Research Skills

Route research tasks between a cost-conscious agentic search workflow, You.com Research API scripts, and managed or payment-aware MCP fallback.

Route finance questions to an existing local script, a new You.com Finance Research API call, or an MCP payment-aware fallback.

Personal research-paper radar. Fetches the latest papers and code repos for the user's keyword subscriptions across arXiv, Crossref (IEEE/ACM), Semantic Scholar, GitHub, HuggingFace, Papers with Code and RSS; deduplicates against history; then YOU (the assistant) expand the queries, filter for computer-science relevance, write Chinese summaries, detect hot sub-fields, and emit a Markdown + HTML digest (optionally emailed). Use when the user asks to "run my paper radar / 文献雷达", "check for new papers", "what's new in my topics", "今天有什么新论文 / 最新文献", "today's research digest", or to configure their keyword subscriptions / sources / schedule.

Use when the user asks to "verify citations", "check references", "validate paper citations", or "evaluate reference relevance". It extracts references from LaTeX/PDF papers, checks formatting rules, verifies existence via Crossref / Semantic Scholar / OpenAlex / PubMed / arXiv / dblp / Google Scholar / WebSearch, and scores thematic/semantic relevance.

헤르만 바빙크(Herman Bavinck, 1854-1921)의 신학을 토대로 설교 주제를 개발하고 깊이 있는 메시지를 형성하도록 돕는 코칭 스킬. 바빙크의 마그눔 오푸스 『개혁교의학(Reformed Dogmatics, 4권, Baker Academic 2003-2008 / 원작 Gereformeerde Dogmatiek 1895-1901)』을 1차 자료로 삼고, 거기서 답을 찾지 못할 때 다른 주요 저작(Our Reasonable Faith·The Certainty of Faith·In the Beginning·The Last Things·Christian Worldview·Bavinck on Preaching and Preachers·Essays on Religion·The Christian Family 등)으로, 그것에도 없으면 광범위 저술로 확장한다. 바빙크 저작 바깥의 추측이나 개인 의견은 회피하고, 답을 직접 찾지 못한 경우 그 사실을 명확히 표시한다. 바빙크 핵심 사상(은혜는 자연을 회복하고 완성한다 grace restores nature·삼위일체 중심 세계관 Trinitarian worldview·유기적 모티프 organic motif·일반 은총 common grace·일반 계시와 특별 계시의 조화·창조-타락-구속-종말의 통합·신학과 철학의 대화·언약 신학·신앙의 확실성)을 다룬다. 사용자가 "바빙크", "Bavinck", "개혁교의학", "Reformed Dogmatics", "은혜와 자연", "은혜는 자연을 회복", "일반 은총", "유기적 모티프", "Trinity and Organism", "기독교 세계관", "Christian Worldview", "신칼빈주의", "네덜란드 개혁주의", "Kuyper와 Bavinck", "James Eglinton", "신앙의 확실성", "바빙크 신학으로 설교"를 언급하거나 바빙크에 기대 설교 주제·메시지를 형성하길 원할 때 발동한다. 어거스틴·루터·칼빈·MLJ 코칭 스킬과 짝을 이루며 19-20세기 네덜란드 개혁주의 영역을 담당한다. 다양한 정통 기독교 교파 사용자가 모두 활용할 수 있도록 교파 중립적으로 작동하되, 바빙크의 입장은 그의 저작에 근거하여 정확히 전달한다. 신학생·목회자·진지한 평신도를 위해 설계되었다.

설교 주제 한 단어(예: "고난", "용서", "정의", "가난", "노동", "결혼", "환경", "AI", "전쟁", "외로움") 또는 한 문장을 입력받아, 11개 학문 분야(사회·기술·산업·경제·환경·정치·국제관계·법·제도·심리·영성)에서 학제간 기초 조사자료를 종합 산출하는 스킬. 통계·데이터·최신 연구·역사적 흐름·핵심 사상가·현장 사례를 분야별로 수집·정리하여 설교자가 본문과 회중 사이를 잇는 "현실 세계 컨텍스트"를 폭넓게 확보하도록 돕는다. 필요한 경우 웹 검색으로 최신 자료(통계·뉴스·보고서)를 보강한다. 사용자가 "○○ 주제로 설교 준비 자료", "○○에 대한 다양한 분야 자료", "○○ 기초 조사", "○○ 학제간 자료", "○○ 사회적·심리적·영적 분석", "이 주제로 무엇을 알아야 하나", "설교 자료 조사", "설교 배경 자료", "○○에 대한 통계와 데이터", "현대 사회에서 ○○", "○○에 대한 다각도 자료"를 언급하거나, 짧은 단어/주제어를 던지며 폭넓은 설교 자료 조사를 요청할 때 반드시 발동한다. 다른 sermon 스킬들이 본문·교리·문체·기획을 담당한다면, 본 스킬은 "설교 주제 바깥의 현실 세계 자료"를 다학제로 모으는 고유 영역을 전담한다. 목회자·신학생·종교 교육자·설교 사역자를 위해 설계되었다.

> Find and download virtually any digital resource from the internet — ebooks, academic papers, movies, TV shows, music, software, images, fonts, courses, and more. Covers both English and Chinese internet ecosystems. Includes CLI tool workflows (yt-dlp, aria2, gallery-dl, spotdl), resource site directories, cloud drive search engines (百度/阿里/夸克网盘搜索), and search from a URL, (2) find and download an ebook or academic paper, (3) find and download software, (4) search for any digital resource, (5) batch download images or media from a gallery/site, (6) download torrents or magnet links, (7) find free stock assets (images, video, audio, fonts), (8) search Chinese cloud drives for resources, or (9) any task involving finding or downloading digital content from the internet.

多AI并行深度研究。当用户需要对某个主题进行全面调研、深度研究、多方对比、或需要覆盖多个维度和来源的综合分析时触发。适合复杂主题（技术选型、竞品分析、行业趋势、争议性话题等），不适合简单事实查询。通过多个AI服务并行研究，交叉验证，输出带引用的综合报告。

>- Place pre-screened literature citations into a LaTeX or Word manuscript, or restyle the with a compiled references.bib, for author-date journals (APA, MLA, Harvard, Chicago author-date, IEEE, Vancouver); (2) footnote placement — full formatted \footnote{} or OOXML footnotes for legal and notes styles (Bluebook, OSCOLA, Chicago, APA, McGill) with Id./supra short forms; (3) restyle — convert existing footnote citations from one style to another. This skill is manual-invoke ONLY — trigger ONLY when the user explicitly runs /cite-placement or explicitly names the "cite-placement" skill. Do NOT auto-trigger on general citation, footnote, or reference requests.

>- Convert between LaTeX and Microsoft Word for academic manuscripts in either .tex/LaTeX to Word/.docx ("tex to docx", "latex to word", "tex2docx", "convert to word", "pandoc convert"); converting .docx manuscripts to LaTeX for editing and back ("convert to latex", "manuscript", "footnotes", "reference doc", the docx-to-tex-to-docx round-trip / academic paper editing pipeline); high-fidelity delivery where plain pandoc loses tables, mangles cross-references, or fails on custom macros — booktabs/regression tables, OMML equations, cleveref, \estauto, \@@input, \thanks, TikZ, native Word tables, longtable, siunitx; and building .tex from mixed PDF/docx/LLM-generated sources. Replaces and reroutes the retired skills manuscript-editing-template-latex, latex-to-docx-fidelity, tex2docx, and latex-from-mixed-sources.

>- research question produced by Stage 0, scrape each result's citation (Cite to BibTeX), then parse + enrich into the pipeline schema. The driver signs in to Google with a persistent profile and runs headless via Playwright. Only use this skill when explicitly requested. Do NOT auto-trigger on general literature review or paper search requests.

> prior stages (Undermind, Scholar Labs, supplementary search) into a single LLM fuzzy match via DeepSeek/Claude. Only use this skill when explicitly requested — e.g., the user says "run lit-dedup", "lit-dedup", or "/lit-dedup". Do NOT auto-trigger on general literature review requests.

> Scholar (--scholar), SSRN, NBER, HeinOnline, citation chaining via Semantic Scholar, and forthcoming paper lists from top finance journals. Long research prompts are automatically condensed into 3-5 short queries via Claude Sonnet before searching. Only use this skill when explicitly requested — e.g., the user says "run supplementary search", "supplementary-search", or "/supplementary-search". Do NOT auto-trigger on general literature review or paper search requests.

> search (Interactions API) from the brief produced by Stage 0, then parse the cited report into the pipeline schema. API-driven (GEMINI_API_KEY), no browser. An alternative deep-search pathway alongside Undermind (Stage 1) and Scholar Labs (Stage 2). Only use this skill when explicitly requested. Do NOT auto-trigger on general literature review or paper search requests.

> research prompt. The orchestrator's agent-driven flow runs this re-ranker on Opus subagents; a standalone run uses the in-script Claude Sonnet API fallback. Rates relevance 1-10, tags each paper as theoretical/empirical, identifies methodology, and classifies relationship to user's work. Only use this skill when explicitly requested -- e.g., the user says "run lit-screen", "lit-screen", or "/lit-screen". Do NOT auto-trigger on general literature review requests.

> from the natural-language brief produced by Stage 0, then parse + enrich the exported references into the pipeline schema. The driver logs in automatically with stored credentials and runs headless via Playwright. Only use this skill when explicitly requested. Do NOT auto-trigger on general literature review or paper search requests.

Run the lit-review orchestrator keyless agent-driven web search channel that uses WebSearch and WebFetch outputs normalized through websearch_ingest.py. Use when the user invokes the web search channel, asks for Stage 4d open-web literature discovery, or needs a Claude Code web-search fallback without SearchAPI, Gemini, or Undermind credentials.

Style every matplotlib figure like the Stata 18/19 default (stcolor) scheme — Arial embedded as TrueType, white background, recessive light-gray grid below the data, no top/right spines, unframed legends, and the validated blue/red/gray palette. Use whenever a task generates or restyles charts, plots, or figures for papers, reports, or slides, even if the user doesn't mention Stata — this is the house style for all publication figures. Also use when asked to make figures "look like Stata", match the stcolor scheme, or restyle existing matplotlib output.

Connect to and query WRDS (Wharton Research Data Services) from any research project. Use this skill whenever the user needs to download, query, or explore data from WRDS — including Compustat, CRSP, FactSet, I/B/E/S, or any other WRDS-hosted database. Also trigger when the user mentions WRDS tables, WRDS libraries, or wants to look up variable definitions or coverage in WRDS datasets. Do NOT trigger for general SQL or database questions unrelated to WRDS.

Research topics and document findings in Notion with organized structure and sources

Comprehensive, research-backed Hinge dating profile optimization. Use when someone wants to improve their Hinge profile, audit an existing profile, write better prompts/captions, select and order photos strategically, or understand why they're not getting quality matches. This is the thorough process (~45 mins) - discovery interview, honest market math, photo strategy, copy creation, settings cleanup, and implementation support. Grounded in peer-reviewed behavioral research, platform data, and signaling theory.

This skill should be used when the user asks to "develop a feature", "implement a ticket", "build PROJ-123", "run the development pipeline", "develop this ticket end to end", or wants fully autonomous feature implementation with parallel research agents, planning, phased implementation, review, and PR creation. Zero checkpoints; pauses only on blockers.

Autonomously research an ML task and run MANY bounded experiments to find the best config — a fixed-budget edit→train→eval→keep-or-discard loop in the spirit of karpathy/autoresearch, wrapped in the ml-intern orchestrator model and fanned out with a Claude Code dynamic workflow. Runs LONG: an iterative generational loop (mims-harvard/AutoScientists style) where parallel agent teams propose hypotheses, peer-critique them before spending any GPU, share findings on a common board, promote a champion, and keep going until budget/stagnation/convergence. Triggers when the user wants to "run many experiments", "sweep / search for the best config", "beat a benchmark", "do an ablation", "autoresearch X", "run for a long time / overnight / for days", or "find what improves metric Y on dataset Z". Deep-researches existing solutions across the internet FIRST (fan-out web search + PapersWithCode + GitHub, sources cross-checked into a cited DEEPRESEARCH.md), then ASKS where to get GPUs ("cards") and data before spending any compute, generates an experiment matrix seeded from diverse literature angles, runs it as a background workflow under an explicit budget, keeps a running leaderboard + shared findings board, verifies winners, and reports the best config. Reuses ml-intern's notify.sh + hf_push.sh for milestone alerts and HF Hub publishing.

This skill should be used when the user asks to "research web data", "scrape websites", "extract web data", "perform market research", "analyze competitors", "monitor prices", "collect product information", "search and analyze web content", or mentions Bright Data MCP, web scraping, web data extraction, or automated research. Provides comprehensive web research workflows using Bright Data MCP tools including search, scraping, extraction, and browser automation capabilities.

Explicit extra-research mode. Use only when the user says `/re` or clearly asks for a research-heavy pass before coding. This skill should bias Codex toward more source-checking and justification without replacing its normal orchestration.

Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.

Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.

Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.

Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.

Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.

Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.

Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.

Scans, analyzes, and documents the existing repository architecture, directories, and file purposes into docs/ARCHITECTURE.md.

Analyze user/customer feedback into a Feedback Analysis Pack (taxonomy, themes, recommendations). See also: conducting-user-interviews (collect new), designing-surveys (quantitative).

Plan, conduct, and synthesize user/customer interviews. See also: conducting-interviews (hiring), designing-surveys (quantitative).

Run structured behavioral HIRING interviews: plan, questions, scorecard, debrief. See also: conducting-user-interviews (product research).

Design and launch a product survey: brief, questionnaire, analysis plan, launch checklist. See also: conducting-user-interviews (qualitative).

Measure PMF: Sean Ellis survey, retention evidence, reference-customer signals, action plan. See also: retention-engagement (optimize post-PMF).

> problems, designing ML/AI experiments, reading papers, building experiment loops, analyzing outputs, writing research notes, or turning vague curiosity into a disciplined research plan. Emphasizes avoiding absorbed problems, upgrading information inputs beyond shared reading lists, and reasoning backward from outcomes the researcher genuinely wants to exist.

Converts messy discovery inputs (interviews, feedback, research, tickets) into structured hypotheses, assumptions, and candidate requirements with full traceability.

| Finds qualified candidates for a role by searching LinkedIn, Indeed, GitHub, and other professional platforms using Nimble Web Search Agents. Accepts a job description, role title, or freeform request and returns a ranked candidate list with profiles, skills, and contact signals. Use this skill when the user wants to find, source, or recruit candidates for "who can I hire for", "find me a [role]", "recruiting for", "talent search", "find a [role] in [city]", "build a candidate list", "sourcing for [role]", "who's available for", "find potential hires". Also triggers on a pasted job description followed by a sourcing request. Do NOT use for job market research or salary benchmarking — use market-finder instead. Do NOT use for researching a single known person — use company-deep-dive or meeting-prep instead.

| Reference for Nimble Web Search Agents (Agent API V2). Load when a task needs open-ended research, enrichment, or dataset building — where the source isn't fixed, data is scattered, structure is inconsistent, or a synthesized answer is needed. locking, run-level `skill` override, run controls, live events vs polling, trust and citations, and safe credentials.

Use this agent when you need to research and gather external best practices, documentation, and examples for any technology, framework, or development practice. This includes finding official documentation, community standards, well-regarded examples from open source projects, and domain-specific conventions. The agent excels at synthesizing information from multiple sources to provide comprehensive guidance on how to implement features or solve problems according to industry standards. <example>Context: User wants to know the best way to structure GitHub issues for their Rails project. user: \"I need to create some GitHub issues for our project. Can you research best practices for writing good issues?\" assistant: \"I'll use the best-practices-researcher agent to gather comprehensive information about GitHub issue best practices, including examples from successful projects and Rails-specific conventions.\" <commentary>Since the user is asking for research on best practices, use the best-practices-researcher a...

Enhance a plan with parallel research agents for each section to add depth, best practices, and implementation details

Systematic debugging that identifies root causes rather than treating symptoms. Uses sequential thinking for complex analysis, web search for research, and structured investigation to avoid circular reasoning and whack-a-mole fixes.

Use this agent when you need to gather comprehensive documentation and best practices for frameworks, libraries, or dependencies in your project. This includes fetching official documentation, exploring source code, identifying version-specific constraints, and understanding implementation patterns. <example>Context: The user needs to understand how to properly implement a new feature using a specific library. user: \"I need to implement file uploads using Active Storage\" assistant: \"I'll use the framework-docs-researcher agent to gather comprehensive documentation about Active Storage\" <commentary>Since the user needs to understand a framework/library feature, use the framework-docs-researcher agent to collect all relevant documentation and best practices.</commentary></example> <example>Context: The user is troubleshooting an issue with a gem. user: \"Why is the turbo-rails gem not working as expected?\" assistant: \"Let me use the framework-docs-researcher agent to investigate the turbo-rails documentation...

Use this agent when you need to search institutional learnings in docs/solutions/ for relevant past solutions before implementing a new feature or fixing a problem. This agent efficiently filters documented solutions by frontmatter metadata (tags, category, module, symptoms) to find applicable patterns, gotchas, and lessons learned. The agent excels at preventing repeated mistakes by surfacing relevant institutional knowledge before work begins.\\n\\n<example>Context: User is about to implement a feature involving email processing.\\nuser: \"I need to add email threading to the brief system\"\\nassistant: \"I'll use the learnings-researcher agent to check docs/solutions/ for any relevant learnings about email processing or brief system implementations.\"\\n<commentary>Since the user is implementing a feature in a documented domain, use the learnings-researcher agent to surface relevant past solutions before starting work.</commentary></example>\\n\\n<example>Context: User is debugging a performance issue.\\nuser: \"Bri...

Use this agent when you need to conduct thorough research on a repository's structure, documentation, and patterns. This includes analyzing architecture files, examining GitHub issues for patterns, reviewing contribution guidelines, checking for templates, and searching codebases for implementation patterns. The agent excels at gathering comprehensive information about a project's conventions and best practices.\\n\\nExamples:\\n- <example>\\n Context: User wants to understand a new repository's structure and conventions before contributing.\\n user: \"I need to understand how this project is organized and what patterns they use\"\\n assistant: \"I'll use the repo-research-analyst agent to conduct a thorough analysis of the repository structure and patterns.\"\\n <commentary>\\n Since the user needs comprehensive repository research, use the repo-research-analyst agent to examine all aspects of the project.\\n </commentary>\\n</example>\\n- <example>\\n Context: User is preparing to create a GitHub issue and wants to foll...