다»는\n독자의 재현 판단을 바꾸므로 **정보**다. «실적은 머지된 것만 주장한다»는 저자의 집계 규율\n서술이라 **자기감사**다.\n\n## Step 4 — 수치·주장 게이트 (기존 검증 자산으로 라우팅 — 재발명 금지)\n\n**분모는 기계로 연다**: 본문의 **아라비아 숫자 전수**를 grep으로 추출해 목록을 만들고,\n수치 주장이 아닌 항목(버전 표기·목차 번호·연도 등)을 **사유와 함께 제외**한 뒤, 남은 각\n행에 아래 라벨 중 하나를 단다. 단위 목록으로 좁혀 시작하지 않는다 — 영문 단위(ms·GB)가\n새기 때문이다. 한글 수사(\"세 배\")는 아라비아 전수로도 못 잡으므로 **눈 판정 잔여**로\n명기하고 통독에서 본다. 자기 눈으로 고른 수치만 채점하는 것은 measured가 아니다.\n\n⚠️ **`\\b` 경계 금지** — 유니코드 인식 엔진(ripgrep·GNU grep UTF-8 로케일·Python `re` —\n**`grep -P`는 예외다**: `(*UCP)` 없이는 `\\w`가 ASCII 한정이라 숫자-한글 사이에 경계가\n생긴다. 반드시 `rg` 로 고정)에서 **한글은 word 문자**라 숫자와 한글 사이엔 경계가 생기지\n않는다. `\\b\\d[\\d,]*\\b`류 패턴은 숫자 뒤에 한글 조사·단위가 바로 붙는 표기(예: «7개»)를\n놓친다. **known-pair로 직접 확인**(엔진 고정, 복붙 실행): 이 SKILL.md 자신에 `rg -n\n'\\b\\d[\\d,]*\\b'`와 `rg -n '\\d(?:[\\d,]*\\d)?'`(끝자리 콤마를 삼키지 않게 끝을 숫자로 고정)를\n각각 돌려 델타를 세면, 경계판이 놓치는 숫자가 나온다(측정일 기준 델타 수를 이력에\n기록 — 놓치는 쪽은 대부분 조사·단위가 바로 붙는 주장 수치이고, 날짜·Step 번호처럼 뒤에\n공백·기호가 오는 숫자는 양쪽 다 잡힌다). **경계 없는 추출**로 시작하고, 과다추출된\n비주장 항목은 위 문장대로 사유와 함께 제외한다.\n\n### Step 4-b — 전칭 단정 후보 검출 (오탐 허용 — 후보 표시용, 판정은 사람)\n\n«전부/모두/하나도 없다/전혀/일절/예외 없이» 류 전칭 단정 어휘 + **부정형 전칭**을\n`rg -n '(안|못) ?(했|만들|나오|잡히)|지 않았(다|습니다)'`(엔진 고정, 복붙 실행)로 걸러\n후보로 표시하고, 각 후보의 반례가 정말 없는지 본문·근거를 다시 대조한다. grep은 후보만\n내고 판정은 사람이 한다 — 오탐 다수가 정상이다. **단, 후보를 세지 않거나 판정을\n비워두는 것은 결함이다** — 판정할 사람을 구할 수 없으면 후보 목록을 그대로 남기고 이\n조건을 **미충족으로 명시**하고 발행 판단자에게 넘긴다(자기 판정으로 대체 금지 — Step 5\n격리 규율과 동형).\n\n실측(비공개 원장, 2026-08-14): 같은 개고 세션에서 반례 탐색 없는 전칭 단정을 두 번\n썼고, 한 번은 위 어휘 목록에 없는 **부정형**(\"~을 안 만들었다\")이었다 — grep 어휘만으로\n못 잡는 계열이 실재한다는 뜻이라 부정형 패턴을 함께 넣는다. **반례 탐색 없이 쓴 전칭\n단정은 원문보다 개고본에서 더 잘 나온다** — 다듬는 행위 자체가 근거 재확인 없이 서술을\n넓히기 때문이다. Step 5 재콜드리드가 뒤늦게 잡을 수도 있지만, 앞단에서 후보를 먼저\n좁혀두면 그 라운드의 비용이 준다.\n\n수치·주장에는 **두 가지 라벨**이 있고 서로 다른 상태다 — 섞지 않는다:\n\n- **«발행 직전 재측정 대상»** — 근거는 확인됐으나 **시간이 지나면 값이 변하는** 것\n  (다운로드·별 수·테스트 수). 측정 시점·조건(창)을 병기하고 이 라벨을 단다.\n- **«미확인»** — **근거 실물을 아직 확인하지 못한** 주장. 창을 지어 붙이지 않는다(조작된\n  정밀도). 라벨과 확인 경로(어느 저장소·로그를 보면 닫히는지)를 적고, 발행 전 해소를\n  필수로 남긴다. 미발견은 \"미확인\"이지 \"없음\"이 아니다.\n\n기록에 없는 실적·사례는 1차 출처(저장소·PR·로그)를 직접 조회해 확인하고 나서 싣는다.\n- **출처 역추적이 필요하면** `/phantom-quench` 로, **차트를 그리게 되면** 차트 작성 전에\n  dataviz 스킬을 먼저 로드한다. 프로젝트에 금지·조건 수치 목록(원장)이 있으면 발행 전\n  1패스 대조한다. 이 스킬은 **외부 검증 도구를 재발명하지 않는다**(출처 검증·차트 검증은\n  위 라우팅으로) — 스킬 안의 grep 열거·스캔은 절차의 일부이지 검증기 신설이 아니다.\n\n## Step 5 — 렌디션 + 지각 QA\n\n- **md 정본은 항상** 만든다. 다이어그램은 mermaid(GitHub·주요 뷰어 네이티브 렌더).\n- **HTML/PDF 렌디션은 조건부** — 요청이 명시했거나 게재 채널이 요구할 때만 만든다(판단\n  주체는 요청/채널이지 저자의 재량이 아니다): 자체완결 HTML(외부 의존 없는 인라인 SVG\n  다이어그램, 시스템 한글 폰트 스택, `@page` 인쇄 규칙) → headless Chrome `--print-to-pdf`.\n- **md-only 예외의 범위는 좁다** — 게재 매체가 md 를 렌더하면(위키·GitHub 등) **md-only\n  산출물도 렌더 산출물이다.** N/A 는 게재 매체가 렌더를 하지 않음을 확인한 경우에만 쓴다.\n  **매체가 미상이면**(Step 1 «확인 불가» 경로로 진행한 경우) N/A 자격이 없다 — GitHub\n  렌더를 기본 렌더러로 가정하고 지각 확인을 수행하며, 그 가정 사실을 산출물 이력에\n  남긴다.\n  실측(비공개 원장, 2026-08-14): 렌더된 표의 한 셀에 여러 항목이 뭉쳐 기호-뜻 대응이\n  깨졌는데, 원문엔 항목이 전부 적혀 있어 논리적 누락이 없었고 열 수·이스케이프 같은\n  기계 검사도 통과했다. 배경지식 0 콜드리드를 여러 라운드 돌렸는데도 **렌더된 표를 보는\n  사람만** 그 결함을 알아챘다 — «md-only니까 N/A»로 판단한 것이 오판이었다 — 위키가\n  md를 렌더하는 순간 렌더 산출물이 생긴다.\n- **지각 QA(필수 — 렌더 산출물이 있을 때, md-only라도 게재 매체가 렌더하면 포함)**: 렌더\n  결과를 **전 페이지 눈으로** 확인한다 — 라벨 잘림(한글 받침), 페이지 나눔, 표/그림 겹침,\n  다이어그램 텍스트 가림, **표 셀 안에 여러 항목이 한 줄로 뭉쳐 있는지**(구분자 반복 —\n  렌더된 표에서만 보이고 원문 grep으론 안 잡힌다). 도구 exit 0은 렌더 성공이지 가독성\n  판정이 아니다. 판정 짝은 **독립 2차 지각 패스**(다른 눈이 같은 렌더를 봄)다 — 콜드리드는\n  내용을 읽지 렌더 결함을 보지 않으므로 짝이 될 수 없다.\n- **발행 전 콜드리드 1패스**: 격리된 검토가 처음 읽는 눈으로 통독한다. 저자는 자기 글의\n  전제 결손을 못 본다. **격리의 정의**: 저작 맥락을 상속하지 않는 실행이다. 같은 레포에서\n  띄운 서브에이전트는 프로젝트 지침·메모리를 상속하므로 **완전 블라인드가 아니다** — 저작\n  맥락 차단이 필요한 판정(전제 결손·자기 어휘 검사)은 레포 밖 cwd의 headless 실행 +\n  컨트롤(알려진 결함 1건 동반)로 하고, 통독 수준 검토는 다른 에이전트로도 되지만 **어느\n  격리 수준이었는지 이력에 적는다.** 에이전트 디스패치는 호출 세션의 권한·도구를 따른다\n  (이 스킬의 allowed-tools 밖의 일이다). 강격리도 비저자 짝도 구할 수 없으면 해당 judged\n  조건을 **미충족으로 명시**하고 발행 판단자에게 넘긴다 — 자기 검토로 대체하지 않는다.\n- 🟥 **재콜드리드 — 지적을 반영해 고쳐 썼으면 고친 것을 다시 읽힌다.** 콜드리드 1회는\n  *초안*을 검증할 뿐이고, **발행되는 것은 수리본**이다. 수리는 결함의 주된 출처라서\n  «지적 반영»과 «통과»는 다른 사건이다. 본문이 바뀌었으면 라운드를 하나 더 돈다.\n  **정지 조건은 라운드 수가 아니라 변경이다** — 그 라운드에 **새 지적이 0건이고 본문\n  변경이 0건일 때만** 닫는다(어느 하나만으로는 안 닫힌다). 고쳤으면 아직 안 닫힌 것이다.\n  **미반영 지적이 남으면** 각 건에 명명된 사유 + 발행 판단자 수락 기록을 붙인다 — 없으면\n  미충족으로 명시(Step 5 다른 judged 조건과 동형 라우팅). 라운드마다 «지적 n건 · 반영\n  n건 · 본문 변경 여부 · **Step 4/4-b 스캔을 이 수리본에 재실행했는가(y/n)**»를 이력에\n  적는다 — 수리가 결함의 주된 출처인데 수치·전칭단정 게이트가 초안 기준에 머물면 바로\n  그 자리에서 새 결함이 태어난다.\n  > 실측(2026-08-11): 1차 콜드리드가 초안의 삽입 지점 오류를 잡았고, **그 수리가 새 결함\n  > 3종**(소유 직역 · 문장 길이 124자 · 어휘 반복)을 낳았다. 재콜드리드를 안 돌아 그대로\n  > 발행될 뻔했고, 읽는 사람이 «톤이 다르다»로 먼저 잡았다. 돌려 보니 문체보다 큰 것까지\n  > 나왔다 — 삽입분의 주장이 **반례가 흔한 단정**이었고(«검사를 아무리 늘려도 잡히지\n  > 않는다»), 자리도 닫는 절이 아니라 한계 절이 맞았다. 문장 다듬기 라운드가 **주장 범위와\n  > 배치**를 되돌렸다.\n\n## Done When\n\n| 조건 | check-class |\n|---|---|\n| 대상 매체 실물 표본 확인 기록이 산출물 이력에 존재 — 불가 시 **시도 내용·사유 포함** 명기(시도 기록 없는 «불가»는 불충족) | mandatory-pass |\n| Step 2 **기계 클래스**(줄표·용어-머리·콜론·조각문·소유 직역) 스캔 잔여 0 — 컨트롤(알려진 양성 1건) 동반, 제외는 명명 사유와 함께 목록화 | measured |\n| Step 2 **판정 클래스**(내부 조어·레지스터) 통과 | judged — 짝: 콜드리드 통독(통독 후 제외 목록 대조) |\n| **부분 개고인 경우**(기존 문서에 삽입·수정): Step 2-b 리듬 대조 — 삽입분 각 문장이 본문 길이 상위 10% 이내 ∧ 어간 3회 연속 반복 0. 전문 신규 집필이면 N/A 명기 | measured |\n| 본문 수치 전건(기계 추출 분모 기준, `\\b` 미사용 경계없는 추출, **발행 직전 최종본 기준**)이 라벨(창 병기/재측정 대상/미확인) 동반 + **한글 수사(세 배·두 배 등) 눈 판정 잔여 목록이 이력에 명기됨(0건이면 «0»으로 기록)** | measured |\n| 전칭 단정(부정형 포함) 후보 grep 스캔을 **발행 직전 최종본**에서 실행 — 후보 n건 수치 기록 | measured |\n| 위 후보 n건 각각에 반례 확인 결과(«확인함»/«확인 못 함»)가 붙음 — 미판정 0 | judged — 짝: Step 5 콜드리드(통독 후 후보 목록 대조) |\n| **파생 압축 자산인 경우**(Step 0 세 번째 레지스터): 자립성 검사(정본 어휘·주장 범위·은어 대조) 결과가 이력에 존재 — 해당 없으면 N/A 명기 | judged — 짝: 배경지식 0 콜드리드(원문 비열람) |\n| 렌더 산출물(HTML/PDF/이미지 — 파생 압축 자산 포함)이 존재하거나 **게재 매체가 md를 렌더하는 경우**(위키·GitHub 등) 전 페이지 지각 확인 — 게재 매체가 md를 렌더하지 않음을 확인한 경우만 N/A 명기(사유 기록). **매체 미상이면** GitHub 렌더 가정으로 지각 확인 수행(가정 기록) — N/A 불가. Step 5 미적용 레지스터(낭독 대본)는 N/A 명기 | judged — 짝: **독립 2차 지각 패스**(다른 눈이 같은 렌더를 봄) |\n| 콜드리드가 **변경 없음으로 닫혔다** — 마지막 라운드에 **새 지적이 0건이고 본문 변경이 0건**일 때 닫는다(어느 하나만으로는 안 닫힌다). 지적을 반영해 고쳤으면 그 수리본으로 한 라운드 더. **미반영 지적이 남으면** 각 건에 명명된 사유 + 발행 판단자 수락 기록을 붙인다 — 없으면 미충족으로 명시. 라운드별 «지적 n · 반영 n · 본문 변경 여부» + 격리 수준(강/약) 이력 기록. Step 5 미적용 레지스터(낭독 대본)는 N/A 명기 | judged — 짝: 격리 검토(Step 5 정의) |\n| 정직 수위 분리(Step 3)가 적용됨 | judged — 짝: 발행 승인자 확인 또는 격리 적대 검토. 둘 다 불가하면 **미충족으로 명시 보고**(자기 검토로 대체 금지) |\n\n## 역할 경계 (중복 아님을 명시)\n\n- `hub-persona-auditor` **에이전트** — 완성된 대외 초안의 **페르소나 감사**(검토). 이 스킬은\n  **저작·개고 절차**다. Step 5 콜드리드에서 그 에이전트를 짝으로 쓸 수 있다(라우팅 관계).\n- `harness-doctor --lint` — **하네스 자산**의 언어 패턴(자기마케팅) 검출. 이 스킬은 독자\n  대면 문서가 대상이고 번역투·레지스터·정직 수위까지 다룬다.\n- 플랫폼 내장 문서 기능 — 특정 문체 캘리브레이션·정직 수위 층 분리·지각 QA 파이프라인은\n  내장에 없다(이 스킬이 더하는 것은 거버넌스다).\n\n독립 실행 및 degrade 경로: phantom-quench·dataviz 미설치 → 해당 라우팅을 수동 대조로 ·\nWebFetch 불가 → Step 1 «확인 불가» 경로(시도 기록 의무) · headless Chrome 부재 →\nHTML/PDF 렌디션을 «미생성»으로 명기하고 md 정본만 산출 · **Step 4-b 판정 주체(사람) 부재\n→ 후보 목록을 그대로 두고 해당 Done When 을 미충족으로 명시**(자기 판정 대체 금지) ·\n**독립 2차 지각 패스 부재 → 렌더 스크린샷을 산출물 이력에 첨부하고 해당 Done When 을\n미충족으로 명시**(저자가 같은 렌더를 두 번 보는 것으로 대체 금지 — 생성자=평가자가 된다).\n각 degrade는 산출물 이력에 적는다.\n\n**언어 범위**: 이름 그대로 **한국어 전용**이다. Step 0·1·3·4·5의 구조는 언어 무관이지만\nStep 2 문체 클래스가 전부 한국어 실측이라, 영어 지원은 영어 실측 클래스가 쌓인 뒤 별도\n확장(`en-` 자매 또는 일반화)으로 간다 — 실측 없는 클래스를 미리 짓지 않는다(유지 규칙).\n","tagline":"Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target ve","category":"security","tags":["agent-skill"],"author":"chrono-meta","verified":false,"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"recursive skill source sync","sourceDetail":"chrono-meta/forge-harness","creatorName":"chrono-meta","creatorUrl":"https://github.com/chrono-meta","sourceUrl":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":14,"forks":2,"verified_installs":0,"successful_runs":0,"total_outcomes":0,"rating":0,"review_count":0,"quality_score":31.33},"quality":{"score":58,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"14","tone":"neutral"},{"label":"Freshness","value":"8d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Low GitHub adoption signal","The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description."]},"trust":{"version":"trust-score-v5","score":54,"base_score":62,"outcome_confidence":0,"tier":"risk","label":"Do not auto-install","summary":"Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.","recommendedAction":"Choose a stronger alternative or inspect the source manually before any install attempt.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["54/100 Trust Score v5","62/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":30,"weight":0.13,"status":"fail","detail":"14 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":32,"weight":0.08,"status":"fail","detail":"14 stars, 2 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"8d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"command execution surface, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":48,"weight":0.07,"status":"warn","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"fail","label":"GitHub adoption","detail":"14 GitHub stars"},{"status":"fail","label":"Stars/forks activity","detail":"14 stars, 2 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"8d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"warn","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"pass","label":"OpenAgentSkill usage","detail":"3 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"14 GitHub stars","repoActivity":"14 stars, 2 forks","lastPushed":"8d since push","license":"MIT","repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","install":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","8d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["security","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","trust_score":54,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":62,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"trust_score_v5":{"version":"trust-score-v5","score":54,"base_score":62,"outcome_confidence":0,"tier":"risk","label":"Do not auto-install","summary":"Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.","recommendedAction":"Choose a stronger alternative or inspect the source manually before any install attempt.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["54/100 Trust Score v5","62/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":30,"weight":0.13,"status":"fail","detail":"14 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":32,"weight":0.08,"status":"fail","detail":"14 stars, 2 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"8d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"command execution surface, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":48,"weight":0.07,"status":"warn","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"fail","label":"GitHub adoption","detail":"14 GitHub stars"},{"status":"fail","label":"Stars/forks activity","detail":"14 stars, 2 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"8d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"warn","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"pass","label":"OpenAgentSkill usage","detail":"3 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"14 GitHub stars","repoActivity":"14 stars, 2 forks","lastPushed":"8d since push","license":"MIT","repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","install":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","8d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["security","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","trust_score":54,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":62,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"trust_score_v4":{"version":"trust-score-v4","score":62,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":30,"weight":0.13,"status":"fail","detail":"14 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":32,"weight":0.08,"status":"fail","detail":"14 stars, 2 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"8d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":86,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":64,"weight":0.12,"status":"info","detail":"command execution surface, network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":48,"weight":0.07,"status":"warn","detail":"shell or command execution, filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"fail","label":"GitHub adoption","detail":"14 GitHub stars"},{"status":"fail","label":"Stars/forks activity","detail":"14 stars, 2 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"8d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface, network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"warn","label":"Permission surface","detail":"shell or command execution, filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"pass","label":"OpenAgentSkill usage","detail":"3 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"],"evidence":{"stars":"14 GitHub stars","repoActivity":"14 stars, 2 forks","lastPushed":"8d since push","license":"MIT","repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","install":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","8d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["security","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"outcome_stats":null,"safety":{"score":44,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","44/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Permission surface may require sandboxing"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"blocked":false,"human_review_required":true,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Shell or command execution","44/100 agent safety score"]},"eval":{"version":"openagentskill-skill-eval-v1","status":"failed","score":62,"risk_level":"high","decision":{"recommendation":"do_not_auto_install","reason":"Permission surface: shell or command execution, filesystem or document access","auto_install_allowed":false,"policy":"block","human_review_required":true},"blockers":["Permission surface: shell or command execution, filesystem or document access"],"warnings":["Trust score: Potentially useful, but at least one trust signal needs human inspection.","Audit score: Needs review","Agent safety gate: Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","High-risk permission hints: Shell or command execution","Permission surface may require sandboxing","The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.","The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":84,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate ko-tech-writer before installing it in an agent workflow","security","Document processing workflows; Claude Code teams; builders willing to evaluate younger projects"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add chrono-meta/forge-harness --skill ko-tech-writer"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add chrono-meta/forge-harness --skill ko-tech-writer"]},{"id":"trust_score","label":"Trust score","status":"warn","score":62,"required_for_auto_install":true,"detail":"Potentially useful, but at least one trust signal needs human inspection.","evidence":["Manual review","14 GitHub stars","MIT"]},{"id":"audit_score","label":"Audit score","status":"warn","score":72,"required_for_auto_install":true,"detail":"Needs review","evidence":["Permission surface may require sandboxing"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":44,"required_for_auto_install":true,"detail":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","evidence":["Test manually in an isolated workspace and compare against safer alternatives.","High-risk permission hints: Shell or command execution"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"pass","score":86,"required_for_auto_install":false,"detail":"Metadata includes enough usage and workflow context","evidence":["Strong README/SKILL.md context"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"MIT","evidence":["MIT"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"pass","score":100,"required_for_auto_install":false,"detail":"8d since push","evidence":["8d since push"]},{"id":"permission_surface","label":"Permission surface","status":"fail","score":48,"required_for_auto_install":true,"detail":"shell or command execution, filesystem or document access","evidence":["Shell or command execution: high","Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"info","score":55,"required_for_auto_install":false,"detail":"No close alternatives were found in the current shortlist.","evidence":[]}],"endpoints":{"web":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer/evals","api":"/api/agent/evals?slug=chrono-meta-ko-tech-writer","text":"/api/agent/evals?slug=chrono-meta-ko-tech-writer&format=text"}},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"chrono-meta-ko-tech-writer","name":"ko-tech-writer","description":"Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\".","category":"security","url":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer","repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","github_repo":"chrono-meta/forge-harness"},"suited_tasks":["Document processing workflows","Claude Code teams","builders willing to evaluate younger projects","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Inspect repository metadata","Compare code changes"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add chrono-meta-ko-tech-writer"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ko-tech-writer\" agent skill from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"ko-tech-writer\" as a Claude Code skill from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"ko-tech-writer\" from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/chrono-meta-ko-tech-writer/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/chrono-meta-ko-tech-writer"},"trust":{"score":62,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"14 GitHub stars","repoActivity":"14 stars, 2 forks","lastPushed":"8d since push","license":"MIT","repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","install":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["security","agent-skill"],"known_risks":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Permission surface may require sandboxing","The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.","The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":58,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"8d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","Low GitHub adoption signal","The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","High-risk permission hints: Shell or command execution","Permission surface may require sandboxing","The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.","The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten."],"agent_contract":{"task_input":"Use ko-tech-writer in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 62/100 Manual review","Audit: 72/100 Needs review","Safety: 44/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"chrono-meta-ko-tech-writer (ko-tech-writer)","install_command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"chrono-meta-ko-tech-writer","task":"Use ko-tech-writer in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer","api":"https://www.openagentskill.com/api/agent/skills/chrono-meta-ko-tech-writer","audit":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=chrono-meta-ko-tech-writer&task=Use%20ko-tech-writer%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20ko-tech-writer%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20ko-tech-writer%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/chrono-meta-ko-tech-writer/install","manifest":"https://www.openagentskill.com/api/registry/manifest/chrono-meta-ko-tech-writer"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"chrono-meta-ko-tech-writer","name":"ko-tech-writer","description":"Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\".","category":"security","url":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer","repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","github_repo":"chrono-meta/forge-harness"},"suited_tasks":["Document processing workflows","Claude Code teams","builders willing to evaluate younger projects","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Inspect repository metadata","Compare code changes"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add chrono-meta-ko-tech-writer"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ko-tech-writer\" agent skill from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"ko-tech-writer\" as a Claude Code skill from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"ko-tech-writer\" from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/chrono-meta-ko-tech-writer/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/chrono-meta-ko-tech-writer"},"trust":{"score":62,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"14 GitHub stars","repoActivity":"14 stars, 2 forks","lastPushed":"8d since push","license":"MIT","repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","install":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution, filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["security","agent-skill"],"known_risks":["The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Permission surface may require sandboxing","The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.","The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":58,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"8d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","Low GitHub adoption signal","The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","High-risk permission hints: Shell or command execution","Permission surface may require sandboxing","The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.","The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten."],"agent_contract":{"task_input":"Use ko-tech-writer in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 62/100 Manual review","Audit: 72/100 Needs review","Safety: 44/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"chrono-meta-ko-tech-writer (ko-tech-writer)","install_command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"chrono-meta-ko-tech-writer","task":"Use ko-tech-writer in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer","api":"https://www.openagentskill.com/api/agent/skills/chrono-meta-ko-tech-writer","audit":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=chrono-meta-ko-tech-writer&task=Use%20ko-tech-writer%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20ko-tech-writer%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20ko-tech-writer%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/chrono-meta-ko-tech-writer/install","manifest":"https://www.openagentskill.com/api/registry/manifest/chrono-meta-ko-tech-writer"}},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"document-processing","title":"Document processing"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":14,"starsLabel":"14","forks":2,"license":"MIT","qualityScore":58,"trustScore":62,"auditScore":72},"maintenance":{"status":"fresh","label":"8d since push","daysSincePush":8,"lastPushedAt":"2026-08-29T04:26:11+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Permission surface may require sandboxing","The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.","The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten.","Low GitHub adoption signal"]},"coverageTags":["Coding","GitHub automation","security","agent-skill"]},"audit":{"audit_score":72,"risk_level":"needs_review","risk_label":"Needs review","quality_score":58,"trust_score":62,"maintenance_score":100,"security_score":74,"install_score":92,"warnings":["Permission surface may require sandboxing","The provided SKILL.md excerpt stops in the middle of Step 4, and the promised Step 5 perceptual QA pass plus the full label set for the number/claim gate are not visible. If the repository file is equally truncated, the skill does not match its own description.","The skill permits WebFetch but does not explicitly state that fetched venue samples must be treated as untrusted data, leaving room for prompt injection from adversarial web pages.","The skill's fixtures include a known-positive file that intentionally contains translationese; the workflow does not state that fixture files must be excluded from document scans or never rewritten.","Low GitHub adoption signal","Quality score needs review","Permission surface needs review: shell or command execution, filesystem or document access","GitHub adoption: 14 GitHub stars","Stars/forks activity: 14 stars, 2 forks; issue activity unavailable in current metadata","Permission surface: shell or command execution, filesystem or document access"]},"quality_signals":{"model":"v2","star_score":8.23,"usage_score":0,"review_score":5.1,"metadata_score":3,"freshness_score":15},"platforms":["Claude Code"],"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"stacks":[{"slug":"web-data-pipeline","title":"Web data pipeline","url":"https://www.openagentskill.com/collections/web-data-pipeline"},{"slug":"rag-knowledge-base","title":"RAG knowledge base","url":"https://www.openagentskill.com/collections/rag-knowledge-base"},{"slug":"coding-review-agent","title":"Coding review agent","url":"https://www.openagentskill.com/collections/coding-review-agent"}],"install":"npx skills add chrono-meta/forge-harness --skill ko-tech-writer","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add chrono-meta-ko-tech-writer","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"ko-tech-writer\" agent skill from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"ko-tech-writer\" as a Claude Code skill from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"ko-tech-writer\" from https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Writes or revises Korean technical prose across three registers — reader-facing documents (tech-blog posts, technical docs), spoken scripts, and derived compressed assets (teasers, summaries) — through a fixed pipeline: register detection, real-sample calibration of the target venue, a translationese-removal pass, honesty-level layering (reader information vs internal audit vocabulary), a number/claim gate, and a rendition + perceptual QA pass. Triggers: \"기술문서 써줘\", \"테크블로그 초안 잡아줘\", \"이 문서 번역투 고쳐줘\", \"블로그체로 다듬어줘\", \"이 글 회사 기술블로그에 올릴 수 있게 다듬어줘\". After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"chrono-meta-ko-tech-writer\",\"task\":\"Install ko-tech-writer\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","github_repo":"chrono-meta/forge-harness","version":"1.0.0","license":"MIT","urls":{"web":"https://www.openagentskill.com/skills/chrono-meta-ko-tech-writer","repository":"https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-commons/skills/ko-tech-writer","api":"/api/agent/skills/chrono-meta-ko-tech-writer","install_api":"/api/skills/chrono-meta-ko-tech-writer/install"},"meta":{"created_at":"2026-08-29T04:37:31.942481+00:00","updated_at":"2026-09-01T11:59:28.941454+00:00","agent_friendly":true}}