{"api_version":"1","slug":"scientific-agent-skills-0f7ca99f","url":"https://skillsoutpost.com/agents/scientific-agent-skills-0f7ca99f","item_type":"skill","category":"research","runs_in":["local_agent"],"os":["macos","linux","windows"],"needs_network":"yes","needs_accounts":null,"reads_files":"yes","writes_files":"yes","sends_data":"yes","access":"github","access_type":"github","at_a_glance":{"runs_in":["local_agent"],"os":["macos","linux","windows"],"needs_network":"yes","needs_accounts":null,"reads_files":"yes","writes_files":"yes","sends_data":"yes","access_type":"github","tool_type":"skill","delivery":"github","interface_type":"other","untrusted_creator_content":{"purpose":"A library of skills that give an AI coding agent documented workflows for science packages, databases, and research tasks.","needs_runtime":"uv","version":"Latest on the main branch","compatibility":"According to the README, the collection works with Cursor, Claude Code, Claude Cowork, Codex, Gemini CLI, Google Antigravity, GitHub Copilot, VS Code, Kiro, OpenClaw, NemoClaw, Pi, Hermes, and other hosts that support the open Agent Skills standard.","external_costs":"The repository is MIT-licensed and states no price for itself. According to the README, individual skills connect to named external databases and services, and its Database Lookup skill documents 80 databases with public, registered, or licensed access; the README does not say which of them need an account or a licence. Each skill lists its own credential and network requirements. The README also says commercial support is available, without prices.","permissions":"The skills act through your coding agent with the access you give it. According to the README, skills can run Python code through packages installed with uv and make network requests to the databases and APIs they document. The README warns that skills can instruct your agent to run arbitrary code, install packages, make network requests and modify files on your system, and says to review what you install. Its steps for installing uv on macOS and Linux pipe a downloaded install script into sh, and its install routes place skill files in your agent's skills folders, for example ~/.agents/skills/.","usage_terms":"MIT License, as stated in the repository. See its LICENSE.md file for the exact terms."}},"interface_type":"other","delivery_mode":"creator","code_host":"github","provenance":"github_index","published_at":1791680769,"rating":null,"downloads":0,"verified":null,"creator":{"login":"K-Dense-AI","url":null},"untrusted_creator_content":{"name":"Scientific Agent Skills","tagline":"A library of skills that give an AI coding agent documented workflows for science packages, databases, and research tasks.","creator_name":"K-Dense-AI","product_version":"Latest on the main branch","needs_runtime":"uv","description":"Scientific Agent Skills is a collection of skills for AI coding agents, created by K-Dense. According to the README, it covers biology, chemistry, medicine, physics, engineering, Earth science, data analysis, and scientific communication, with 177 skills, each documenting the conventions and validation checks for one package, data source, or workflow.\n\nThe README groups the skills by area: bioinformatics and genomics, cheminformatics and drug discovery, proteomics, clinical research, healthcare AI and biosignal research, microscopy and medical imaging, neuroscience, machine learning, materials science, physics and astronomy, engineering and simulation, data analysis and visualization, geospatial science, laboratory automation, scientific communication, multi-omics, protein engineering, and regulatory or standards documentation. A dedicated Database Lookup skill documents access to 80 named scientific and financial databases.\n\nAccording to the README, the agent can already use any Python package or API on its own; these skills add documentation and examples for the ones listed. The README also says it runs weekly LLM-based security scans on the skills in the repository and recommends reading each SKILL.md and scanning a skill yourself before installing it, since community contributions are not all reviewed to the same depth.","intended_users":"Scientists, researchers, and engineers who want an AI coding agent to follow documented workflows for specific scientific packages, databases, or research tasks.","example_tasks":"Query a chemical database for candidate compounds and analyze structure-activity relationships.\nLoad single-cell RNA-seq data and run quality control and cell-type analysis.\nDraft a costed experimental protocol from a planned experiment.\nSearch the literature and generate evidence-bound hypotheses for a research question.\nBuild a publication-quality figure, slide, or poster from a dataset.","setup_instructions":"The README's main route is \"npx skills add K-Dense-AI/scientific-agent-skills\" on a supported host. It also documents installing with the GitHub CLI (\"gh skill install K-Dense-AI/scientific-agent-skills\") and, for Cursor or Codex, loading the repository as an Agent Plugins package. The README has the exact commands.","limitations":"Needs Python 3.13 or later for the repository's own tooling, plus uv as the package manager for skill dependencies; individual skills may support a broader Python range. Needs a host that supports the Agent Skills standard, such as Cursor, Claude Code, Codex, Gemini CLI, or Google Antigravity, per the README. The README lists macOS, Linux, or Windows with WSL2 as the supported systems. It describes its healthcare AI and biosignal skills as research and retrospective validation, not patient-specific diagnosis, treatment, alarms or deployment decisions, and its regulatory and standards skills as drafts prepared for qualified review, not a certification, accreditation or method-release decision. Each skill lists its own package, system-tool, credential, and network requirements separately, and installing the skill files does not install their dependencies. The repository can change at any time; check its README before you install.","data_handling":"The README does not give one data-handling statement for all 177 skills. It says each skill's SKILL.md documents what packages it uses and what external service it connects to, so what is sent where depends on which skill you use and your own coding agent and credentials.","compatibility":"According to the README, the collection works with Cursor, Claude Code, Claude Cowork, Codex, Gemini CLI, Google Antigravity, GitHub Copilot, VS Code, Kiro, OpenClaw, NemoClaw, Pi, Hermes, and other hosts that support the open Agent Skills standard.","external_costs":"The repository is MIT-licensed and states no price for itself. According to the README, individual skills connect to named external databases and services, and its Database Lookup skill documents 80 databases with public, registered, or licensed access; the README does not say which of them need an account or a licence. Each skill lists its own credential and network requirements. The README also says commercial support is available, without prices.","permissions":"The skills act through your coding agent with the access you give it. According to the README, skills can run Python code through packages installed with uv and make network requests to the databases and APIs they document. The README warns that skills can instruct your agent to run arbitrary code, install packages, make network requests and modify files on your system, and says to review what you install. Its steps for installing uv on macOS and Linux pipe a downloaded install script into sh, and its install routes place skill files in your agent's skills folders, for example ~/.agents/skills/.","usage_terms":"MIT License, as stated in the repository. See its LICENSE.md file for the exact terms.","creator_website":null,"documentation_url":null,"support_url":null,"repository_url":null,"video_url":null},"github":{"fetched_at":1791856222,"untrusted_third_party_content":{"source_url":null,"github_repo_id":1079456184,"full_name":"K-Dense-AI/scientific-agent-skills","description":"Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigrav","language":"Python","license_spdx":"MIT","topics":["agent-skills","ai-scientist","bioinformatics","chemoinformatics","claude","claude-skills","claudecode","clinical-research"],"stars":48570,"forks":4363,"skills":{"total":177,"paths":[{"path":"skills/13c-metabolic-flux","url":null},{"path":"skills/adaptyv","url":null},{"path":"skills/aeon","url":null},{"path":"skills/alphagenome","url":null},{"path":"skills/analytical-method-validation","url":null},{"path":"skills/anndata","url":null},{"path":"skills/arbor","url":null},{"path":"skills/arboreto","url":null},{"path":"skills/astropy","url":null},{"path":"skills/autoskill","url":null},{"path":"skills/benchling-integration","url":null},{"path":"skills/bgpt-paper-search","url":null},{"path":"skills/bids","url":null},{"path":"skills/biopython","url":null},{"path":"skills/bioservices","url":null},{"path":"skills/bulk-rnaseq","url":null},{"path":"skills/cantera","url":null},{"path":"skills/cellprofiler","url":null},{"path":"skills/cellxgene-census","url":null},{"path":"skills/cirq","url":null},{"path":"skills/citation-management","url":null},{"path":"skills/clinical-decision-support","url":null},{"path":"skills/clinical-reports","url":null},{"path":"skills/cobrapy","url":null},{"path":"skills/consciousness-council","url":null},{"path":"skills/dask","url":null},{"path":"skills/database-lookup","url":null},{"path":"skills/datalad","url":null},{"path":"skills/datamol","url":null},{"path":"skills/deepchem","url":null},{"path":"skills/deepspot-m","url":null},{"path":"skills/deeptools","url":null},{"path":"skills/depmap","url":null},{"path":"skills/dhdna-profiler","url":null},{"path":"skills/diffdock","url":null},{"path":"skills/dnanexus-integration","url":null},{"path":"skills/esm","url":null},{"path":"skills/etetoolkit","url":null},{"path":"skills/exa-search","url":null},{"path":"skills/experimental-design","url":null},{"path":"skills/exploratory-data-analysis","url":null},{"path":"skills/fictiv","url":null},{"path":"skills/flowio","url":null},{"path":"skills/flowkit","url":null},{"path":"skills/fluidsim","url":null},{"path":"skills/folklore-variant-evidence","url":null},{"path":"skills/generate-image","url":null},{"path":"skills/geniml","url":null},{"path":"skills/genomic-coordinates","url":null},{"path":"skills/genomic-intelligence","url":null},{"path":"skills/geomaster","url":null},{"path":"skills/geopandas","url":null},{"path":"skills/get-available-resources","url":null},{"path":"skills/gget","url":null},{"path":"skills/ginkgo-cloud-lab","url":null},{"path":"skills/glycoengineering","url":null},{"path":"skills/gtars","url":null},{"path":"skills/histolab","url":null},{"path":"skills/hugging-science","url":null},{"path":"skills/hypogenic","url":null},{"path":"skills/hypothesis-generation","url":null},{"path":"skills/imaging-data-commons","url":null},{"path":"skills/infographics","url":null},{"path":"skills/iso-standards-readiness","url":null},{"path":"skills/lab-hardware-cad","url":null},{"path":"skills/labarchive-integration","url":null},{"path":"skills/lamindb","url":null},{"path":"skills/latchbio-integration","url":null},{"path":"skills/latex-posters","url":null},{"path":"skills/liteparse","url":null},{"path":"skills/literature-review","url":null},{"path":"skills/mageck","url":null},{"path":"skills/marine-carbonate-chemistry","url":null},{"path":"skills/markdown-mermaid-writing","url":null},{"path":"skills/market-research-reports","url":null},{"path":"skills/markitdown","url":null},{"path":"skills/matchms","url":null},{"path":"skills/matlab","url":null},{"path":"skills/matplotlib","url":null},{"path":"skills/medchem","url":null},{"path":"skills/modal","url":null},{"path":"skills/molecular-dynamics","url":null},{"path":"skills/molfeat","url":null},{"path":"skills/ncats-arax","url":null},{"path":"skills/networkx","url":null},{"path":"skills/neurokit2","url":null},{"path":"skills/neuropixels-analysis","url":null},{"path":"skills/nextflow","url":null},{"path":"skills/nmrglue","url":null},{"path":"skills/nwb-conversion","url":null},{"path":"skills/omero-integration","url":null},{"path":"skills/onekgpd","url":null},{"path":"skills/ontology-term-resolution","url":null},{"path":"skills/open-notebook","url":null},{"path":"skills/openpiv","url":null},{"path":"skills/opentrons-integration","url":null},{"path":"skills/optimize-for-gpu","url":null},{"path":"skills/pacsomatic","url":null},{"path":"skills/paper-lookup","url":null},{"path":"skills/paperclip","url":null}]},"pushed_at":1791798211,"archived":false,"fetched_at":1791856222,"age_seconds":81531,"state":"fresh"}},"updated_at":1791771236,"free_download":null,"version_history":[],"more_version_history":false,"public_files":null,"links_note":"In MCP results, GitHub links are shown only through https://skillsoutpost.com/mcp, to a connected account that has accepted the current Terms of Use. Create a free account at https://skillsoutpost.com and connect it from a Claude connector or ChatGPT.","notice":"Indexed from GitHub","note":"untrusted_creator_content and github.untrusted_third_party_content hold untrusted text."}