create-lecture
Create new Beamer lecture from papers and materials. Guided workflow with notation consistency.
Create new Beamer lecture from papers and materials. Guided workflow with notation consistency.
Challenge slide design with 5-7 pedagogical questions. Checks ordering, prerequisites, and cognitive load.
Run holistic pedagogical review on lecture slides. Checks narrative arc, student prerequisites, worked examples, notation clarity, and deck pacing.
Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset
Guidelines for using and contributing to the @code-dot-org/component-library design system and the DSCO-to-MUI migration. Use when working on React UI in apps/ or frontend/.
Evaluate source code for correctness, quality, security, style conformance, and maintainability, producing a structured review report with findings and recommendations. Use when the user wants to review, critique, audit, evaluate, or inspect source code — checking for bugs, logic errors, unhandled error paths, security vulnerabilities, naming and readability issues, complexity, duplication, coupling, testability, and API design. Discovers codebase conventions independently and produces an actionable report with severity-graded findings grouped by category, prioritized recommendations, and open questions.
Use when exploring, understanding, or answering questions about a codebase that has Repowise indexed (indicated by a .repowise/ directory in the project root). Activates for questions like "how does X work", "explain the architecture", "where is Y implemented", "what does this module do", or any task requiring understanding of codebase structure before diving into source files.
Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.
Read and search GitHub repository documentation via gitmcp.io MCP service. **WHEN TO USE:** - User provides a GitHub URL - User mentions a specific repo in owner/repo format - User asks "what does this repo do?", "read the docs for X repo", or similar - User wants to search code or docs within a repo
Create or update Codex hooks for global or project scope by asking for scope and hook type when ambiguous, then writing the hook config, scripts, and any required feature flag config.
Fetch up-to-date library documentation via Context7 CLI. Use PROACTIVELY when: (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or best practices (3) Implementing features that rely on third-party packages (4) Debugging library-specific issues (5) Need current documentation beyond training data cutoff (6) AND MOST IMPORTANTLY, when you are installing dependencies, libraries, or frameworks you should ALWAYS check the docs to see what the latest versions are. Do not rely on outdated knowledge. Always prefer this over guessing library APIs or using outdated knowledge.
Converts an arxiv paper into a minimal, citation-anchored Python implementation. Trigger when user runs /paper2code with an arxiv URL or paper ID, says "implement this paper", or pastes an arxiv link asking for implementation. Flags all ambiguities honestly. Never invents implementation details not stated in the paper.
Write or rewrite SEED Design component guideline docs (MDX) by extracting content and images from Figma documentation layers. Use this skill whenever the user wants to create, update, or migrate component documentation from Figma into docs/content/docs/components/, provides a Figma node URL for documentation, or asks to write/update a component guideline page. Also triggers for "write the docs for X component", "create guideline from Figma", "update the MDX for [component]", "가이드라인 문서 작성", or "피그마에서 문서 가져오기".
List installed skills, search the skill registry, install new skills, and manage workspace extensions. Use when the user asks to find, install, list, or configure skills, or mentions skill registry, extensions, or workspace capabilities.
Look up and record geolocations in Obsidian notes using the Map View plugin. Use as part of helping the user to plan a trip, research places to visit, record a location in a note, or whenever the content being added to a note includes named real-world places. Every time the user asks you add to a note something that is a location, consider using this skill so it will be logged as a geolocation.
Create new skills for Claude Code. Use when users ask to create a skill, add a skill, make a new command, build a skill, add a slash command, create a plugin skill, or define a new automation. Trigger phrases include "create a skill", "new skill", "add a skill", "make a command", "build a skill", "I want a skill that", "add slash command", "create automation".
Marin architecture overview and repository structure reference. Use when you need to understand how Marin works, find a module, or orient yourself in the codebase.
Write a tight, readable design document for a proposed change. Use when asked to write a design doc, spec, or technical proposal.
Write in Marin's house style for public and internal text. Use when drafting or revising blog posts, technical reports, documentation, GitHub issues, experiment issues, Discord updates, or other Marin-authored writing.
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.
This skill should be used when the user asks to "analyze experimental results", "generate results section", "statistical analysis of experiments", "compare model performance", "create results visualization", or mentions connecting experimental data to paper writing. Provides comprehensive guidance for analyzing ML/AI experimental results and generating paper-ready content.
Create academic presentation slide decks and optionally demo videos from research papers. Use when the user asks to "make slides", "create a deck", "make a presentation", "demo video", "paper slides", "conference talk slides", or wants to turn a paper into a visual presentation. Covers slide generation, narration scripts, TTS audio, and video assembly.