Research AI Skills

Get a deep critical review of research from an external reviewer backend (Codex or manual). Use when user says "review my research", "help me review", "get external review", or wants critical feedback…

Deterministic citation-count and provenance gate for meta-paper-write. Checks the citation_map summary against the numeric paper citation target without trusting an LLM verdict.

Create new Beamer lecture from papers and materials. Guided workflow with notation consistency.

Resume prior work by rebuilding context from the Basic Memory knowledge graph — pick up where you left off using memory:// URLs, recent activity, and search. Use when starting a session or when the…

Re-derive your knowledge system from first principles when structural drift accumulates. Analyzes dimension incoherence, vocabulary mismatch, boundary dissolution, and template divergence. Preserves…

Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use `empathy-map`; for…

Research prediction markets - base rates, resolution rules, historical data

Weekly diagnostic report on a user's research knowledge base — flags stale profiles (not updated in weeks), thesis drift (AI detects original premise no longer holds), and orphan pages (profiles with…

Read-only audit of `.tex`, `.qmd`, or `.md` text for AI-voice tells — boilerplate transitions ("Moreover", "Furthermore", "It is important to note that"), AI-cliché lexicon ("delve", "navigate the…

Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.

Domain-validated multi-dimensional scoring system for divergent thinking tasks, including fluency, flexibility, originality, and automated semantic distance methods

Draft from the vault: outline from concept pages, keep citations to the user's own sources, and surface where their material disagrees. Use this skill when the user wants to write an article, post,…

学术审查 / research-integrity screening of a manuscript's figures and reported numbers. Finds duplicated, reused, or transformed image panels and data anomalies: copied value blocks, fixed…

GitHub operations via `gh` CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4)…

Use when a user provides ChatGPT web AI-search keywords, repeat count, target entity, entity type, OpenCLI profile, and crawl interval preference, then needs repeated crawls aggregated into JSON plus…

Structured pipeline for writing ML and AI research papers — from literature review to LaTeX submission

Standard operating procedure for academic figure generation. Four rendering engines: Python (data viz), Mermaid (flowcharts), AI Image via NanoBanana/OpenRouter (complex diagrams), SVG (vector).…

Build evidence-bound journal or conference shortlists for Light stage 12. Use after typesetting delivers venue-handoff.json/PDF/compliance facts; when an author asks where to submit, journal…

Use when translating established proposal objectives into research methods, a technical route, formal definitions, and an evaluation plan.

Verify that cited references actually exist and that their metadata matches, using the runnable scripts this skill ships for CrossRef, Semantic Scholar, arXiv, and PubMed. Use when the bibliography…

Manage project recipes/how-to sheets by listing, creating, updating, researching, or applying a recipe. Use for recipe, cook, /cook, list, new, update, research, apply.

Use when a broad paper candidate pool needs deterministic deduplication and a stable core set.

Write a specific section of an academic paper (Abstract, Introduction, Background, Related Work, Methods, Experiments, Results, Discussion/Conclusion) with section-specific guidance and two-pass…

Use when drafting a grant or challenge proposal for a radiology or medical AI project, including a Korean government industry-academia plan. Structures significance, innovation, approach, aims,…

記事内の事実主張（数値、日付、固有名詞、統計）を自動抽出し、Web検索で裏付け確認するスキル。 「ファクトチェックして」「事実確認して」「裏付けを取って」等のリクエストで発動。 信頼度スコア付きレポートを出力。

Surface expert frameworks. Use when creating or evaluating skills, hooks, or agents.

Systematic multi-factor stock screening using formal factor models to identify stocks with favorable factor exposures. Use when the user asks about factor investing, multi-factor screening,…

Turn Claude into a content research machine for any niche. Point it at any creator or account and it pulls their posts, finds the exact ones that blew up (the outliers), then breaks down WHY — the…

Systematic literature review across multiple arXiv papers.

Detect AI-generated text using rule-based analysis, LLM-as-judge scoring, and optional external APIs. Use when: auditing content for AI authorship, academic integrity checks, editorial review, SEO…

Plan videos and prepare publishing materials for YouTubers/UP主. Use when user wants to plan a video, write a script (口播稿) with on-screen / screen-share cues, generate video title, description, tags,…

Research with scoped depth and counterevidence.

Company, competitor, and market intelligence research using Exa or an equivalent web-search/MCP tool. Use for requests to research a company, build competitor lists, find company news, summarize…

从官方注册平台核实临床试验或其他研究的注册记录，并与方案、分析计划和稿件交叉检查注册时间、研究设计、 结局、样本量及结果报告差异。当用户提供 NCT、ChiCTR、ISRCTN、UMIN 等注册号，询问是否前瞻注册、是否 存在结局切换或需要注册声明时使用；报告规范的全面检查交给 dyz-med-guideline，未查到原始记录时不得生成 确定性注册声明。 Use to check trial…

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering,…

Prepare manuscripts for Cell Press journals (Cell, Molecular Cell, Neuron, Immunity, Cell Reports, Cell Systems, iScience, Cell Metabolism, Current Biology and others), covering Summary, Highlights,…

Advanced search on ScienceDirect with filters like author, journal, year, title, keywords. Use when the user wants filtered academic paper search.

Use when the user wants a market overview, external market intelligence, category analysis, or emerging opportunity investigation. Research market structure, demand conditions, category conventions,…

劳动用工回复草稿工作流，用于把劳动法律与用工管理问题整理成可复核、可追溯、可转发的简短答复文本。Use when：律师、法务、HRBP 或合规同学需要回复业务、管理层或客户的劳动用工问题，并希望输出“结论 + 依据 + 风险提示 + 待复核点”。NOT…

Summarize deep research results into markdown report, cover all fields, skip uncertain values.

Lists material events at a holding since a date: exec changes, litigation, rating actions, guidance and defaults, with why each one matters, using the Nimble `portfolio-monitoring` agent template on…

Clean research code for public release while preserving reported results. Uses release_audit.py to separate safe mechanical cleanup from ask-first behavior risks and identity leaks. Use for…

Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across a project. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库",…

Use this skill whenever the user must hold a sequence of items in working memory — phone numbers, OTP codes, account IDs, address strings, multi-step instructions, long forms, navigation menus with…

Generate ideas via named methods from creative practice.

Draft or restructure scientific manuscript arguments, sections, and initial-submission materials from author-provided evidence. Use for 论文写作、章节起草、论证重构、正文压缩、首次投稿材料. Use nature-polishing for…

Invoke parallel document-specialist agents for external web searches and documentation lookup

Compile heterogeneous knowledge sources—including documents, notes, web content, transcripts, research materials, and code repositories—into a Karpathy-style, evidence-grounded LLM Wiki with a…

Set up OpenSEO in the current AI agent. Use when a user pastes the OpenSEO installation prompt or asks to connect its plugin, MCP, and skills.

Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when…

Deterministic final delivery summary for meta-paper-write. Reports only verified PDF compilation fields and the exact citation-map SUMMARY statistics.