Skills for AI/ML research: understanding papers, designing experiments, refining research questions, and developing research taste
/plugin marketplace add GhostScientist/skills
/plugin install research-skills@GhostScientist/skills
Analyzes existing iOS/macOS/Apple platform projects to create a comprehensive, phased plan for building a watchOS companion or standalone app. Use when users want to add watchOS support to an existing Apple platform app, create a Watch app version of their iOS app, or build watchOS features. The skill digests project architecture, identifies patterns, analyzes API compatibility, searches for current watchOS documentation, and produces a detailed implementation plan with API availability warnings before any code generation.
Generates a rigorous experiment design given a hypothesis. Use when asked to design experiments, plan experiments, create an experimental setup, or figure out how to test a research hypothesis. Covers controls, baselines, ablations, metrics, statistical tests, and compute estimates.
Guides you through implementing a research paper step-by-step from scratch. Use when asked to implement a paper, code up a paper, reproduce research results, or build a model from a paper. Focuses on building understanding through implementation with checkpoint questions.
Generates a complete iOS app icon set with all required sizes. Use when asked to create an app icon, design an iOS icon, generate app store artwork, or make an icon for an iPhone/iPad app. Follows a philosophy-first approach - first defining the visual identity and concept, then producing production-ready icons.
Transforms an academic paper into deep, multi-layered understanding. Use when asked to explain a paper, break down a research paper, understand an arXiv paper, or build intuition for a technical concept from a paper. Generates explanations at multiple levels plus visual intuition diagrams.
Helps transform a vague research interest into a concrete, tractable research question. Use when asked to refine a research idea, develop a research question, scope a research project, or figure out what to work on. Walks through systematic refinement with feasibility analysis.
Develops intuition for what makes research "good" versus "incremental." Use when asked about research taste, how to identify good research, what makes a paper impactful, how to develop research intuition, or how to pick important problems. Analyzes patterns in highly-cited work and what top researchers do differently.
Critiques your paper draft as a skeptical reviewer would. Use when asked to review a paper draft, find weaknesses in a paper, prepare for peer review, anticipate reviewer criticism, or stress-test research before submission. Identifies weak claims, missing baselines, unclear explanations, and overclaims.
Generates a technical blog post from code implementation. Use when asked to write a blog post about a feature, explain an implementation for a blog, document code as a blog article, or create technical content from source code. Triggers on phrases like "write a blog post about", "turn this into a blog", "create a technical article", or "explain this for a blog".
Claude Agent SDK Development Plugin
Comprehensive toolkit for developing Claude Code plugins. Includes 7 expert skills covering hooks, MCP integration, commands, agents, and best practices. AI-assisted plugin creation and validation.
Implementation of the Ralph Wiggum technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review