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 →Digital archiving workflows with AI enrichment, entity extraction, and knowledge graph construction. Use when building content archives, implementing AI-powered categorization, extracting entities and relationships, or integrating multiple data sources. Covers patterns from the Jay Rosen Digital Archive project.
Electron desktop application development with React, TypeScript, and Vite. Use when building desktop apps, implementing IPC communication, managing windows/tray, handling PTY terminals, integrating WebRTC/audio, or packaging with electron-builder. Covers patterns from AudioBash, Yap, and Pisscord projects.
Structured workflow for fact-checking claims in journalism. Use when verifying statements for publication, rating claims for fact-check articles, or building pre-publication verification processes. Includes claim extraction, evidence gathering, rating scales, and correction protocols.
Use this skill when creating new files that represent architectural decisions — data models, infrastructure configs, auth boundaries, API contracts, CI/CD pipelines, or event systems. Flags irreversible decisions and forces a discussion about trade-offs before committing.
Python data processing pipelines with modular architecture. Use when building content processing workflows, implementing dispatcher patterns, integrating Google Sheets/Drive APIs, or creating batch processing systems. Covers patterns from rosen-scraper, image-analyzer, and social-scraper projects.
Web scraping with anti-bot bypass, content extraction, undocumented APIs and poison pill detection. Use when extracting content from websites, handling paywalls, implementing scraping cascades or processing social media. Covers requests, trafilatura, Playwright with stealth mode, yt-dlp and instaloader patterns.
Zero-build frontend development with CDN-loaded React, Tailwind CSS, and vanilla JavaScript. Use when building static web apps without bundlers, creating Leaflet maps, integrating Google Sheets as database, or developing browser extensions. Covers patterns from rosen-frontend, NJCIC map, and PocketLink projects.
Extract text from PDFs, fill forms, and merge documents. Use when handling PDF files or document extraction.
Extract PDF text, fill forms, merge files. Use when handling PDFs.
Use when preparing a Formax code handoff: selecting files, generating repomix bundles, and writing a high-quality prompt for WebGPT or another coding agent with clear constraints and validation scope.
Use when a dev is new to the project, asks for an overview, or wants to get oriented quickly. Fills graph gaps then runs a guided codebase interview.
Automatically evaluates OmG sessions to extract reusable patterns (error resolutions, workarounds, conventions) and save them to `.omg/rules/learned/`.
Answer a question about a GRACE project using full project context. Use when the user has a question about the codebase, architecture, modules, or implementation — loads all GRACE artifacts, navigates the knowledge graph, and provides a grounded answer with citations.
Query AND UPLOAD to Google NotebookLM. Create new notebooks, upload local files (PDF/MD/TXT), add URLs, paste text content. Browser automation with persistent auth.
**🚀 Enhanced with Local Validators**: This command now uses local JavaScript validators for D1, D2, and D3 dimensions to significantly reduce token consumption while maintaining evaluation quality. C
Creates detailed Standard Operating Procedures (SOPs) for business processes. Use when user needs SOPs, process documentation, operational guides, workflow documentation, or step-by-step instructions for repeatable business processes.
<!-- Part of the skill-forge AbsolutelySkilled skill. Load this file when
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
Plan and create Amazon A+ Content (Enhanced Brand Content). Design module layouts, write persuasive copy, plan comparison charts, and create image briefs that convert browsers into buyers.
Premium A+ and Brand Story — module design, lifestyle imagery, comparison charts, mobile optimization
Amazon FBA Calculator - Complete fee breakdown and profit analysis
Amazon keyword research and market opportunity analysis for sellers. Retrieve autocomplete suggestions (long-tail keywords), analyze competitor landscape, and assess market opportunity for any keyword on 12 Amazon marketplaces (US/UK/DE/FR/IT/ES/JP/CA/AU/IN/MX/BR). No API key required. Make sure to use this skill whenever the user mentions Amazon product research, finding products to sell on Amazon, Amazon keyword ideas, niche analysis, competition analysis for Amazon, market opportunity on Amazon, comparing Amazon keywords, evaluating whether a product is worth selling, Amazon autocomplete data, seasonal demand for Amazon products, or anything related to researching what to sell on Amazon — even if they don't explicitly say 'keyword research'. Also trigger when the user asks vague questions like 'is this a good product to sell?', 'what's the competition like for X on Amazon?', 'should I sell X or Y?', or 'what are people searching for on Amazon?'.
Plan Amazon product photography for maximum conversion. Shot lists, lighting setups, infographic briefs, lifestyle scene planning, and image optimization following Amazon's requirements.
Guidelines for generating clinical decision support (CDS) documents: patient cohort analyses (biomarker-stratified outcomes) and treatment recommendation reports (GRADE-graded evidence). Covers document structure, executive summary design, evidence grading (GRADE 1A–2C), statistical reporting (HR, CI, survival), and biomarker integration. Use when creating pharmaceutical research documents, clinical guidelines, or regulatory submissions.
Low-level Python plotting library for full customization of scientific figures. Use for publication-quality plots (line, scatter, bar, heatmap, contour, 3D), multi-panel subplot layouts, and fine-grained control over every visual element. Export to PNG/PDF/SVG. For quick statistical plots use seaborn; for interactive plots use plotly.
PyHealth is a Python library for healthcare machine learning. Build clinical prediction models from EHR (Electronic Health Record) data: process MIMIC-III/IV, eICU, and OMOP-CDM datasets, encode medical codes (ICD, ATC, NDC), construct patient-level datasets, and train models (Transformer, RETAIN, GRASP, MedBERT) for tasks including mortality prediction, drug recommendation, readmission, and diagnosis prediction. Alternatives: FIDDLE (EHR preprocessing only), clinical-longformer (NLP on clinical notes only), ehr-ml (EHR embedding only).
Bayesian modeling with PyMC 5. 8-step workflow: define model, set priors, define likelihood, sample (NUTS/ADVI), diagnose (R-hat, ESS, divergences), interpret posteriors, compare models (LOO/WAIC), predict. Hierarchical, logistic, GP model variants. Prior/posterior predictive checks.
Classical machine learning in Python. Use for classification, regression, clustering, dimensionality reduction, model evaluation, hyperparameter tuning, and preprocessing pipelines. Covers linear models, tree ensembles, SVMs, K-Means, PCA, t-SNE. For deep learning use PyTorch/TensorFlow; for gradient boosting at scale use XGBoost/LightGBM.
Survival analysis and time-to-event modeling with scikit-survival. Cox proportional hazards (standard/elastic net), Random Survival Forests, Gradient Boosting, SVMs for censored data. C-index (Harrell/Uno), Brier score, time-dependent AUC evaluation. Kaplan-Meier, Nelson-Aalen, competing risks. scikit-learn Pipeline/GridSearchCV compatible. For frequentist regression use statsmodels; for Bayesian survival use pymc; for simpler parametric models use lifelines.
Parse and create FCS (Flow Cytometry Standard) files v2.0-3.1. Read event data as NumPy arrays, extract channel metadata, handle multi-dataset files, export to CSV/FCS. For advanced gating and compensation use FlowKit.
Query NCI Imaging Data Commons (IDC) for cancer radiology and pathology imaging datasets hosted on Google Cloud. Search DICOM collections by modality, anatomical site, cancer type, or collection name. Download images via Google Cloud Storage or IDAT tool. 50TB+ of publicly accessible DICOM images. Requires Google Cloud account for large downloads; small queries work without billing. For local DICOM processing use pydicom-medical-imaging; for whole-slide pathology use histolab.
OMERO is an open-source platform for biological image data management. Use the omero-py Python client to connect to an OMERO server, search and retrieve images as numpy arrays, annotate images with tags and key-value pairs, manage ROIs, and integrate OMERO image data into downstream analysis pipelines — all programmatically without the OMERO desktop GUI.
PathML is an open-source toolkit for computational pathology. Use it to process whole-slide images (WSIs): load slides, extract tiles, apply stain normalization and nuclear segmentation preprocessing, extract features, and train machine learning models. Supports H&E and multiplex imaging. Ideal for building end-to-end digital pathology pipelines from raw WSI files to quantitative outputs.
Pure Python DICOM library for medical imaging (CT, MRI, X-ray, ultrasound). Read/write DICOM files, extract pixel data as NumPy arrays, access/modify metadata tags, apply windowing (VOI LUT), anonymize PHI, build DICOM from scratch, process series into 3D volumes. For whole-slide pathology images use histolab; for NIfTI neuroimaging use nibabel.
Python library for tracking particles (fluorescent spots, colloids, vesicles, cells) in video microscopy using the Crocker-Grier algorithm. Core modules: locate particles in single frames, batch-process image sequences, link positions into trajectories, filter short-lived tracks, and compute mean squared displacement (MSD) for diffusion analysis. Supports 2D and 3D tracking with subpixel accuracy. Integrates with pims for reading TIF stacks, AVI, and image series. Use when you need quantitative single-particle tracking (SPT) from fluorescence or brightfield video and downstream diffusion coefficient extraction.