Generate a treasure-hunt style reading guide for an academic paper โ a typeset PDF of 20 quest questions that pulls the reader through the paper. Use when the user has a paper PDF and wants a reading guide, study guide, reading quest, questions to work through while reading, or "help me actually read this paper" โ English or Korean output.
Write and post a comprehensive laboratory notebook entry to Notion, summarizing all work from the current Claude Code session. Use this skill on '/send-note' or when the user asks to create a lab note, post session notes, write up today's work, document the session in Notion, save to lab notebook, or send notes. Even casual requests like 'send note', 'lab note', 'post to notion', 'write up what we did', or 'log this session' should trigger this skill.
Run a multi-perspective review panel on a manuscript draft to help authors improve it for high-impact publication. Simulates 13 specialist reviewers who each review the paper, discuss disagreements, and produce a synthesized improvement roadmap. Agents search PubMed, bioRxiv, and the web for references. MANDATORY TRIGGERS: manuscript review, paper review, review my paper, review this manuscript, review panel, improve my paper, pre-submission review, mock peer review, reviewer feedback, review draft, multi-agent review, help me improve this paper, feedback on my manuscript, strengthen my paper. Use when the user uploads a manuscript (PDF, DOCX, or text) and asks for review, feedback, or improvement suggestions โ even casually like "what do you think of this paper" or "can you review this draft". Also trigger for anticipating reviewer comments or pre-submission checks.
Generate a podcast-style in-depth scientific interview that introduces an academic paper. Uses multi-agent analysis (field expert, methods specialist, context historian, critical reviewer, accessibility translator, impact assessor) to prepare rich source material, then an editor agent curates the narrative, and a writer agent composes the final interview between a professional science interviewer and the paper's author. The user drops a PDF of the paper; all supplementary context is gathered via web search and PubMed/bioRxiv. MANDATORY TRIGGERS: "paper interview", "podcast interview for paper", "introduce this paper", "generate interview for this paper", "paper podcast", "deep dive interview", "interview about this paper", "๋ ผ๋ฌธ ์ธํฐ๋ทฐ", "๋ ผ๋ฌธ ์๊ฐ ์ธํฐ๋ทฐ", "paper introduction interview". Also trigger when the user uploads a PDF and asks for a podcast, interview, deep dive, or accessible introduction of a scientific paper.
IRIS R&D ์ ๋ฌดํฌํธ ์ด์์คํดํธ. ํ๊ตญ ์ ๋ถ R&D ๊ณผ์ ๊ด๋ฆฌ ์์คํ (IRIS, iris.go.kr)์ R&D ์ ๋ฌดํฌํธ์ ์ ๊ทน์ ์ผ๋ก ํ์ฉํ์ฌ ์ฌ์ฉ์์ R&D ์ ๋ฌด๋ฅผ ๋ํํ๋ค. ๋จ์ํ ํ์ด์ง๋ก ์๋ดํ๋ ๊ฒ์ด ์๋๋ผ, ์ ๋ณด๋ฅผ ์ง์ ์ฐพ์์ ์ ๋ฆฌํด์ฃผ๊ณ , ์์์ ์ฑ์ ์ ์ถํ๊ณ , ๊ณผ์ ํํฉ์ ๋ถ์ํด์ฃผ๋ ๋ฅ๋์ ์ธ ์ด์์คํดํธ์ด๋ค. ์ฐ๊ตฌ์ฑ ์์(PI)๊ฐ ๊ณผ์ ์ ์, ํ์ฝ์ ์ฒญ, ํ์ฝ๋ณ๊ฒฝ, ์ฐ๊ตฌ๋น ๊ด๋ฆฌ, ์ฑ๊ณผ๋ฑ๋ก, ๋ณด๊ณ ์ ์ ์ถ, ์ ์ฐ, ๊ธฐ์ ๋ฃ, ๋ฉ๋ถ ๋ฑ์ ์ ๋ฌด๋ฅผ ์ํํ ๋ IRIS ํฌํธ์ ๋ณต์กํ ๋ฉ๋ด์ Nexacro UI๋ฅผ ๋์ ์กฐ์ํ์ฌ ์ ๋ฌด๋ฅผ ์ฒ๋ฆฌํ๋ค. ๋ชจ๋ ์ฃผ์ ๋์์ ๊ฐ์ฌ ์ถ์ (audit trail) HTML ํ์ผ๋ก ๊ธฐ๋ก๋์ด ์ฌ์ฉ์์๊ฒ ์ ๊ณต๋๋ค. MANDATORY TRIGGERS: IRIS, iris.go.kr, R&D ์ ๋ฌดํฌํธ, ๊ณผ์ ์ ์, ํ์ฝ์ ์ฒญ, ํ์ฝ๋ณ๊ฒฝ, ์ฐ๊ตฌ๋น, ์ฑ๊ณผ๋ฑ๋ก, ๋ณด๊ณ ์ ์ ์ถ, ์ ์ฐ, ๊ธฐ์ ๋ฃ, ๋ฉ๋ถ, ์ฐ๊ตฌ๊ฐ๋ฐ๊ณํ์, ์ฐ๊ตฌ์์ค์ฅ๋น, ์์์กฐ์ฌ, ์ฌ์ ๊ณต๊ณ , ํ๊ฐ์์ํ, ์ฆ๋ช ์ ๋ฐ๊ธ, ๊ตญ์ธ์ํ์ ๋ณด, ์ ์์๋ฆผ, ๋ง์ดR&D, ์ ์ฌ์ฒ๋ถ, ์ด์๊ธ, ๋ถ๋ด๊ธ. ์ฌ์ฉ์๊ฐ 'IRIS์์ ํ์ฝ๋ณ๊ฒฝ ํ๊ณ ์ถ์ด', '์ฐ๊ตฌ๋น ์ง๊ธํํฉ ํ์ธ', '๋ณด๊ณ ์ ์ ์ถํด์ผ ํด', '๊ณผ์ ์ ์ํ๋ ค๊ณ ', '์ ์ฐ๊ฒฐ๊ณผ ์กฐํ', '์ฑ๊ณผ ๋ฑ๋ก', '๊ธฐ์ ๋ฃ ๋ฉ๋ถ', '์ฆ๋ช ์ ๋ฐ๊ธ', '๋ด ๊ณผ์ ๋ชฉ๋ก ๋ณด์ฌ์ค', '์ฐธ์ฌ๊ณผ์ ํํฉ ์ ๋ฆฌํด์ค' ๋ฑ์ ์์ฒญ์ ํ ๋ ์ด ์คํฌ์ ์ฌ์ฉํ๋ค.
mySNU ํฌํธ์์ ์ธ๋ถ๊ฐ์ ์ ๊ณ ๋ฅผ ์๋์ผ๋ก ์์ฑยท์ ์ถํ๋ ์คํฌ. ์ฌ์ฉ์๊ฐ ์ด๋ฉ์ผ, ๊ณต๋ฌธ, ๋๋ ๋ํ ๋ด์ฉ์ ๋ฐํ์ผ๋ก ์ธ๋ถ๊ฐ์/ํ๊ฐ/์๋ฌธ/๋ฐํ ๋ฑ์ ์ธ๋ถํ๋ ์ ๊ณ ๋ฅผ ์์ฒญํ๋ฉด, ํ์ํ ์ ๋ณด๋ฅผ ์ถ์ถํ๊ณ mySNU ์ธ๋ถ๊ฐ์ ์ ๊ณ ์์์ Chrome ๋ธ๋ผ์ฐ์ ๋ฅผ ํตํด ์๋์ผ๋ก ์ ๋ ฅํ๋ค. ์ ์ฒญ ์ ์ถ์ ๋ฐ๋์ ์ฌ์ฉ์ ํ์ธ ํ ์งํํ๋ค. MANDATORY TRIGGERS: ์ธ๋ถ๊ฐ์, ์ธ๋ถ๊ฐ์ ์ ๊ณ , ์ธ๋ถํ๋ ์ ๊ณ , ๊ฐ์์ ๊ณ , ์๋ฌธ์ ๊ณ , ํ๊ฐ์ ๊ณ , ์ฌ์ฌ์ ๊ณ , mySNU ์ธ๋ถ๊ฐ์, ์ธ๋ถ๊ฐ์๋ฑ ์ ๊ณ , external lecture report, ์ธ๋ถ๊ฐ์์ ๊ณ ์ ์์ฑ. ์ฌ์ฉ์๊ฐ "์ด ์ด๋ฉ์ผ ๋ณด๊ณ ์ธ๋ถ๊ฐ์ ์ ๊ณ ํด์ค", "ํ๊ฐ ์ฐธ์ฌํ๋๋ฐ ์ ๊ณ ์ข ํด์ค", "์๋ฌธ ์ ๊ณ ํด์ผ ํด", "์ธ๋ถ๊ฐ์ ๋ฑ๋ก" ๋ฑ์ ์์ฒญ์ ํ ๋ ์ด ์คํฌ์ ์ฌ์ฉํ๋ค. ์ด๋ฉ์ผ ๋ด์ฉ์ด๋ ๊ณต๋ฌธ์ ์ฐธ์กฐํ๋ผ๋ ๋งฅ๋ฝ์ด ์์ผ๋ฉด ๋๋์ฑ ์ด ์คํฌ์ด ์ ํฉํ๋ค.
Scan Gmail inbox for unanswered emails, research context from Sent mail and thread history, then compose and save draft replies in the user's voice and style. Drafts are never sent โ only saved for review. Use this skill whenever the user wants to catch up on email, draft replies, auto-reply to unanswered messages, prepare responses, reach inbox zero, or handle email backlog. Trigger on phrases like "draft replies", "respond to my emails", "catch up on mail", "write replies for me", or any variation of wanting Gmail draft responses prepared automatically.
์์ธ๋ํ๊ต SRnD(์ฐ๊ตฌํ์ ํตํฉ๊ด๋ฆฌ์์คํ , srnd.snu.ac.kr) ๋ธ๋ผ์ฐ์ ์๋ํ ์คํฌ. Nexacro Platform 14 ๊ธฐ๋ฐ UI๋ฅผ javascript_tool๋ก ์ ์ดํ์ฌ ๊ณผ์ ์กฐํ, ์ง์ถ์ ์ฒญ, ์ฐธ์ฌ์ฐ๊ตฌ์ ๊ด๋ฆฌ, ์นด๋์ฒญ๊ตฌ, ์ฐ๊ตฌ์ ์ , ๊ตฌ๋งค, ์ถ์ฅ์ ์ฒญ ๋ฑ ์ฐ๊ตฌํ์ ์์ ์ ์ํํ๋ค. TRIGGER: ์ฌ์ฉ์๊ฐ srnd.snu.ac.kr์ ์๊ฑฐ๋, SRnD/์ฐ๊ตฌํ์ ์ ์ธ๊ธํ๊ฑฐ๋, ๊ณผ์ ์กฐํยท์ง์ถ์ ์ฒญยท์ฐธ์ฌ์ฐ๊ตฌ์ยท์ฐ๊ตฌ๋นยท์นด๋์ฒญ๊ตฌยท์ฐ๊ตฌ์ ์ ยท๊ตฌ๋งคยท์ถ์ฅ์ ์ฒญ ๋ฑ ์์ธ๋ ์ฐ๊ตฌํ์ ์ ๋ฌด๋ฅผ ์์ฒญํ ๋. DO NOT TRIGGER: ๋ค๋ฅธ ๋ํ ์์คํ ์ด๋ ์ผ๋ฐ ์น์ฑ์ ๋ค๋ฃฐ ๋.