yichen-zju/claude-for-research
125 instruction files for AI agents, collected from yichen-zju/claude-for-research. Install any of them at an exact version with mdr add yichen-zju/claude-for-research/<name>.
git:20260930.9b33ccf · audit A · 10 stars
git:20261014.9f2a5e0 · audit A · 10 stars
evolving-ai-agents SKILL.md skill
yichen-zju/claude-for-research · claude/skills/a-evolve/SKILL.md · Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution…
v1.0.0 · audit A · 10 stars
academic-plotting SKILL.md skill
yichen-zju/claude-for-research · claude/skills/academic-plotting/SKILL.md · Generates publication-quality figures for ML papers from research context. Given a paper section or description…
v1.0.0 · audit A · 10 stars
academic-research-suite SKILL.md skill
yichen-zju/claude-for-research · claude/skills/academic-research-suite/SKILL.md · Claude-native Academic Research Skills suite (ported from the Codex adapter) for deep research, academic paper writing…
v0.1.14 · audit A · 10 stars
huggingface-accelerate SKILL.md skill
yichen-zju/claude-for-research · claude/skills/accelerate/SKILL.md · Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for…
v1.0.0 · audit A · 10 stars
ai-use-disclosure SKILL.md skill
yichen-zju/claude-for-research · claude/skills/ai-use-disclosure/SKILL.md · Generate venue-specific AI-use disclosure statements for manuscript submission (ICLR, NeurIPS, ICML, Nature, Science…
git:20261014.9f2a5e0 · audit A · 10 stars
alpha-research SKILL.md skill
yichen-zju/claude-for-research · claude/skills/alpha-research/SKILL.md · Search, read, and query research papers via the alphaxiv MCP server (2.5M+ arXiv papers). Use when the user asks about…
git:20261014.9f2a5e0 · audit A · 10 stars
alphafold2 SKILL.md skill
yichen-zju/claude-for-research · claude/skills/alphafold2/SKILL.md · Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer…
git:20261014.9f2a5e0 · audit A · 10 stars
anti-defensive-writing-en SKILL.md skill
yichen-zju/claude-for-research · claude/skills/anti-defensive-writing-en/SKILL.md · Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments…
git:20261014.9f2a5e0 · audit A · 10 stars
anti-defensive-writing SKILL.md skill
yichen-zju/claude-for-research · claude/skills/anti-defensive-writing/SKILL.md · 论文写作、修改、压缩和实验组织全流程中阻止【防御性写作】。把论文视为一场学术发布会， 而不是项目总结、实验日志或自我审查报告：识别这项工作最值得发表的价值，围绕它建立…
git:20261014.9f2a5e0 · audit A · 10 stars
autoresearch SKILL.md skill
yichen-zju/claude-for-research · claude/skills/autoresearch/SKILL.md · Autonomous experiment loop with evidence-driven move selection — scales from parameter tuning (directional search) to…
git:20261014.9f2a5e0 · audit A · 10 stars
awq-quantization SKILL.md skill
yichen-zju/claude-for-research · claude/skills/awq/SKILL.md · Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when…
v1.0.0 · audit A · 10 stars
benchmark-paper-template SKILL.md skill
yichen-zju/claude-for-research · claude/skills/benchmark-paper-template/SKILL.md · Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline…
git:20261014.9f2a5e0 · audit A · 10 stars
quantizing-models-bitsandbytes SKILL.md skill
yichen-zju/claude-for-research · claude/skills/bitsandbytes/SKILL.md · Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is…
v1.0.0 · audit A · 10 stars
blip-2-vision-language SKILL.md skill
yichen-zju/claude-for-research · claude/skills/blip-2/SKILL.md · Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning…
v1.0.0 · audit A · 10 stars
boltz SKILL.md skill
yichen-zju/claude-for-research · claude/skills/boltz/SKILL.md · Run or plan Boltz biomolecular structure predictions for proteins, complexes, ligands, or nucleic-acid assemblies. Use…
git:20261014.9f2a5e0 · audit A · 10 stars
borzoi SKILL.md skill
yichen-zju/claude-for-research · claude/skills/borzoi/SKILL.md · Use Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task…
git:20261014.9f2a5e0 · audit A · 10 stars
brainstorming-research-ideas SKILL.md skill
yichen-zju/claude-for-research · claude/skills/brainstorming-research-ideas/SKILL.md · Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when…
v1.0.0 · audit A · 10 stars
chai1 SKILL.md skill
yichen-zju/claude-for-research · claude/skills/chai1/SKILL.md · Run or prepare Chai-1 structure predictions for biomolecular complexes. Use when a task asks for Chai-1 inputs…
git:20261014.9f2a5e0 · audit A · 10 stars
clip SKILL.md skill
yichen-zju/claude-for-research · claude/skills/clip/SKILL.md · OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and…
v1.0.0 · audit A · 10 stars
compute-env-setup SKILL.md skill
yichen-zju/claude-for-research · claude/skills/compute-env-setup/SKILL.md · Set up a reproducible compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries…
git:20261014.9f2a5e0 · audit A · 10 stars
contributing SKILL.md skill
yichen-zju/claude-for-research · claude/skills/contributing/SKILL.md · Maintain and improve this Claude Code research environment — its skills, subagents, conventions, and workflows. Use…
git:20261014.9f2a5e0 · audit A · 10 stars
creative-thinking-for-research SKILL.md skill
yichen-zju/claude-for-research · claude/skills/creative-thinking-for-research/SKILL.md · Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely…
v1.0.0 · audit A · 10 stars
customize SKILL.md skill
yichen-zju/claude-for-research · claude/skills/customize/SKILL.md · Configure this Claude Code research environment — skills, subagents, permissions, hooks, compute providers, and project…
git:20261014.9f2a5e0 · audit A · 10 stars
deep-research SKILL.md skill
yichen-zju/claude-for-research · claude/skills/deep-research/SKILL.md · Run a thorough, source-heavy investigation on any topic. Use when the user asks for deep research, a comprehensive…
git:20261014.9f2a5e0 · audit A · 10 stars
deepspeed SKILL.md skill
yichen-zju/claude-for-research · claude/skills/deepspeed/SKILL.md · Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism…
v1.0.0 · audit A · 10 stars
diffdock SKILL.md skill
yichen-zju/claude-for-research · claude/skills/diffdock/SKILL.md · Run or plan DiffDock molecular docking workflows. Use when a task asks for protein-ligand pose prediction, docking…
git:20261014.9f2a5e0 · audit A · 10 stars
docker SKILL.md skill
yichen-zju/claude-for-research · claude/skills/docker/SKILL.md · Execute research code inside isolated Docker containers for safe replication, experiments, and benchmarks. Use when the…
git:20261014.9f2a5e0 · audit A · 10 stars
esmfold2 SKILL.md skill
yichen-zju/claude-for-research · claude/skills/esmfold2/SKILL.md · Predict quick protein structures with ESMFold-style workflows. Use when a task needs fast MSA-free folding, sequence…
git:20261014.9f2a5e0 · audit A · 10 stars
evo2 SKILL.md skill
yichen-zju/claude-for-research · claude/skills/evo2/SKILL.md · Use Evo2-style biological sequence models for generation, scoring, or variant-effect analysis. Use when a task asks…
git:20261014.9f2a5e0 · audit A · 10 stars
experiment-forge SKILL.md skill
yichen-zju/claude-for-research · claude/skills/experiment-forge/SKILL.md · Forge self-contained experiment packages with code, configs and runbooks from a task description; use when launching or…
git:20261014.9f2a5e0 · audit A · 10 stars
experiment-queue SKILL.md skill
yichen-zju/claude-for-research · claude/skills/experiment-queue/SKILL.md · SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and…
git:20261014.9f2a5e0 · audit A · 10 stars
experiment-watchdog SKILL.md skill
yichen-zju/claude-for-research · claude/skills/experiment-watchdog/SKILL.md · Server-side watchdog daemon that monitors registered training/download/loop tasks and surfaces DEAD/STALLED/IDLE…
git:20261014.9f2a5e0 · audit A · 10 stars
fair-esm2 SKILL.md skill
yichen-zju/claude-for-research · claude/skills/fair-esm2/SKILL.md · Use ESM2 protein language models for embeddings, mutation scoring, remote homology, or representation analysis. Use…
git:20261014.9f2a5e0 · audit A · 10 stars
figure-composer SKILL.md skill
yichen-zju/claude-for-research · claude/skills/figure-composer/SKILL.md · Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task…
git:20261014.9f2a5e0 · audit A · 10 stars
figure-style SKILL.md skill
yichen-zju/claude-for-research · claude/skills/figure-style/SKILL.md · Apply scientific plotting and figure-quality rules to a single plot or panel. Use when drawing, cleaning, labeling, or…
git:20261014.9f2a5e0 · audit A · 10 stars
optimizing-attention-flash SKILL.md skill
yichen-zju/claude-for-research · claude/skills/flash-attention/SKILL.md · Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when…
v1.0.0 · audit A · 10 stars
gguf-quantization SKILL.md skill
yichen-zju/claude-for-research · claude/skills/gguf/SKILL.md · GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware…
v1.0.0 · audit A · 10 stars
gptq SKILL.md skill
yichen-zju/claude-for-research · claude/skills/gptq/SKILL.md · Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on…
v1.0.0 · audit A · 10 stars
grpo-rl-training SKILL.md skill
yichen-zju/claude-for-research · claude/skills/grpo-rl-training/SKILL.md · Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
v1.0.0 · audit A · 10 stars
hqq-quantization SKILL.md skill
yichen-zju/claude-for-research · claude/skills/hqq/SKILL.md · Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision…
v1.0.0 · audit A · 10 stars
idea-evaluator SKILL.md skill
yichen-zju/claude-for-research · claude/skills/idea-evaluator/SKILL.md · Evaluates a preliminary research idea against a five-dimension framework (Higher, Faster, Stronger, Cheaper, Broader)…
git:20261014.9f2a5e0 · audit A · 10 stars
indication-dossier SKILL.md skill
yichen-zju/claude-for-research · claude/skills/indication-dossier/SKILL.md · Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target…
git:20261014.9f2a5e0 · audit A · 10 stars
intro-drafter SKILL.md skill
yichen-zju/claude-for-research · claude/skills/intro-drafter/SKILL.md · Drafts a 6-paragraph Introduction outline for a technical paper from a structured Flowchart: background and running…
git:20261014.9f2a5e0 · audit A · 10 stars
jobs SKILL.md skill
yichen-zju/claude-for-research · claude/skills/jobs/SKILL.md · Inspect visible research run state, scheduled research follow-ups, and durable watch/autoresearch/replication…
git:20261014.9f2a5e0 · audit A · 10 stars
knowledge-distillation SKILL.md skill
yichen-zju/claude-for-research · claude/skills/knowledge-distillation/SKILL.md · Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller…
v1.0.0 · audit A · 10 stars
ligandmpnn SKILL.md skill
yichen-zju/claude-for-research · claude/skills/ligandmpnn/SKILL.md · Design protein sequences around ligand or small-molecule contexts with LigandMPNN-style workflows. Use when a task asks…
git:20261014.9f2a5e0 · audit A · 10 stars
literature-review SKILL.md skill
yichen-zju/claude-for-research · claude/skills/literature-review/SKILL.md · Run a literature review using paper search and primary-source synthesis. Use when the user asks for a lit review, paper…
git:20261014.9f2a5e0 · audit A · 10 stars
implementing-llms-litgpt SKILL.md skill
yichen-zju/claude-for-research · claude/skills/litgpt/SKILL.md · Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen…
v1.0.0 · audit A · 10 stars
llama-factory SKILL.md skill
yichen-zju/claude-for-research · claude/skills/llama-factory/SKILL.md · Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal…
v1.0.0 · audit A · 10 stars
llava SKILL.md skill
yichen-zju/claude-for-research · claude/skills/llava/SKILL.md · Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP…
v1.0.0 · audit A · 10 stars
evaluating-llms-harness SKILL.md skill
yichen-zju/claude-for-research · claude/skills/lm-evaluation-harness/SKILL.md · Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking…
v1.0.0 · audit A · 10 stars
long-context SKILL.md skill
yichen-zju/claude-for-research · claude/skills/long-context/SKILL.md · Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when…
v1.0.0 · audit A · 10 stars
managed-model-endpoints SKILL.md skill
yichen-zju/claude-for-research · claude/skills/managed-model-endpoints/SKILL.md · Register or audit managed model endpoints. Use when a research workflow needs a local or remote model service, endpoint…
git:20261014.9f2a5e0 · audit A · 10 stars
training-llms-megatron SKILL.md skill
yichen-zju/claude-for-research · claude/skills/megatron-core/SKILL.md · Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use…
v1.0.0 · audit A · 10 stars
ml-paper-writing SKILL.md skill
yichen-zju/claude-for-research · claude/skills/ml-paper-writing/SKILL.md · Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research…
v1.2.0 · audit A · 10 stars
ml-training-recipe SKILL.md skill
yichen-zju/claude-for-research · claude/skills/ml-training-recipe/SKILL.md · Find ranked, implementable ML training recipes backed by papers, datasets, docs, and code. Use when the user asks how…
git:20261014.9f2a5e0 · audit A · 10 stars
mlflow SKILL.md skill
yichen-zju/claude-for-research · claude/skills/mlflow/SKILL.md · Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments…
v1.0.0 · audit B · 10 stars
modal-compute SKILL.md skill
yichen-zju/claude-for-research · claude/skills/modal-compute/SKILL.md · Run explicitly chosen research benchmark or replication jobs on Modal's serverless infrastructure. Use when a research…
git:20261014.9f2a5e0 · audit A · 10 stars
model-pruning SKILL.md skill
yichen-zju/claude-for-research · claude/skills/model-pruning/SKILL.md · Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models…
v1.0.0 · audit A · 10 stars
moe-training SKILL.md skill
yichen-zju/claude-for-research · claude/skills/moe-training/SKILL.md · Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited…
v1.0.0 · audit A · 10 stars
monitor-experiment SKILL.md skill
yichen-zju/claude-for-research · claude/skills/monitor-experiment/SKILL.md · Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done"…
git:20261014.9f2a5e0 · audit A · 10 stars
nanogpt SKILL.md skill
yichen-zju/claude-for-research · claude/skills/nanogpt/SKILL.md · Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning…
v1.0.0 · audit A · 10 stars
nemo-evaluator-sdk SKILL.md skill
yichen-zju/claude-for-research · claude/skills/nemo-evaluator/SKILL.md · Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend…
v1.0.0 · audit A · 10 stars
openfold3 SKILL.md skill
yichen-zju/claude-for-research · claude/skills/openfold3/SKILL.md · Run or plan OpenFold3-style structure prediction workflows. Use when a task asks for open protein or complex…
git:20261014.9f2a5e0 · audit A · 10 stars
openrlhf-training SKILL.md skill
yichen-zju/claude-for-research · claude/skills/openrlhf/SKILL.md · High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models…
v1.0.0 · audit B · 10 stars
paper-code-audit SKILL.md skill
yichen-zju/claude-for-research · claude/skills/paper-code-audit/SKILL.md · Compare a paper's claims against its public codebase and identify mismatches, omissions, and reproducibility risks. Use…
git:20261014.9f2a5e0 · audit A · 10 stars
paper-narrative SKILL.md skill
yichen-zju/claude-for-research · claude/skills/paper-narrative/SKILL.md · Shape the scientific story across a manuscript, abstract, figures, and evidence — choose the main narrative line…
git:20261014.9f2a5e0 · audit A · 10 stars
paper-production SKILL.md skill
yichen-zju/claude-for-research · claude/skills/paper-production/SKILL.md · End-to-end paper production pipeline fusing the best writing skills — idea gate (idea-evaluator), skeleton…
git:20261014.9f2a5e0 · audit A · 10 stars
paper-writing SKILL.md skill
yichen-zju/claude-for-research · claude/skills/paper-writing/SKILL.md · Turn research findings into a polished paper-style draft with sections, equations, and citations. Use when the user…
git:20261014.9f2a5e0 · audit A · 10 stars
pdf-explore SKILL.md skill
yichen-zju/claude-for-research · claude/skills/pdf-explore/SKILL.md · Read, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables…
git:20261014.9f2a5e0 · audit A · 10 stars
peft-fine-tuning SKILL.md skill
yichen-zju/claude-for-research · claude/skills/peft/SKILL.md · Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B)…
v1.0.0 · audit A · 10 stars
pre-submission-reviewer SKILL.md skill
yichen-zju/claude-for-research · claude/skills/pre-submission-reviewer/SKILL.md · Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English…
git:20261014.9f2a5e0 · audit A · 10 stars
presenting-conference-talks SKILL.md skill
yichen-zju/claude-for-research · claude/skills/presenting-conference-talks/SKILL.md · Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes…
v1.0.0 · audit A · 10 stars
preview SKILL.md skill
yichen-zju/claude-for-research · claude/skills/preview/SKILL.md · Preview or export Markdown, PDF, HTML, or code artifacts using shell/browser tools. Use when the user wants to review a…
git:20261014.9f2a5e0 · audit A · 10 stars
evolving-ai-agents SKILL.md skill
yichen-zju/claude-for-research · skills/a-evolve/SKILL.md · Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution…
v1.0.0 · audit A · 10 stars
academic-plotting SKILL.md skill
yichen-zju/claude-for-research · skills/academic-plotting/SKILL.md · Generates publication-quality figures for ML papers from research context. Given a paper section or description…
v1.0.0 · audit A · 10 stars
academic-research-suite SKILL.md skill
yichen-zju/claude-for-research · skills/academic-research-suite/SKILL.md · Claude-native Academic Research Skills suite (ported from the Codex adapter) for deep research, academic paper writing…
v0.1.14 · audit A · 10 stars
huggingface-accelerate SKILL.md skill
yichen-zju/claude-for-research · skills/accelerate/SKILL.md · Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for…
v1.0.0 · audit A · 10 stars
ai-use-disclosure SKILL.md skill
yichen-zju/claude-for-research · skills/ai-use-disclosure/SKILL.md · Generate venue-specific AI-use disclosure statements for manuscript submission (ICLR, NeurIPS, ICML, Nature, Science…
git:20261001.fde7ef9 · audit A · 10 stars
alpha-research SKILL.md skill
yichen-zju/claude-for-research · skills/alpha-research/SKILL.md · Search, read, and query research papers via the alphaxiv MCP server (2.5M+ arXiv papers). Use when the user asks about…
git:20260930.9b33ccf · audit A · 10 stars
alphafold2 SKILL.md skill
yichen-zju/claude-for-research · skills/alphafold2/SKILL.md · Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer…
git:20260930.9b33ccf · audit A · 10 stars
anti-defensive-writing-en SKILL.md skill
yichen-zju/claude-for-research · skills/anti-defensive-writing-en/SKILL.md · Stops defensive writing across the entire paper lifecycle — writing, revising, cutting, and organizing experiments…
git:20261001.fde7ef9 · audit A · 10 stars
anti-defensive-writing SKILL.md skill
yichen-zju/claude-for-research · skills/anti-defensive-writing/SKILL.md · 论文写作、修改、压缩和实验组织全流程中阻止【防御性写作】。把论文视为一场学术发布会， 而不是项目总结、实验日志或自我审查报告：识别这项工作最值得发表的价值，围绕它建立…
git:20261001.fde7ef9 · audit A · 10 stars
autoresearch SKILL.md skill
yichen-zju/claude-for-research · skills/autoresearch/SKILL.md · Autonomous experiment loop with evidence-driven move selection — scales from parameter tuning (directional search) to…
git:20261008.414312a · audit A · 10 stars
awq-quantization SKILL.md skill
yichen-zju/claude-for-research · skills/awq/SKILL.md · Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when…
v1.0.0 · audit A · 10 stars
benchmark-paper-template SKILL.md skill
yichen-zju/claude-for-research · skills/benchmark-paper-template/SKILL.md · Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline…
git:20261001.fde7ef9 · audit A · 10 stars
quantizing-models-bitsandbytes SKILL.md skill
yichen-zju/claude-for-research · skills/bitsandbytes/SKILL.md · Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is…
v1.0.0 · audit A · 10 stars
blip-2-vision-language SKILL.md skill
yichen-zju/claude-for-research · skills/blip-2/SKILL.md · Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning…
v1.0.0 · audit A · 10 stars
boltz SKILL.md skill
yichen-zju/claude-for-research · skills/boltz/SKILL.md · Run or plan Boltz biomolecular structure predictions for proteins, complexes, ligands, or nucleic-acid assemblies. Use…
git:20260930.9b33ccf · audit A · 10 stars
borzoi SKILL.md skill
yichen-zju/claude-for-research · skills/borzoi/SKILL.md · Use Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task…
git:20260930.9b33ccf · audit A · 10 stars
brainstorming-research-ideas SKILL.md skill
yichen-zju/claude-for-research · skills/brainstorming-research-ideas/SKILL.md · Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when…
v1.0.0 · audit A · 10 stars
chai1 SKILL.md skill
yichen-zju/claude-for-research · skills/chai1/SKILL.md · Run or prepare Chai-1 structure predictions for biomolecular complexes. Use when a task asks for Chai-1 inputs…
git:20260930.9b33ccf · audit A · 10 stars
clip SKILL.md skill
yichen-zju/claude-for-research · skills/clip/SKILL.md · OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and…
v1.0.0 · audit A · 10 stars
compute-env-setup SKILL.md skill
yichen-zju/claude-for-research · skills/compute-env-setup/SKILL.md · Set up a reproducible compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries…
git:20260930.9b33ccf · audit A · 10 stars
contributing SKILL.md skill
yichen-zju/claude-for-research · skills/contributing/SKILL.md · Maintain and improve this Claude Code research environment — its skills, subagents, conventions, and workflows. Use…
git:20260930.9b33ccf · audit A · 10 stars
creative-thinking-for-research SKILL.md skill
yichen-zju/claude-for-research · skills/creative-thinking-for-research/SKILL.md · Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely…
v1.0.0 · audit A · 10 stars
customize SKILL.md skill
yichen-zju/claude-for-research · skills/customize/SKILL.md · Configure this Claude Code research environment — skills, subagents, permissions, hooks, compute providers, and project…
git:20260930.9b33ccf · audit A · 10 stars
deep-research SKILL.md skill
yichen-zju/claude-for-research · skills/deep-research/SKILL.md · Run a thorough, source-heavy investigation on any topic. Use when the user asks for deep research, a comprehensive…
git:20261010.1788eea · audit A · 10 stars
deepspeed SKILL.md skill
yichen-zju/claude-for-research · skills/deepspeed/SKILL.md · Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism…
v1.0.0 · audit A · 10 stars
diffdock SKILL.md skill
yichen-zju/claude-for-research · skills/diffdock/SKILL.md · Run or plan DiffDock molecular docking workflows. Use when a task asks for protein-ligand pose prediction, docking…
git:20260930.9b33ccf · audit A · 10 stars
docker SKILL.md skill
yichen-zju/claude-for-research · skills/docker/SKILL.md · Execute research code inside isolated Docker containers for safe replication, experiments, and benchmarks. Use when the…
git:20260930.9b33ccf · audit A · 10 stars
eli5 SKILL.md skill
yichen-zju/claude-for-research · skills/eli5/SKILL.md · Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear…
git:20260930.9b33ccf · audit A · 10 stars
esmfold2 SKILL.md skill
yichen-zju/claude-for-research · skills/esmfold2/SKILL.md · Predict quick protein structures with ESMFold-style workflows. Use when a task needs fast MSA-free folding, sequence…
git:20260930.9b33ccf · audit A · 10 stars
evo2 SKILL.md skill
yichen-zju/claude-for-research · skills/evo2/SKILL.md · Use Evo2-style biological sequence models for generation, scoring, or variant-effect analysis. Use when a task asks…
git:20260930.9b33ccf · audit A · 10 stars
experiment-forge SKILL.md skill
yichen-zju/claude-for-research · skills/experiment-forge/SKILL.md · Forge self-contained experiment packages with code, configs and runbooks from a task description; use when launching or…
git:20261012.70e1643 · audit A · 10 stars
experiment-queue SKILL.md skill
yichen-zju/claude-for-research · skills/experiment-queue/SKILL.md · SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and…
git:20261003.4f702ed · audit A · 10 stars
experiment-watchdog SKILL.md skill
yichen-zju/claude-for-research · skills/experiment-watchdog/SKILL.md · Server-side watchdog daemon that monitors registered training/download/loop tasks and surfaces DEAD/STALLED/IDLE…
git:20260930.9b33ccf · audit A · 10 stars
fair-esm2 SKILL.md skill
yichen-zju/claude-for-research · skills/fair-esm2/SKILL.md · Use ESM2 protein language models for embeddings, mutation scoring, remote homology, or representation analysis. Use…
git:20260930.9b33ccf · audit A · 10 stars
figure-composer SKILL.md skill
yichen-zju/claude-for-research · skills/figure-composer/SKILL.md · Compose a publication-grade multi-panel scientific figure from a claim, dataset, or draft result. Use when the task…
git:20260930.9b33ccf · audit A · 10 stars
figure-style SKILL.md skill
yichen-zju/claude-for-research · skills/figure-style/SKILL.md · Apply scientific plotting and figure-quality rules to a single plot or panel. Use when drawing, cleaning, labeling, or…
git:20260930.9b33ccf · audit A · 10 stars
optimizing-attention-flash SKILL.md skill
yichen-zju/claude-for-research · skills/flash-attention/SKILL.md · Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when…
v1.0.0 · audit A · 10 stars
gguf-quantization SKILL.md skill
yichen-zju/claude-for-research · skills/gguf/SKILL.md · GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware…
v1.0.0 · audit A · 10 stars
gptq SKILL.md skill
yichen-zju/claude-for-research · skills/gptq/SKILL.md · Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on…
v1.0.0 · audit A · 10 stars
grpo-rl-training SKILL.md skill
yichen-zju/claude-for-research · skills/grpo-rl-training/SKILL.md · Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
v1.0.0 · audit A · 10 stars
hqq-quantization SKILL.md skill
yichen-zju/claude-for-research · skills/hqq/SKILL.md · Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision…
v1.0.0 · audit A · 10 stars
idea-evaluator SKILL.md skill
yichen-zju/claude-for-research · skills/idea-evaluator/SKILL.md · Evaluates a preliminary research idea against a five-dimension framework (Higher, Faster, Stronger, Cheaper, Broader)…
git:20261012.70e1643 · audit A · 10 stars
indication-dossier SKILL.md skill
yichen-zju/claude-for-research · skills/indication-dossier/SKILL.md · Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target…
git:20260930.9b33ccf · audit A · 10 stars
intro-drafter SKILL.md skill
yichen-zju/claude-for-research · skills/intro-drafter/SKILL.md · Drafts a 6-paragraph Introduction outline for a technical paper from a structured Flowchart: background and running…
git:20261009.6afbfc0 · audit A · 10 stars
jobs SKILL.md skill
yichen-zju/claude-for-research · skills/jobs/SKILL.md · Inspect visible research run state, scheduled research follow-ups, and durable watch/autoresearch/replication…
git:20260930.9b33ccf · audit A · 10 stars
knowledge-distillation SKILL.md skill
yichen-zju/claude-for-research · skills/knowledge-distillation/SKILL.md · Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller…
v1.0.0 · audit A · 10 stars
ligandmpnn SKILL.md skill
yichen-zju/claude-for-research · skills/ligandmpnn/SKILL.md · Design protein sequences around ligand or small-molecule contexts with LigandMPNN-style workflows. Use when a task asks…
git:20260930.9b33ccf · audit A · 10 stars
literature-review SKILL.md skill
yichen-zju/claude-for-research · skills/literature-review/SKILL.md · Run a literature review using paper search and primary-source synthesis. Use when the user asks for a lit review, paper…
git:20261012.70e1643 · audit A · 10 stars
implementing-llms-litgpt SKILL.md skill
yichen-zju/claude-for-research · skills/litgpt/SKILL.md · Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen…
v1.0.0 · audit A · 10 stars
Source
github.com/yichen-zju/claude-for-research · 10 stars · license none · pushed 2026-10-21