← all publishers

iamseungpil

@iamseungpil source repo

31 published skills

  1. Humanize Writing · iamseungpil bundle
    Use when the user wants text to sound more human, says writing sounds "too AI" or "too ChatGPT," asks to humanize or rewrite a draft to feel natural, or shares content wanting it to feel authentic and less robotic. Also applies to LinkedIn posts, blog drafts, or emails where the user wants a more genuine voice.
    0
    installs
  2. Gget · iamseungpil bundle
    gget
    0
    installs
  3. Uspto Database · iamseungpil bundle
    Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
    0
    installs
  4. Alphafold Database · iamseungpil bundle
    Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
    0
    installs
  5. Iterative Code Review 2 · iamseungpil
    Iteratively improve code quality through analyze-implement-review-test loop. Use when writing new features, fixing bugs, refactoring, or preparing for production deployment. Combines principles from task planning, modular architecture, code review, and debugging. Loops until Critical/Warning issues are resolved and tests pass (max 5 iterations).
    0
    installs
  6. Academic Latex Pipeline 2 · iamseungpil bundle
    Complete workflow for converting Korean/English academic survey Markdown into publication-quality LaTeX PDFs. Handles Obsidian artifact cleanup (wikilinks, mermaid), XeLaTeX compilation with Korean font support (ucharclasses + Noto Sans CJK KR), BibTeX citations, TikZ figure generation, tcolorbox example boxes, and iterative format review. Use this skill whenever the user wants to build a PDF from an academic markdown file, compile a LaTeX survey paper, or fix formatting issues in an existing academic PDF. MANDATORY TRIGGERS: LaTeX survey, academic PDF, 서베이 PDF, 논문 PDF 빌드, xelatex, build_latex.py, Korean academic paper, survey compilation
    0
    installs
  7. Hwpx · iamseungpil bundle
    Comprehensive HWPX (Korean Hancom Office) document creation, editing, and analysis. When Claude needs to work with Korean word processor documents (.hwpx files) for: (1) Reading and extracting content, (2) Creating new documents, (3) Modifying or editing content, (4) Extracting tables to CSV, (5) Modifying tables or table cells, or any other HWPX document tasks. MANDATORY TRIGGERS: hwpx, hwp, 한글, 한컴, Hancom, Korean document
    0
    installs
  8. Autoresearch · iamseungpil bundle
    Autonomous iteration loop: modify, verify, keep/discard against any metric
    0
    installs
  9. Paper Banana · iamseungpil
    논문 텍스트에서 publication-ready 학술 일러스트레이션(methodology diagram, statistical plot, system architecture)을 자동 생성하는 스킬. Google의 PaperBanana 멀티 에이전트 파이프라인(Retriever→Planner→Stylist→Visualizer→Critic)을 사용하여 논문 figure를 자동으로 생성, 수정, 평가한다. 이 스킬은 다음 상황에서 반드시 사용한다: - 논문 figure/diagram 생성 요청 ("논문 그림 그려줘", "methodology diagram", "figure 생성", "architecture diagram") - 통계 차트/plot 생성 ("결과 차트", "bar chart", "plot 그려줘", "statistical plot") - 학술 일러스트레이션 관련 ("시스템 구조도", "pipeline 그림", "모델 아키텍처 시각화") - PaperBanana 직접 호출 ("paperbanana", "paper banana") - 논문 figure 품질 평가 ("figure 평가", "diagram 비교", "그림 품질 확인") - 논문 작성 중 시각 자료 필요 시 ("이 방법론을 그림으로", "이 결과를 차트로") MANDATORY TRIGGERS: paperbanana, paper banana, 논문 figure, 논문 그림, methodology diagram, architecture diagram, statistical plot, 학술 일러스트레이션, figure 생성, 차트 생성, 시스템 구조도, pipeline diagram, 모델 아키텍처 시각화, figure 평가, diagram 비교
    0
    installs
  10. Paper Digest · iamseungpil
    Generate shareable paper summaries for Discord/Slack/Twitter. Use when user provides arxiv paper(s) and wants a digestible summary to share. Triggers on phrases like "논문 요약", "paper summary", "share this paper", "디스코드에 공유", "summarize for sharing". Produces insight-centered single-paragraph summaries that explain WHY research matters, not just WHAT it does.
    0
    installs
  11. Survey Paper · iamseungpil
    arxiv 논문을 체계적으로 분석하여 Obsidian 서베이 노트를 생성한다. arxiv 페이지/ID를 입력받아 (1) Paper Digest 스타일 핵심 요약, (2) Iterative Writing 원칙 기반 세부 정리, (3) 플로우 다이어그램 포함 Obsidian 페이지를 생성한다. TRIGGERS: "논문 서베이", "paper survey", "arxiv 정리", "논문 노트", "서베이 페이지", "survey note"
    0
    installs
  12. Update Study · iamseungpil bundle
    This skill should be used when the user asks to "update study", "analyze new experiments", "update experiment document", or "refresh study notes". Produces academic-paper-quality experiment reports with matplotlib plots, executive summary with comparison tables, implementation structure, experimental results with figure interpretation, proposed improvements with code examples, hypotheses, limitations, and LaTeX PDF export with figures. Features incremental detection (only analyze NEW experiments), data extraction to DataFrame, automated plot generation, iterative writing improvement loop with quality criteria, zero-hallucination verification, and LaTeX PDF export. Usage - `/update-study logs/experiment.log study.md` or `/update-study "logs/exp1.log logs/exp2.log" results/ablation_study.md`
    0
    installs
  13. Research Debug · iamseungpil bundle
    Research-driven debugging workflow that combines web research for similar cases, deep code analysis with task-planner-analyzer, and iterative fixes with modular-code-architect and code-reviewer. Use when encountering training collapse, gibberish generation, or architecture-level bugs where the problem may be documented in research literature. Parallel execution of research and fixes for efficiency.
    0
    installs
  14. Deepswe Analyze · iamseungpil bundle
    Turn a finished harbor run (DeepSWE, SWE-bench Pro, any scaffold) into the weekly failure-reasoning analysis — Sonnet verdicts on every failed trial, prior-work taxonomy labels, success verdicts, win/loss contrast pairs, an Opus agreement check, and the weekly viewer build. Use when a week's job folders are complete and the user wants "이번 주차 분석" or the site updated.
    0
    installs
  15. Humanize Korean · iamseungpil bundle
    AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 40+ AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스러운 한국어로 재작성한다. 트리거 — "AI 티 없애줘", "AI 같은 글 자연스럽게", "GPT/ChatGPT 문체", "AI 번역투 고쳐", "사람이 쓴 것처럼 윤문", "AI 윤문", "ChatGPT 티 제거", "한글 AI 탐지·윤문", "AI 글 사람처럼", "번역투 제거", "영어 인용 많은 글 윤문", "AI 글 티 안 나게", "휴머나이저", "humanize Korean", "AI detector bypass 한글". 후속 작업 — "특정 카테고리만 다시", "윤문 강도 조정", "장르 바꿔서", "이 문단만", "2차 윤문" 도 모두 이 스킬. 단순 맞춤법·오탈자 교정은 직접 처리, 번역은 번역 스킬, 내용 추가·삭제를 동반한 재작성은 별도 집필 스킬.
    0
    installs
  16. Stacked Research · iamseungpil bundle
    실험 결과가 쌓이게 만드는 연구 규율. 실험을 설계·발사·판정할 때, 이전 결과를 참조할 때, 헌법·사전등록·판정문을 다룰 때, autoresearch 루프를 돌릴 때, 그리고 정본 코드를 바꾸며 승인을 받을 때 사용. 같은 결론을 다시 사는 것, 무효 레버(선언은 있고 배선은 없는 것), 이미 되던 것을 조용히 깨뜨리는 것, 목표선 실험이 소음에 밀리는 것, 일회성 스크립트·도구 증식, 문서가 진전을 대체하는 것을 막는다. Triggers on "실험 설계", "사전등록", "발사", "판정", "autoresearch", "헌법", "이전 결과", "다시 재", "루프 점검", "승인", "회귀", "폴더 정리".
    0
    installs
  17. Interactive Report · iamseungpil
    Interactive Report — Experiment Results Visualization
    0
    installs
  18. Weekly Report Writer · iamseungpil
    Automatically generate academic-style weekly research reports by analyzing Git changes in the current project directory with iterative quality improvement
    0
    installs
  19. Iterative Code Review · iamseungpil
    Iteratively improve code quality by using task-planner-analyzer for planning, modular-code-architect agent to fix issues, code-reviewer agent to validate quality, and running tests to verify correctness. Use when implementing new features, after bug fixes, during refactoring, or when preparing code for production deployment. Loops until code-reviewer reports no critical issues AND tests pass.
    0
    installs
  20. Latex Project Manager · iamseungpil bundle
    Structure and manage LaTeX projects with section-based folder organization and Git integration. Two commands: (1) `structure` splits a monolithic .tex file into per-section files with main.tex orchestrator, figures/ directory, and BibTeX refs.bib, (2) `push` initializes git and pushes to GitHub or Overleaf with token-based auth. Supports multi-project layout where main.tex switches between projects via a single command variable. MANDATORY TRIGGERS: latex structure, tex organize, section split, latex git push, overleaf push, latex 정리, tex 구조화, 섹션 분리
    0
    installs
  21. Paper Section Rewrite · iamseungpil bundle
    학술 논문·연구계획서 한 섹션을 LLM이 자율적으로 4-Level critic loop로 분석·개선하는 윤문 스킬. 설계 순서를 강제 — Level 1 내용 → Level 2 문단 간 구성 → Level 3 문단 내 구성 → Level 4 문장. Level 1·2·3는 CONVERGED skip 금지. 두괄식 + 의도(질문)→방법→결과→해석. paper-digest의 insight-first(단순 나열 X), iterative-academic-writing의 논리적 비약 0, humanize의 자연스러움(em-dash 0, 번역투 0, 계사 대용 관용구 "~에 해당한다/~로 기능한다/~에 위치한다/자리매김" 0, 동족어·중복어 stacking 0, "~하고자 한다" 비율 ≤ 30%, register 일관성, 개념어 과반복 회전, 종결어미 다양성). 한 문장 한 역할(One Sentence One Role) + 단문 비율 ≥ 60% 강제. ML 비전공자 가독성 게이트(약어 풀어쓰기 / 수식 전 자연어 / jargon ≤ 3 / 서술형 풀어쓰기 — 명사형 종결 금지). 섹션 자기 완결성. 본문+부록 전체 수식·notation 감사 (중복/혼용/오용/Orphan 검출). KO/EN + 연구계획서 장르 지원. MANDATORY TRIGGERS - 섹션 다시 쓰기, 섹션 윤문, 풀어쓰기, 두괄식, paper section rewrite, 연구계획서 윤문, 자연스럽게, AI 티 빼줘, ML-beginner, notation audit, em-dash 0, 단문, 단문 비율, 한 문장 한 역할, insight-first, 자기 완결, 논리적 비약, 서술형 풀어쓰기, 명사형 종결 금지, 계사 대용, 해당한다 위치한다 기능한다, 동족어 stacking, 하고자 한다 줄이기, register 일관성, 개념어 과반복, 종결어미 다양성
    0
    installs
  22. Codex Iterative Solver · iamseungpil
    Collaborate with Codex CLI to iteratively analyze, plan, and solve complex coding problems through multiple rounds of expert feedback. Use when analyzing complex codebases with multiple approaches, validating implementation plans, or solving problems that benefit from expert validation.
    0
    installs
  23. Academic Latex Pipeline · iamseungpil bundle
    Complete workflow for converting Korean/English academic survey Markdown into publication-quality LaTeX PDFs. Handles Obsidian artifact cleanup (wikilinks, mermaid), XeLaTeX compilation with Korean font support (ucharclasses + Noto Sans CJK KR), BibTeX citations, TikZ figure generation, tcolorbox example boxes, and iterative format review. Supports section-based folder structure with main.tex orchestrator and BibTeX refs.bib management. Use this skill whenever the user wants to build a PDF from an academic markdown file, compile a LaTeX survey paper, or fix formatting issues in an existing academic PDF. MANDATORY TRIGGERS: LaTeX survey, academic PDF, 서베이 PDF, 논문 PDF 빌드, xelatex, build_latex.py, Korean academic paper, survey compilation
    0
    installs
  24. Academic Writing Trainer · iamseungpil bundle
    처음부터 단계적으로 학술 글을 작성하며 글쓰기 원칙을 체화하는 트레이너 스킬. 단문(5문단 디폴트) / 장문(섹션 Q&A) 두 모드. 의도→내용→구조→문장 4단계 점층 결정. 한 문단씩 통과 점수까지 반복 후 통합. 한 문장 한 역할(One Sentence One Role) 강제 — Stage 4에서 두 카테고리 짊어진 문장은 즉시 ✗ 판정 후 분할. KO 50자 / EN 20 words 단문 디폴트. 노션 4축 평가와 R1~R5 합평 패턴으로 채점. 친절한 Coach 페르소나(존댓말, 칭찬+개선+다음행동 3단). 같은 원칙을 5문단에 걸쳐 반복 호출해 체화. KO/EN 지원. critic은 Claude 본인이 같은 대화 안에서 수행. MANDATORY TRIGGERS - 글쓰기 연습, 연구 제안서 작성, 학술 글 트레이너, academic writing trainer, 글쓰기 합평, 한 문단씩 작성, 글쓰기 실습, 단문, 한 문장 한 역할
    0
    installs
  25. Code Architecture Writer · iamseungpil bundle
    Analyze codebases and generate architecture/code explanation documents. Two modes - (1) `/code-architecture-writer diff <base_branch> [output.md]` for change explanation, (2) `/code-architecture-writer flow <entrypoint.py> [output.md]` for execution flow. Explains "why" each file/function exists, not just "what" it does.
    0
    installs
  26. Paper Readability Review · iamseungpil bundle
    논문 PDF에 가독성 피드백을 내용·구조·문장 세 층위로 진단해, 본문 위에 색상 하이라이트 + 마진 카드(진단 + 대안 방향) + 우선순위 로드맵이 있는 리뷰 PDF를 생성한다. critic-loop으로 자체 점검·반복 개선한다. 사용자가 자기 논문이나 학생/동료의 원고를 첨부하고 "가독성 봐줘", "리뷰 PDF 만들어줘", "피드백 달아줘", "박스 코멘트로 정리해줘", "구조 점검해줘", "문장 다듬을 곳 짚어줘" 같은 요청을 할 때 사용한다. MANDATORY TRIGGERS - 가독성 리뷰, 논문 피드백, readability review, 박스 코멘트, 마진 코멘트, annotated review, paper feedback, 진단 PDF, 코멘트 PDF, paper critique, 원고 점검, 글 다듬기, 구조·문장·내용 피드백
    0
    installs
  27. Academic Slides Iterative · iamseungpil bundle
    Build academic Beamer slide decks through a four-phase iterative loop: (0) gather grounded source material, (1) insight-first prose outline with self-critic, (2) LaTeX render + visual verification, (3) fact-drift re-audit against live code. Every slide carries exactly one concept as a flowchart / code block / table / I-O example — never a prose bullet list. The deck itself is lean (keywords + figures); a companion talking-points markdown carries the depth. Leads with a TL;DR slide framed as "since <baseline>: [added] / [worked] / [missing]". Seeds vs agent-discovered examples are always distinguished. Matches Metropolis Beamer style, no emojis, minimum prose, flowcharts / verbatim boxes / I-O structure preferred over bullet lists. Paper-digest-style principle: explain WHY it matters at an abstract level, not WHAT each file/line does — but numbers and example payloads must be verbatim. MANDATORY TRIGGERS: academic slides, iterative slides, research talk deck, Beamer presentation, one concept per slide, impleme
    0
    installs
  28. Iterative Academic Writing · iamseungpil
    Write academic documents with iterative self-evaluation, fact verification, naturalness check, and refinement. Use when creating research papers, SoPs, abstracts, weekly reports, or any scholarly writing. Applies 19 principles (14 original + 5 naturalness) including fact-based writing with hallucination detection and AI-style sentence filtering. Loops through FactBase→Draft→Evaluate→Plan→Rewrite until Critical issues and hallucinations reach zero (max 5 iterations). Triggers on requests like "write my SoP", "help with paper", "주간 보고서 작성", "논문 작성 도와줘".
    0
    installs
  29. Understand · iamseungpil bundle
    Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships
    0
    installs
  30. Research Survey Visualizer · iamseungpil bundle
    Survey research publications and create intuitive interactive visualizations inline in chat. Use when users ask to (1) survey/analyze a researcher's publications, (2) compare multiple research methods/papers, (3) explain research architectures visually, (4) create visual summaries of academic papers. Triggers on phrases like "연구 정리", "논문 서베이", "research survey", "compare papers", "visualize research", "아티팩트로 만들어줘", "이해하기 쉽게 정리", "인터랙티브하게 설명", "논문 설명". Produces inline Visualizer widgets (SVG diagrams + HTML interactive simulations) interleaved with text explanations following a Why→What→How narrative structure. Always use this skill when asked to visually explain or survey papers — do NOT create React artifacts or .jsx files.
    0
    installs
  31. Scientific Writing · iamseungpil bundle
    Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.
    0
    installs