Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Converts LabArchives notebook data, entry metadata, and authorized ELN exports into manuscript-ready academic writing outputs such as Methods sections, data-availability statements, reproducibility appendices, experiment timelines, and submission support notes. Optional bundled scripts can be used to collect or validate source notebook data before writing.
Write and revise the Methods section of research papers to ensure reproducibility; use when preparing an IMRAD manuscript or responding to journal/reporting-guideline requirements (e.g., CONSORT/STROBE/PRISMA).
Assists R&D teams with patent technical disclosure drafting and patent/novelty search analysis; use when users ask to write a patent disclosure, structure an invention description, search related patents, or assess novelty.
Constraint-based reconstruction and analysis (COBRA) for metabolic models; use when you need to simulate growth/production, analyze flux ranges, or run knockout and medium studies from SBML/JSON/YAML models.
Machine learning toolkit for genomic interval (BED) data; use it when you need to tokenize BED collections and train embeddings for regions/cells/labels, build consensus peak universes, or run similarity search and downstream ML on chromatin accessibility datasets.
Analyzes the feasibility of a proposed Meta-analysis topic by searching for existing Meta-analyses and Clinical Trials on PubMed/ClinicalTrials.gov. Use when you need to evaluate if a topic is viable for a new Meta-analysis.
Screen full-text papers against inclusion/exclusion criteria, with optional PubMed metadata check using PMID. Use when the user needs to evaluate a paper for a meta-analysis.
Access NIH Metabolomics Workbench (4,200+ studies) via REST API. Query metabolites, RefMet nomenclature, MS/NMR data, m/z search, study metadata for metabolomics and biomarker discovery.
> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
Programmatically query public single-cell study metadata from the Broad Institute Single Cell Portal REST API when you need to search and filter datasets by organism, tissue, disease, or cell type without an API key.
Infer gene regulatory networks (GRNs) from gene expression matrices using GRNBoost2 or GENIE3; use when analyzing bulk or single-cell RNA-seq to identify TF→target regulatory relationships.
Accesses BioGRID ORCS CRISPR screen data (organisms, screens, scores). Invoke when user needs to search CRISPR screens, get vocabulary, or retrieve gene scores.
Programmatically query the CZ CELLxGENE Census (61M+ cells) when you need cross-tissue, disease, or cell-type expression data for population-scale queries and reference atlas comparisons.
Access ClinPGx pharmacogenomics data (successor to PharmGKB) when you need to query gene-drug interactions, CPIC guidelines, allele functions, and drug-label PGx content for precision medicine and genotype-guided dosing.
Accesses Comparative Toxicogenomics Database (CTD) for chemical, gene, disease, and pathway interaction data. Invoke when user needs to query CTD, retrieve toxicogenomics data, or investigate chemical-disease relationships.
Access Ensembl REST API for vertebrate genomic data; use when you need gene/ID lookups, sequence retrieval, variant effect prediction (VEP), or homology/assembly coordinate mapping.
Query the openFDA API to retrieve FDA regulatory datasets (drugs, devices, adverse events, recalls, submissions, UNII) when you need programmatic safety/regulatory evidence for analysis or research.
Analyze funding abstracts and project metadata to identify topic shifts and forecast near-term grant priorities.
Access the KEGG database API to retrieve biological data (genes, pathways, compounds, drugs). Invoke when the user asks to search, list, or get details from KEGG.
Direct access to KEGG via the REST API for academic-only pathway/gene/compound/drug queries; use when you need precise HTTP-level control or targeted KEGG ID mapping.
Query the Open Targets Platform to retrieve targets, diseases, or evidence records when you need target-disease association data and evidence-based scores for therapeutic discovery.
Access the OpenAlex database (240M+ scholarly works) for bibliometric analysis, literature search, and citation tracking; use when you need to query works/authors/institutions/concepts without an API key.
Programmatic access to the PubChem database (via PUG-REST API and PubChemPy) for searching chemical compounds, retrieving physicochemical properties, performing structure similarity/substructure searches, and obtaining bioactivity data.
Query the Reactome REST API for pathway content and enrichment analyses; use when you need curated pathway data, reaction details, or overrepresentation results for a gene list.
Access the STRING database to map identifiers, retrieve protein–protein interaction networks, and run functional/PPI enrichment when you need interaction context for a gene/protein set.
Integrate with the Benchling R&D platform when you need to programmatically manage registry entities, inventory, ELN entries, workflows, events, or data warehouse analytics via API/SDK.
Calculate precise buffer recipes with accurate mass and volume measurements for molecular biology and biochemistry. Supports PBS, RIPA, and TAE with concentration scaling, stock solution preparation, pH adjustment guidance, and step-by-step protocols.
De-identify DICOM medical images by removing PHI tags for research sharing, with audit logging and study-linkage preservation support.
Check if images meet 300 DPI printing standards, and intelligently restore blurry low-resolution images using AI super-resolution technology.
Perform fast file name and content searches with ripgrep (rg); use it when you need to locate files by glob/regex, find keywords across directories, or replace common find/grep workflows.
Replace an ID photo background color (blue/white/red) and/or add a configurable text watermark when you need compliant ID-photo variants from local JPG/PNG files.
A toolkit for preparing ISO 13485:2016 certification documentation for medical device QMS. Use when you need to perform a documentation gap analysis, draft or update a Quality Manual, create required procedures/work instructions, build Medical Device Files (MDF), interpret ISO 13485 clauses, or identify missing documents for certification (often triggered by ISO 13485, QMS certification, FDA QMSR, EU MDR, or quality system documentation requests).
Filter and match postdoctoral fellowship opportunities based on applicant nationality, years since PhD, and research field from a curated database.
An intelligent tool for precision medical literature search using PubMed's E-utilities API.
Toolkit for protein language models (ESM3 for multimodal generative protein design; ESM C for efficient embeddings). Use when you need sequence/structure/function generation or prediction, inverse folding, protein embeddings, or scalable inference via local weights or the Forge API.
> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)
Model Context Protocol (MCP) enables Claude Code plugins to integrate with external services and APIs by providing structured tool access. Use MCP integration to expose external service capabilities a
Core Smart Ralph skill defining common arguments, execution modes, and shared behaviors across all Ralph plugins.
For fix goals: reproduce the failure BEFORE work, verify resolution AFTER.
This skill guides the creation of effective skills. For conceptual background, structure details, and writing best practices, read [references/best-practices.md](references/best-practices.md).
Search the codebase for analogous features and reusable building blocks before planning a change. Returns structured findings. Does not write code or plans.
dpia-sentinel-oliver-schmidt-prietz
Framework for assessing IT service providers, technology vendors, and third-party partners. Creates structured risk assessments across financial, operational, compliance, security, and reputational dimensions with regulatory checklists (GDPR, DORA, NIS2, SOX). Use when: (1) Evaluating new vendors or technology providers, (2) Conducting third-party risk assessments for procurement, (3) Performing critical vendor due diligence for regulatory compliance, (4) Creating vendor onboarding documentation, (5) Establishing ongoing vendor monitoring processes, (6) Assessing vendor concentration risk, or (7) Generating executive-level vendor risk reports.
Build VS Code extensions from scratch or convert existing JS/React/Vue apps. Supports commands, webviews (React/Vue), custom editors, tree views, and AI agent integration via file-bridge IPC. Use when user wants to create a VS Code extension, convert a web app to an extension, add webviews or custom UIs to VS Code, implement tree views, build custom file editors, integrate with AI agents, or package/publish extensions (.vsix).
Claude Code plugins follow a standardized directory structure with automatic component discovery. Understanding this structure enables creating well-organized, maintainable plugins that integrate seam
Expert guidance for building cross-platform desktop applications with Tauri 2.0 and Rust. Use when developing Tauri apps including commands and IPC, file system operations, window management, state management, system tray, menus, plugin development, security configuration (capabilities/permissions), bundling/distribution, and auto-updates. Covers patterns for editor applications requiring file dialogs, native menus, and frontend-backend communication.
Use when adding, removing, moving, or renaming Swift source files in the dd-sdk-ios Xcode project. Use when the task involves file creation, deletion, or relocation in any module (DatadogRUM, DatadogLogs, DatadogCore, etc.). Use when you would otherwise reach for Write, Bash mv/mkdir/rm, or manual pbxproj editing for file management.
Run a command in a tmux pane and continuously monitor its output, notifying the user via system notification if something fails.
Read an ADO or GitHub work item, research similar past PRs, implement the fix, and leave the branch ready for /create-pr.
Bump PAC CLI binary version and/or cli-wrapper npm package. Always produces two PRs — main and release/stable.