By pipemind-com
Domain-agnostic scientific method research loop: collaboratively refine problems, then autonomously generate and test hypotheses until solved.
npx claudepluginhub pipemind-com/pipemind-marketplace --plugin scientific-methodDeepen a hypothesis with targeted literature research. Use whenever a hypothesis file needs supporting evidence, counterexamples, or a sharpened claim — including after generating-hypotheses or when a user asks to refine, strengthen, or research a specific hypothesis.
Refine a problem statement into a research-ready formulation. Creates problem.md through autonomous self-refinement backed by literature research.
Search for relevant academic and technical sources on a topic, build a structured bibliography in references.md, and download available articles. Use this skill whenever the user wants to find papers, survey existing research, build a reading list, gather citations, do a literature review, or explore what's been published on a topic -- even if they don't say 'literature review' explicitly.
Run a full scientific method research loop: refine problem, generate hypotheses, research literature, experiment, conclude, and iterate until solved. Use this skill whenever someone wants to investigate a question, debug a mysterious issue, explore a hypothesis, do a literature review, or solve any open-ended problem methodically — even if they don't say 'research' explicitly.
Execute experiments from a hypothesis file — run code, work through proofs, gather evidence, analyze data, and write results back. Use this skill whenever a hypothesis file has designed experiments with empty Results sections, when the user says 'run the experiments', 'test the hypothesis', 'try it', or 'execute the experiments', or when the next step in a scientific-method workflow is to actually attempt the experiments.
This skill should be used when the user asks to 'design experiments', 'plan tests for a hypothesis', 'create experiment paths', or 'figure out how to test this hypothesis'. Designs 1–3 experiment paths to verify or falsify a hypothesis and writes them into the hypothesis file.
Synthesize experiment results for a hypothesis into a verdict: confirmed, refuted, or inconclusive. Writes conclusion into the hypothesis file. Use this skill after running-experiments has filled in results, or whenever the user wants to evaluate whether a hypothesis held up, assess experiment outcomes, or decide what a research iteration means for the original problem.
Generate testable hypotheses from a problem statement and prior conclusions. Writes stub hypothesis files.
A marketplace of Claude Code plugins. Install plugins once globally (~/.claude/), then use them across all your projects.
| Plugin | Description | Docs |
|---|---|---|
| spec-driven-development | Self-replicating agentic workflow factory — compiles project-specific agents for any codebase | README |
# Marketplace
claude plugin marketplace add pipemind-com/pipemind-marketplace
# Plugins
claude plugin install spec-driven-development@pipemind-marketplace
claude plugin install scientific-method@pipemind-marketplace
claude plugin install rust-lsp@pipemind-marketplace
claude plugin install typescript-lsp@pipemind-marketplace
For issues with Claude Code itself: https://github.com/anthropics/claude-code
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.