All authors
Claude Skills by Yichen-ZJU
github.com/Yichen-ZJU93 skills1 installs89 views
- Academic Research SuiteClaude-native Academic Research Skills suite (ported from the Codex adapter) for deep research, academic paper writing, manuscript review, full research-to-paper pipelines, and experiment planning or validation. Use when the user asks for deep research, literature review, systematic review, meta-analysis, research question refinement, academic paper drafting, paper revision, citation or integrity checks, reviewer simulation, peer review, editorial decision letters, research-to-paper workflows...Votes: 0GitHub stars: 9
- Ai Use DisclosureGenerate venue-specific AI-use disclosure statements for manuscript submission (ICLR, NeurIPS, ICML, Nature, Science, ACL/EMNLP) plus a human-AI collaboration process record. Use when finalizing a paper, when the venue requires an LLM/AI usage statement, or when the user asks about AI disclosure compliance.Votes: 0GitHub stars: 9
- Alpha ResearchSearch, read, and query research papers via the alphaxiv MCP server (2.5M+ arXiv papers). Use when the user asks about academic papers, wants to find research on a topic, needs to read a specific paper, ask questions about a paper, or inspect a paper's code repository.Votes: 0GitHub stars: 9
- Alphafold2Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer structure prediction, MSA/template handling, confidence metrics, or comparison against PDB/AlphaFold references.Votes: 0GitHub stars: 9
- AutoresearchAutonomous experiment loop with evidence-driven move selection — scales from parameter tuning (directional search) to architecture innovation (structural changes), with git ledger, guard, noise-aware keep/discard, and trend-analysis stop advice. Use when the user asks to optimize a research metric, run an experiment loop, tune hyperparameters, explore architectural changes, or improve model performance iteratively.Votes: 0GitHub stars: 9
- Benchmark Paper TemplateStructures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when writing a benchmark paper, structuring a benchmark paper, checking whether a benchmark idea is substantive, drafting a benchmark Introduction, or planning the data-construction pipel...Votes: 0GitHub stars: 9
- BoltzRun or plan Boltz biomolecular structure predictions for proteins, complexes, ligands, or nucleic-acid assemblies. Use when a task asks for Boltz setup, inputs, outputs, confidence interpretation, or reproduction.Votes: 0GitHub stars: 9
- BorzoiUse Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task asks for noncoding variant impact, regulatory sequence design, or expression prediction.Votes: 0GitHub stars: 9
- Chai1Run or prepare Chai-1 structure predictions for biomolecular complexes. Use when a task asks for Chai-1 inputs, multimers, ligand/nucleic acid structure prediction, or confidence review.Votes: 0GitHub stars: 9
- Compute Env SetupSet up a reproducible compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.Votes: 0GitHub stars: 9
- ContributingMaintain and improve this Claude Code research environment — its skills, subagents, conventions, and workflows. Use when the task is to add, fix, or refactor research capabilities in ~/.claude/.Votes: 0GitHub stars: 9
- CustomizeConfigure this Claude Code research environment — skills, subagents, permissions, hooks, compute providers, and project setup. Use when the task asks to customize the research setup or create a reusable research capability.Votes: 0GitHub stars: 9
- Deep ResearchRun a thorough, source-heavy investigation on any topic. Use when the user asks for deep research, a comprehensive analysis, an in-depth report, or a multi-source investigation. Produces a cited research brief with provenance tracking.Votes: 0GitHub stars: 9
- DiffdockRun or plan DiffDock molecular docking workflows. Use when a task asks for protein-ligand pose prediction, docking setup, ligand/protein preparation, pose ranking, or docking-result verification.Votes: 0GitHub stars: 9
- DockerExecute research code inside isolated Docker containers for safe replication, experiments, and benchmarks. Use when the user selects Docker as the execution environment or asks to run code safely, in isolation, or in a sandbox.Votes: 0GitHub stars: 9
- Eli5Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.Votes: 0GitHub stars: 9
- Experiment Forge``` <task-dir>/ ├── prepare.py # 🔒 锁定：数据准备、tokenizer/dataloader、评估函数。agent 禁止修改 ├── train.py # 🔓 开放：agent 唯一可编辑的文件（模型、优化器、训练循环、超参） ├── program.md # 🧭 人类可迭代：给 agent 的研究组织指令（用 templates/program.md 生成） ├── pyproject.toml # 依赖清单 —— agent 禁止新增依赖 └── results.tsv # 实验台账（表头由 forge 生成，agent 追加行，不提交 git） ```Votes: 0GitHub stars: 9
- Experiment QueueSSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "队列实验", "run grid", "multi-seed sweep", "auto-chain experiments", or when /run-experiment is insufficient for 10+ jobs that need orchestration.Votes: 0GitHub stars: 9
- Experiment WatchdogServer-side watchdog daemon that monitors registered training/download/loop tasks and surfaces DEAD/STALLED/IDLE anomalies. Use when running unattended or overnight experiments and you want silent deaths or stalls to be detected instead of discovered hours later. Wraps the ARIS watchdog.py (stdlib-only).Votes: 0GitHub stars: 9
- Idea EvaluatorEvaluates a preliminary research idea against a five-dimension framework (Higher, Faster, Stronger, Cheaper, Broader) plus idea-lifecycle and student-capability matching, paradigm-shift probing, and a fatal-flaws audit. Returns a reviewer-style verdict. Use when the user has a draft research idea and asks whether it is worth pursuing, asks to 'evaluate this idea', 'score this idea', 'assess feasibility', 'novelty check', 'is this a good research direction', or before committing to a paper scope.Votes: 0GitHub stars: 9
- Indication DossierBuild a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.Votes: 0GitHub stars: 9
- Intro DrafterDrafts a 6-paragraph Introduction outline for a technical paper from a structured Flowchart: background and running example, existing limitations, problem essence and goal, key challenges, solution overview, contributions. Positions the paper as Technique or New Problem/Setting and aligns contributions with challenges. Use when the user asks to 'draft the Introduction', 'outline the Introduction', 'intro logic needs clarifying', 'help structure the paper story', or before writing any Introduc...Votes: 0GitHub stars: 9
- JobsInspect visible research run state, scheduled research follow-ups, and durable watch/autoresearch/replication artifacts. Use when the user asks what research runs are active, what is scheduled, or what state previous runs left behind.Votes: 0GitHub stars: 9
- Literature ReviewRun a literature review using paper search and primary-source synthesis. Use when the user asks for a lit review, paper survey, state of the art, publication-corpus review of a lab/PI/author, or academic landscape summary on a research topic.Votes: 0GitHub stars: 9
- Managed Model EndpointsRegister or audit managed model endpoints. Use when a research workflow needs a local or remote model service, endpoint health checks, credential refs, startup scripts, or inference routing.Votes: 0GitHub stars: 9
- Ml Training RecipeFind ranked, implementable ML training recipes backed by papers, datasets, docs, and code. Use when the user asks how to train/fine-tune a model for a task, wants a benchmark-backed recipe, or needs dataset + hyperparameter + code grounding for an ML method.Votes: 0GitHub stars: 9
- Modal ComputeRun explicitly chosen research benchmark or replication jobs on Modal's serverless infrastructure. Use when a research workflow needs burst remote GPU compute and the Modal CLI is available.Votes: 0GitHub stars: 9
- Monitor ExperimentMonitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.Votes: 0GitHub stars: 9
- Paper Code AuditCompare a paper's claims against its public codebase and identify mismatches, omissions, and reproducibility risks. Use when the user asks to audit a paper's code, check whether a repo matches its paper, or assess reproducibility of published work.Votes: 0GitHub stars: 9
- Paper ProductionEnd-to-end paper production pipeline fusing the best writing skills — idea gate (idea-evaluator), skeleton (tech/benchmark-paper-template), Introduction logic chain (intro-drafter), evidence arc (paper-narrative), figure design (figure-style/figure-composer/academic-plotting), drafting with citations (paper-writing + ml-paper-writing venue templates), dual review (reviewer agent + pre-submission-reviewer). Use when the user wants to write a paper from research results, structure a manuscript ...Votes: 0GitHub stars: 9
- Paper WritingTurn research findings into a polished paper-style draft with sections, equations, and citations. Use when the user asks to write a paper, draft a report, write up findings, or produce a technical document from collected research.Votes: 0GitHub stars: 9
- Pdf ExploreRead, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables, citations, accessions, or claims from multiple places in one or more papers.Votes: 0GitHub stars: 9
- Pre Submission ReviewerRuns a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality. Uses a reviewer-style severity taxonomy (CRITICAL / MAJOR / MINOR) and flags banned AI-tone vocabulary and em-dash misuse. Use when the user asks to 'review this paper', 'audit before submission', 'check the draft', 'find issues', 'proofread', or within one week of a submission deadline.Votes: 0GitHub stars: 9
- PreviewPreview or export Markdown, PDF, HTML, or code artifacts using shell/browser tools. Use when the user wants to review a written artifact, export a report, or view a rendered document.Votes: 0GitHub stars: 9
- Product Self KnowledgeAnswer questions about this Claude Code research environment itself — what skills, agents, tools, and settings exist and how they are wired. Use when a response would claim what the environment can do.Votes: 0GitHub stars: 9
- Remote Compute ModalDispatch research notebook or experiment jobs to Modal. Use when a task has explicitly chosen Modal for bounded cloud compute, GPU jobs, or reproducible remote execution.Votes: 0GitHub stars: 9
- Remote Compute SshRun research jobs on SSH, Slurm, or lab hosts. Use when a task needs remote host setup, job submission, log harvest, artifact sync, or GPU/cluster execution outside Modal.Votes: 0GitHub stars: 9
- ReplicationPlan a replication of a paper, claim, or benchmark, and execute only after an explicit environment choice. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.Votes: 0GitHub stars: 9
- Research OrchestratorOrchestrate an end-to-end autonomous research project (idea → experiments → paper) with a two-loop architecture — inner loop runs experiments, outer loop synthesizes findings and steers direction. Use when starting a research project, running a multi-hypothesis autonomous research effort, or resuming an ongoing project with research-state.yaml. Routes execution to domain skills (fine-tuning, distributed training, evaluation, ...) and process skills (literature-review, experiment-forge, autore...Votes: 0GitHub stars: 9
- Research ReviewRun an internal research critique with likely objections, severity, and a concrete revision plan. Use when the user asks to review a paper, preprint, draft, or research artifact — their own or someone else's.Votes: 0GitHub stars: 9
- Run ExperimentDeploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.Votes: 0GitHub stars: 9
- Runpod ComputeProvision and manage GPU pods on RunPod for explicitly chosen long-running research experiments. Use when a replication, benchmark, or dataset-heavy research run needs persistent GPU compute with SSH access.Votes: 0GitHub stars: 9
- Scvi ToolsRun scvi-tools single-cell workflows. Use when a task asks for scVI/scANVI setup, latent embeddings, batch correction, differential expression, cell annotation, or reproducible AnnData analysis.Votes: 0GitHub stars: 9
- Self AwarenessInspect the active research session state — artifacts written, plans, execution state, and provenance. Use when the task asks what happened in this session, which files were written, what ran, or what remains unverified.Votes: 0GitHub stars: 9
- Session LogWrite a durable session log with completed work, findings, open questions, and next steps. Use when the user asks to log the session, write a lab notebook entry, or record what was done.Votes: 0GitHub stars: 9
- Session SearchRecover prior work from Claude Code session transcripts. Use when the user asks to find something from a previous session, resume earlier research, or recall what was decided.Votes: 0GitHub stars: 9
- Skill CreatorCreate or revise Claude Code research skills in ~/.claude/skills/. Use when a research workflow needs a reusable on-demand capability, skill metadata, trigger wording, references, or skill validation.Votes: 0GitHub stars: 9
- Source ComparisonCompare multiple sources on a topic and produce a source-grounded matrix of agreements, disagreements, and confidence. Use when the user asks to compare papers, methods, tools, models, or claims across sources.Votes: 0GitHub stars: 9
- Style CalibrationLearn the author's natural writing voice from their past papers and apply it as a soft guide when drafting new text. Use when drafting or polishing paper sections and the user wants the text to sound like their own writing, or when a Style Profile should be built/refreshed from writing samples. Personalization, not de-AI-ification.Votes: 0GitHub stars: 9
- Sudis Arr Rebuttal With MeUse for ACL Rolling Review (ARR) author responses, reviewer discussion, ARR review-issue reports, resubmission notes, and commitment planning. Load the general sudis-rebuttal-with-me skill first, then apply this ARR-specific overlay.Votes: 0GitHub stars: 9