学术
学术写作、研究与引用
researching-codebase
bnadlerjr
"Researches and documents existing codebase implementations. Use when exploring how code works, understanding architecture, answering 'how does X work?' questions, or gathering context before making changes. Produces structured research documents with code references."
pre-submission-report
mseok
"Run all quality checks and produce a single dated report before submission or sharing."
mcp-research
ahgraber
Use when tasks require current, source-backed technical information from MCP tools. Apply for library/API questions, dependency version checks, third-party integration work, framework- or SDK-specific debugging, and any case where stale model knowledge could cause incorrect guidance.
interview-me
mseok
"Interactive interview to formalise a research idea into a structured specification with hypotheses and empirical strategy. Conversational — asks questions one at a time."
init-project
mseok
"Bootstrap a new research project. Interview for details, scaffold directory structure, create Overleaf symlink, initialise git, and create project context files."
beamer-deck
mseok
"Generate academic Beamer presentations with multi-agent review. Builds original themes, applies rhetoric principles, iterates until zero warnings."
writing-product-briefs
bnadlerjr
"Write Product Briefs that align teams on goals before discovery. Use when defining a new product vision, articulating problem statements, creating one-pagers, or crafting north star scenarios. Produces vision documents with thesis/antithesis, target audience, metrics, and narrative scenarios."
single-paper-review
mseok
Create a detailed single-paper summary note in Markdown (Obsidian-friendly). Use when asked for "paper review" meaning "논문 정리/요약", single-paper deep summary, or when the user wants method and results written with metric definitions (math + interpretation) and reusable figures/tables embedded from Attachments/.
literature
mseok
"Academic literature discovery, synthesis, and bibliography management. Find papers, verify citations, create .bib files, download PDFs, and synthesize literature narratives. Includes OpenAlex API integration for structured scholarly queries."
implementation-planning
bnadlerjr
Creates detailed implementation plans through interactive research and iteration. Use when in plan mode, planning features, designing implementations, breaking down tasks into phases, or when the user asks "how should I implement X", "plan this feature", or wants a technical specification.
latex
mseok
"LaTeX document compilation and management. When Codex needs to compile LaTeX documents (.tex files) for papers, presentations, or other academic content."
coding-workflow
bnadlerjr
Use when user asks to build a feature, implement something new, or make significant code changes. Recognizes requests like "build", "implement", "create a new feature", "add functionality", "develop", "I need to build X", "let's implement", "new feature request", "make these changes". Orchestrates a four-stage workflow (Research → Brainstorm → Plan → Implement) using the appropriate thought pattern skill at each stage.
scientific-writing
mseok
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.
split-pdf
mseok
Download, split, and deeply read academic PDFs. Use when asked to read, review, or summarize an academic paper. Splits PDFs into 4-page chunks, reads them in small batches, and produces structured reading notes — avoiding context window crashes and shallow comprehension.
validate-bib
mseok
"Cross-reference \cite{} keys against .bib files or embedded \bibitem entries. Finds missing, unused, and typo'd citation keys. Deep verification mode spawns parallel agents for DOI/metadata validation at scale. Read-only in standard mode."
research-ideation
mseok
"Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset. Produces 3–5 ranked questions with identification strategies."
latex-autofix
mseok
"LaTeX compilation with autonomous error resolution. Build artifacts go to out/, PDF is copied back to source directory. Parses logs, auto-fixes known errors (missing packages, font conflicts, citation issues, bad paths, stale cache), and runs citation audit on success."
research-paper
build000r
Generate dense, academic research paper-style pages on any topic. Use when: "research paper", "write a paper on", "research page", "/research-paper", "internal paper on", "write up on [topic]". Supports project-specific modes (styling, data sources, routing) via local modes/ directory. Takes a topic argument (e.g. "teeth", "longevity", "AI agents", "SaaS pricing").
humanizer
mseok
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
project-deck
mseok
"Create presentation decks to communicate project status. For supervisor meetings, coauthor handoffs, or documenting progress."
retarget-journal
mseok
"Retarget a paper to a different journal. Renames folders, swaps bib files, updates citation keys, reformats to target requirements, and compiles to verify."
d-research
d-init-d
Browser-first deep research and lawful public-data collection for AI agents. Triggers: web research, source discovery, scraping public data, literature reviews, market or technical research, evidence ledgers, blocker reports. Read-only; never bypasses logins, paywalls, captchas, or rate limits.
icml-reviewer
mseok
Paper reviewer that evaluates machine learning research projects following official ICML reviewer guidelines. Provides comprehensive reviews with actionable feedback across all key dimensions: claims/evidence, relation to prior work, originality, significance, clarity, and reproducibility. Also provides formative feedback on incomplete drafts, proposals, and research code repositories. MANDATORY TRIGGERS: review paper, ICML review, paper review, evaluate paper, research paper feedback, ML paper review, conference review, academic review, paper critique, NeurIPS review, ICLR review, project proposal, research proposal, paper draft, early feedback, incomplete paper, work in progress, WIP review, review repo, review codebase, research project review
devils-advocate
mseok
"Challenge research assumptions and identify weaknesses in arguments. Stress-test papers before submission or revision."