Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

paper-style

Estrellas30

Forks1

Actualizado15 de abril de 2026 a las 10:29

Load the author's scientific writing style profile, or do a light AI-ism cleanup on a paragraph. Use when drafting, reviewing, or humanizing any paragraph for a scientific manuscript. Triggers - paper style, 저자 문체, style profile, 논문 스타일, humanize, 논문 humanize, AI 흔적 제거, paper humanize.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

s-choung

s-choung/Research-Skills

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Redactores técnicosArtes, diseño, entretenimiento, deportes y medios·SOC 27-3042

SKILL.md

readonly

name	paper-style
description	Load the author's scientific writing style profile, or do a light AI-ism cleanup on a paragraph. Use when drafting, reviewing, or humanizing any paragraph for a scientific manuscript. Triggers - paper style, 저자 문체, style profile, 논문 스타일, humanize, 논문 humanize, AI 흔적 제거, paper humanize.
allowed-tools	Read, Edit, Grep

paper-style

Two modes: (1) load profile for drafters, (2) light humanize for a last-pass AI-ism scrub.

Source: ~/.claude/paper-team/STYLE_PROFILE.md (author-global). Optional per-project override: <cwd>/.claude/paper-team/STYLE_PROFILE.override.md.

Mode 1. Load profile

Called by drafter agents before writing.

Read ~/.claude/paper-team/STYLE_PROFILE.md.
If override exists in cwd, read and merge (override wins on conflict).
Return section 3.1 banned words, section 3.2 approved transitions, section 2 dials, section 12 checklist. Verbatim, no paraphrase.

Mode 2. Light humanize

Called by /paper-humanize. This is a light pass. Do NOT rewrite, do NOT inject voice, do NOT enforce the full STYLE_PROFILE checklist (that is the drafter's job). Only strip the AI-isms below.

Strip list (scientific-safe)

AI vocab: delve into, leverage, intricate, underscores, nuanced, tapestry, realm, in the realm of, it is worth noting, it should be noted, plays a crucial role, stands as a testament, navigating the complexities, comprehensive understanding, shed light on, pave the way.
Em dash overuse (Unicode U+2014): replace with comma, period, or parenthesis. Keep at most one per paragraph.
Rule of three: triple parallel constructions where all three items are near-synonyms. Cut to one.
"As shown in Fig. X" and "as can be seen" as sentence opener: move the figure reference into a parenthetical (Fig. X).
Rhetorical questions and mic-drop paragraph endings.

Hard rules

Never change numbers, citation markers, chemical formulas, or any technical claim.
If a word on the strip list is load-bearing for the claim, leave it and flag.
If more than 30% of the paragraph would need editing, STOP and return ESCALATE.
If the paragraph is already clean, return it verbatim with NO_CHANGES.

Output

## Cleaned text
<paragraph>

## Changes
- <one line per edit>

Más de este repositorio

mismo repositorio

openrouter-cost

s-choung/Research-Skills

OpenRouter API 지출·잔액 조회 + "방금 얼마 썼는지" 델타 측정. macOS keychain 또는 OPENROUTER_API_KEY로 계정별 lifetime/monthly/weekly/daily usage와 남은 크레딧을 표로 보여주고, run 전후 snapshot/diff로 정확한 증분 비용을 낸다. 키 값은 절대 출력하지 않는다. Triggers - openrouter 비용, openrouter 지출, 크레딧 확인, 잔액 확인, 얼마 썼어, 방금 얼마 썼어, api 비용 확인, spend check, openrouter usage, cost monitor, 이번에 얼마.

2026-07-0330

hpc-monitor

s-choung/Research-Skills

Use when the user wants a one-shot read-only status view of their compute — local machine + SLURM GPU cluster + a scheduler-less CPU server + Matlantis (papermill MD jobs) — as tqdm-style bars. Pure bash + ssh, no LLM/API. Triggers - hpcmon, HPC 모니터, GPU 현황, 큐 상황, squeue, 서버 현황, 잡 현황, matlantis 잡, MD 잡 확인, "얼마나 busy".

2026-07-0230

blender-atom-render

s-choung/Research-Skills

Render atomic structures and individual atom spheres using Blender's io_mesh_atomic addon. Two modes - (1) full-structure auto-frame rendering with multi-angle support, (2) single-atom sphere rendering for legends. Triggers - /blender-atom-render, "atom render", "원자 렌더링", "atom legend", "레전드 만들어", "blender로 렌더", "구 렌더링", "structure render blender"

2026-06-2430

ccel-slide-skill

s-choung/Research-Skills

CCEL 연구과제 발표자료 스타일로 슬라이드 덱을 생성. 어떤 주제/기존 PPT든 받아서 네이비-골드-오렌지 + 나눔스퀘어 + 탭칩 패널 스타일의 HTML과 PPTX를 동일하게 만들고 fade 애니메이션을 양쪽에 똑같이 주입. Triggers - /ccel_slide_skill, ccel 슬라이드, ccel 스타일, CCEL slide, 과제 스타일 슬라이드, 과제 발표자료 ppt, 그 네이비골드 과제 스타일.

2026-06-1030

design2html

s-choung/Research-Skills

Design spec MD 파일을 읽어 해당 디자인 시스템의 토큰·컴포넌트·레이아웃을 충실히 반영한 single-file HTML 쇼케이스 페이지를 생성한다. Triggers: /design2html, 디자인 HTML 만들어, design to html, 디자인 스펙 페이지, showcase page, design spec to webpage

2026-05-1630

humanizer-eng

s-choung/Research-Skills

Revise AI-generated English text so it reads like a specific person wrote it. Use this skill when the user asks to "humanize", "make natural", "remove AI feel", "rewrite like a person wrote it", fix "AI-sounding" text, or pass AI detection on English prose. Also trigger when the user pastes English text and asks for a more natural or human tone. Do NOT use for summarization, translation, creative writing from scratch, or Korean text (use humanizer_kor for Korean).

2026-05-1630

name	paper-style
description	Load the author's scientific writing style profile, or do a light AI-ism cleanup on a paragraph. Use when drafting, reviewing, or humanizing any paragraph for a scientific manuscript. Triggers - paper style, 저자 문체, style profile, 논문 스타일, humanize, 논문 humanize, AI 흔적 제거, paper humanize.
allowed-tools	Read, Edit, Grep

paper-style

Two modes: (1) load profile for drafters, (2) light humanize for a last-pass AI-ism scrub.

Source: ~/.claude/paper-team/STYLE_PROFILE.md (author-global). Optional per-project override: <cwd>/.claude/paper-team/STYLE_PROFILE.override.md.

Mode 1. Load profile

Called by drafter agents before writing.

Read ~/.claude/paper-team/STYLE_PROFILE.md.
If override exists in cwd, read and merge (override wins on conflict).
Return section 3.1 banned words, section 3.2 approved transitions, section 2 dials, section 12 checklist. Verbatim, no paraphrase.

Mode 2. Light humanize

Called by /paper-humanize. This is a light pass. Do NOT rewrite, do NOT inject voice, do NOT enforce the full STYLE_PROFILE checklist (that is the drafter's job). Only strip the AI-isms below.

Strip list (scientific-safe)

AI vocab: delve into, leverage, intricate, underscores, nuanced, tapestry, realm, in the realm of, it is worth noting, it should be noted, plays a crucial role, stands as a testament, navigating the complexities, comprehensive understanding, shed light on, pave the way.
Em dash overuse (Unicode U+2014): replace with comma, period, or parenthesis. Keep at most one per paragraph.
Rule of three: triple parallel constructions where all three items are near-synonyms. Cut to one.
"As shown in Fig. X" and "as can be seen" as sentence opener: move the figure reference into a parenthetical (Fig. X).
Rhetorical questions and mic-drop paragraph endings.

Hard rules

Never change numbers, citation markers, chemical formulas, or any technical claim.
If a word on the strip list is load-bearing for the claim, leave it and flag.
If more than 30% of the paragraph would need editing, STOP and return ESCALATE.
If the paragraph is already clean, return it verbatim with NO_CHANGES.

Output

## Cleaned text
<paragraph>

## Changes
- <one line per edit>