Stats
Actions
Available In
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
By flight505
Deep research intelligence for Claude and agents — access, understand, and apply SOTA scientific research from arXiv, Semantic Scholar, Hugging Face Papers, and Perplexity
Evaluates codebase architecture against SOTA research. Use when Claude needs to assess whether an architecture, pattern, or approach is optimal — produces research-backed gap analysis with actionable recommendations. Bridges code analysis with academic literature.
Bridges from research paper to actionable implementation guidance. Use when Claude has identified an approach and needs to understand how to implement it — produces pseudocode, architecture, and adaptation guide.
Conducts multi-source literature review producing structured knowledge synthesis. Use when Claude needs to understand what a research field knows about a topic — consensus, frontier, open questions, and key papers.
Deep comparison of specific methods or architectures. Use when Claude needs to decide which approach to use — produces structured tradeoff analysis with recommendation.
Search arXiv for latest AI/ML preprints. Use when Claude needs bleeding-edge research not yet in peer-reviewed journals — newest methods, architectures, training techniques, benchmarks.
Search Hugging Face Papers for AI/ML research with AI-generated summaries, keywords, community upvotes, and trending papers. Use when Claude needs community-curated research, AI-generated paper summaries, or trending ML papers.
Web-grounded SOTA discovery using Perplexity Sonar models via OpenRouter. Use when academic APIs return foundational papers but you need to know what's CURRENT — what has superseded older methods, what practitioners actually use today, and what was released in the last weeks/months.
Search Semantic Scholar for papers with rich metadata — citation counts, AI-generated TLDRs, influence scores, citation graphs. Use for finding established research, tracing citation chains, understanding paper impact and field structure.
AI frontier plugin — gives Claude and agents access to latest scientific research, SOTA discovery, and architecture evaluation. Use when needing SOTA methods, research consensus, implementation guidance, or evaluating whether a codebase uses optimal patterns and architectures.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Deep research intelligence for Claude Code
Access, understand, and apply SOTA scientific research from arXiv, Semantic Scholar, and Hugging Face Papers
A Claude Code plugin that gives Claude and agents structured access to the scientific research frontier. Optimized for LLM consumption: structured synthesis, not raw search results.
claude plugin marketplace add flight505/flight505-marketplace
claude plugin install ai-frontier
| Skill | Purpose |
|---|---|
arxiv-search | Search arXiv preprints (cs.AI, cs.LG, cs.CL, cs.CV, stat.ML) |
semantic-scholar-search | Search 200M+ papers with TLDRs, citations, influence scores |
hf-papers-search | Search HF Papers with AI summaries, keywords, and trending |
| Agent | Use When |
|---|---|
architecture-evaluator | "Is this architecture optimal? Evaluate against SOTA." |
literature-reviewer | "What does the field know about X?" |
method-analyst | "Should I use method X or Y?" |
implementation-guide | "How do I implement X from this paper?" |
Claude automatically knows when to use research tools via the routing skill. When Claude encounters a research question, it:
fetch())MIT
npx claudepluginhub flight505/ai-frontierConnects to ArXiv and Semantic Scholar to find the latest AI/ML research papers, summarize their abstracts, and explain the methodology.
hoangsonwwSpecialized research analysis agents for critical thinking, evidence verification, synthesis, and parallel paper analysis
rpatrik96Three AI models, one synthesis — multi-model research workflow for scientific domains
AxectPhD-level research capabilities: literature review, multi-source investigation, critical analysis, hypothesis-driven exploration, quantitative/qualitative methods, and lateral thinking
poemsweSelf-evolving deep research. Gets smarter every time you use it. Searches across channels, synthesizes cited reports, and learns which queries and platforms work best.
0xmariowu深度研究 — 13 agent 协作：研究问题定义、系统性检索、偏差评估、综合分析、引用编译
Imbad0202Complete SOTA 2026 Storybook assistant with Vision AI design-to-code, natural language generation, AI-powered accessibility remediation, React Server Components, AI visual regression testing, design token sync, usage analytics, dark mode generation, and comprehensive testing (Storybook 10, React 19, Next.js 15)
flight505Comprehensive project planning and architecture research skills for Claude Code - generates software architecture documents, sprint plans, building blocks, service cost analysis, and implementation roadmaps backed by real research.
flight505AI-powered image, diagram, and video generation for Claude Code - uses Nano Banana 2 (Gemini 3.1 Flash Image) for fast generation, Nano Banana Pro (Gemini 3 Pro Image) for professional diagrams, and Veo 3.1 for video generation.
flight505Long-running agent loop for Claude Code, in the Ralph pattern — a stable prompt, a mutable plan, and a loop that runs until the plan is empty.
flight505Helper plugin for Claude Code's autonomous primitives — /goal, /branch, worktrees, dynamic workflows. Wraps native features with opinionated defaults and safety guardrails.
flight505