An automated AI research-code writer and AI research-paper writer implementation through a skills+ autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.
Skill Claude Code
Use when main results pass result-to-claim (claimsupported=yes or partial) and ablation studies are needed for paper submission. Codex designs ablations from a reviewer's perspective, CC reviews feasibility and implements.
Skill Claude Code needs its repo
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
Skill Claude Code
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
Skill Claude Code needs its repo
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.
Skill Claude Code needs its repo
An automated paper-editing loop that has GPT-5.4 review a compiled research paper, applies writing and presentation fixes, and recompiles it.
Skill Claude Code needs its repo
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
Skill Claude Code needs its repo
Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
Skill Claude Code
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports. Uses a fresh cross-model reviewer with web/DBLP/arXiv lookup to catch hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context…
Skill Claude Code
A tool for drafting patent claims, the legal statements that define what an invention seeks to protect. It uses invention details and prior-art information to shape claims for a patent application.
Skill Claude Code
Communications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or…
Skill Claude Code needs its repo
Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
Skill Claude Code
Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says "DSE", "design space exploration", "sweep parameters", "optimize", "find best config", or wants iterative parameter tuning.
Skill Claude Code
A tool for writing detailed patent embodiments, which are concrete examples of how an invention can be built and used. These descriptions support the claims and show how the invention works in practice.
Skill Claude Code needs its repo
AI-powered web search via Exa with content extraction. Use when user says "exa search", "web search with content", "find similar pages", or needs broad web results beyond academic databases (arXiv, Semantic Scholar).
Skill Claude Code
A research-integrity audit reviews experiment code and evidence before results are reported as claims.
Skill Claude Code needs its repo
A workflow tool that turns a research experiment plan into implemented code, deployed runs on GPUs, and initial results. It connects planning, code review, execution, and result collection.
Skill Claude Code needs its repo
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after research-refine, or when the user asks for a detailed experiment plan, ablation matrix, evaluation protocol, run order, compute budget, or paper-ready validation that supports the core problem, novelty…
Skill Claude Code
A tool for sending status messages and approval requests through Feishu, also called Lark, a workplace messaging and collaboration platform.
Skill Claude Code
A tool for turning user-provided patent drawings into formal descriptions that identify parts with reference numbers. A patent drawing is a technical figure used to support a patent application.
Skill Claude Code needs its repo
A tool that turns structured descriptions of systems and workflows into editable SVG diagrams. SVG is a text-based image format that can be adjusted later without redrawing the whole figure.
Skill Claude Code
A tool for turning scattered research notes and equations into a clear mathematical derivation. It can distinguish an exact identity, a result that needs assumptions, an approximation, or an interpretation of how something works.
Skill Claude Code
Search research papers via Gemini for broad literature discovery. Use when user says "gemini search", "gemini papers", "search with gemini", or wants AI-powered literature discovery beyond arXiv/Semantic Scholar indexes.
Skill Claude Code needs its repo
A workflow that turns a research idea and literature review into a structured grant proposal. A grant proposal is an application that asks a funding organization to support planned research.
Skill Claude Code needs its repo
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: