Best agent skills for researchers, page 13

Repairs one failing section of a mathematical modeling paper from the repair queue, or builds a legacy or quickstart scaffold when you ask for one by name.

yushui2022/MathModel-Skill

Search for scientific papers, preprints, and publications on arXiv.

google-deepmind/science-skills

A skill your agent uses when the user has a vague research direction and wants to explore feasible specific topics.

ai4s-research/ai4s-skills

Supplies venue-specific LaTeX templates and formatting rules for journals, conferences and posters, and checks a manuscript against page limits and submission requirements.

foryourhealth111-pixel/Vibe-Skills

A skill your agent uses when interpreting genomic variants from VCF files, performing clinical variant classification using ClinVar/VEP annotations, analyzing allele frequencies against population…

aws-samples/amazon-bedrock-agents-healthcare-lifesciences

Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication.

inbrainfun/inbrain

Build an OKF (Open Knowledge Format) knowledge base from any YouTube channel.

coleam00/cole-medin-knowledge-base

View, search, and download academic papers from arXiv. An agent skill from actionbook/actionbook.

actionbook/actionbook

Read Tlon activity and message history; manage workspaces (Tlon groups), channels, Markdown notes, shared Bucket files, contacts, profiles, settings, and channel hooks; expose content publicly; send…

tloncorp/tlon-apps

A skill your agent uses when the task is to review an academic paper PDF from the repo input folder, run specialized auditors, and compile a final report.

Ingar30/reviewer

AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.

nanoAgentTeam/research-claw

Monitor running AlphaEvolve experiments, run the evaluation control loop, and report results using the ae CLI.

Google-Cloud-AI/alphaevolve-on-googlecloud

Work with Obsidian vaults using the official obsidian CLI: read/search/create/edit notes, tasks, links, properties, plugins.

openclaw/openclaw

Build an interactive learning board on any topic. An agent skill from raiyanyahya/Superlearn.

raiyanyahya/Superlearn

Guideline-authoring craft for instruction SoTs (.claude/ guides, CLAUDE.md, plan files) — operative rules vs recital, MUST/SHOULD/MAY force tiers, pruning, bloat control, blind review protocol…

alfadur7/llm-wiki-newsroom

A skill your agent uses when performing research for AppsFlyer Flutter Plugin — investigating platform APIs, version behavior, external docs, or any externally-controlled surface that affects…

AppsFlyerSDK/appsflyer-flutter-plugin

A skill your agent uses when a clinical CSV/Excel dataset needs profiling and cleaning before analysis (missing values, outliers, duplicates, type mismatches).

Aperivue/medsci-skills

Build reproducible radiology bibliometrics with corpus identity, disambiguation and sensitivity; not reviews.

huang-sir1/radiology-skills

Guides training and analyzing sparse autoencoders with SAELens to break neural network activations into interpretable features, including superposition and monosemanticity studies.

Orchestra-Research/AI-Research-SKILLs

Draft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions.

Galaxy-Dawn/claude-scholar

Capture-authoring protocol for the main agent. An agent skill from toolboxmd/karpathy-wiki.

toolboxmd/karpathy-wiki

Runs a staged pipeline for mathematical modeling research and contest papers, from problem analysis and computation to paper writing, review rounds and submission checks.

WuXinbo-bo/Math-model-skills

Audits, scaffolds and safely migrates research project folder structures, keeping existing repositories read-only until you approve exact moves from a plan.

Light0305/Light-skills

Orchestrates a Claude↔Codex cycle where Claude Code designs the contract and arbitrates, while Codex by default (via the official openai/codex-plugin-cc plugin) writes, adversarially reviews, and…

Ranteck/graph-engineer

股票投资调研执行引擎，执行8阶段投资尽调流程。接收stock-question-refiner生成的结构化调研指令，部署多智能体并行研究，生成带引用的投资尽调报告。覆盖：公司事实底座、行业周期、业务拆解、财务质量、股权治理、市场分歧、估值护城河、综合报告。当用户需要进行股票投资研究、基本面分析、投资尽调时使用此技能。

liangdabiao/Claude-Code-Stock-Deep-Research-Agent

论文深度解读 Skill — 下载论文PDF → LLM深度解读（问题/创新点/方法原理/实验分析）→ PDF图片提取 → 生成组会PPT → 生成解读音频MP3。端到端学术论文解读工具。

RapidAI/MaClaw

Analyzes reviewer comments and drafts venue-specific rebuttals for AI and computer science conferences, with an issue board, task list and paper edit plan.

OpenLAIR/dr-claw

Runs a branch-parallel research pipeline with declared sufficiency per subquestion, deterministic stop and citation checks, and a separate model for verification.

AnkitClassicVision/Claude-Code-Deep-Research

Scans an Obsidian-style wiki for broken double-link references, orphan pages, files missing from the index and unresolved knowledge conflicts, then reports the findings.

jason-effi-lab/karpathy-llm-wiki-vault

Summarize recent hot academic papers using deepxiv trending, brief, head, and section reads, then produce a markdown digest highlighting what each paper is about and which papers deserve deeper…

DeepXiv/deepxiv_sdk

Compile personal data (journals, notes, messages, tweets) into a personal knowledge wiki.

kothari-nikunj/llm-wiki

Apply RTDT customization specifically to the shipped auto-aero virtual wind tunnel.

NVIDIA-Omniverse-blueprints/digital-twins-for-fluid-simulation

FHIR API development guide for building healthcare endpoints.

FreedomIntelligence/OpenClaw-Medical-Skills

Explains how to run, integrate and debug the deep-research-mcp project through its CLI, Python API or MCP server, with OpenAI, Gemini and DR-Tulu backends.

pminervini/deep-research-mcp

Creates research posters in LaTeX using beamerposter, tikzposter, or baposter.

K-Dense-AI/scientific-agent-skills

Query the Dev Knowledge Graph via SPARQL instead of grepping raw session files.

robertoshimizu/session-graph

Manage Obsidian vault operations. An agent skill from ravila4/claude-adhd-skills.

ravila4/claude-adhd-skills

Files a specific answer, decision or insight you point to in a conversation as one reviewed note in your Obsidian vault, and only when you ask for it.

AgriciDaniel/claude-obsidian

全自动科研平台：从论文检索、知识图谱构建、研究缺口分析、假设生成，到实验执行、论文写作、自审修正的完整科研流水线。Agent 按此 Skill 的指令自主推进研究流程。触发场景：做研究、搜论文、找研究缺口、生成假设、跑实验、写论文、文献综述、benchmark对比 / Triggers: research, literature review, paper search, hypothesis…

ZS520L/HanakoPro

Quick reference for Biopython work: sequence operations, SeqIO file parsing, BLAST searches, Entrez queries, phylogenetic trees and PDB structure analysis.

aiming-lab/AutoResearchClaw

Builds courses on current or externally checkable topics by researching live sources first, keeping a claim-to-source ledger and grounding every page in what was fetched.

THU-MAIC/OpenMAIC

Workflow for fixing or changing RNAlysis code that talks to an EXTERNAL WEB SERVICE — UniProt, Ensembl, PANTHER, PhylomeDB, OrthoInspector, KEGG, or GO.

GuyTeichman/RNAlysis

Make a demo of a research paper in a marimo notebook fully automatically without extra user input.

marimo-team/skills

Turns uploaded photos, voice notes, text or local files into standardized experiment logs in Markdown with YAML frontmatter, optionally through Feishu CLI and Obsidian.

Yuan1z0825/nature-skills

Runs a daily literature pipeline: multi-source search, six-dimension scoring, fine reading, formatted delivery to a chat channel and archival of the notes.

Yuan1z0825/nature-skills

Cross-checks each academic reference against several sources field by field, flags conflicts such as year, DOI, author order and page errors, and outputs a structured report.

Yuan1z0825/nature-skills

Brief the user on what they saved in a period — the thread running through it, not a list.

Fergana-Labs/stash

Diagnoses a draft Chinese NSFC grant application for the applicant, pointing out logic breaks, weak evidence and high-impact fixes, calibrated to the application year and form.

jiankang1991/nsfc-benzi-audit