Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.
gemini-search
gemini-search is an open-source productivity skill for Claude Code and compatible agents, published by wanshuiyin. Its author describes it as: “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.”. The project has 15k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/gemini-search`.
What gemini-search does
Search query: $ARGUMENTS
Installation
Add gemini-search to your agent with:
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/gemini-searchAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for gemini-search is organised into these sections:
- Role & Positioning
- Constants
- Environment & Setup
- Prerequisites
- MCP Configuration
- Authentication
- Available MCP Tools
- Verify Setup
- Workflow
- Step 1: Parse Arguments
- Step 2: Execute Search (MCP Priority)
- Step 3: Parse Results
When to use it
Reach for gemini-search when you want productivity help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Clear MIT license — safe to read and adapt
- Ships in wanshuiyin/Auto-claude-code-research-in-sleep, an established project with 14,858 GitHub stars
- Actively maintained (recent commits)
Topics
Frequently asked questions
- What does gemini-search do?
- 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.
- How do I install gemini-search?
- Run git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/gemini-search in your agent, then reload your skills. Review the source at https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep before installing.
- Is gemini-search free to use?
- Yes. gemini-search is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Where does gemini-search come from?
- gemini-search ships inside wanshuiyin/Auto-claude-code-research-in-sleep, a repository that contains 41 catalogued skills in total. The repository's 14,858 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Productivity →
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).