Orchestrate gummy-agents across distributed network using 'd' command for load-balanced, multi-host AI development
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 →Orchestrate gummy-agents across distributed network using 'd' command for load-balanced, multi-host AI development
Extract the functional DNA from existing works (TV, film, books, plays). Use when adapting a source work, when analyzing what makes something work, when creating trope maps for reuse, or when you need to separate structural necessity from stylistic choice.
Execute implementation work from a scratchpad in a structured, trackable way. This skill loads the implementation plan, creates TodoWrite items for visibility, works through tasks systematically, and
Analyze and extract relevant patterns, best practices, and usage examples
Loads feature docs, workflow docs, and invariants before planning any task. Use when starting complex work, changing multiple features, or when unsure about constraints. Essential first step for non-trivial changes.
Use this skill at the beginning of any session or when needing to understand available project documentation. Provides just-in-time context by scanning YAML frontmatter from all markdown files in the docs/ directory without loading full content.
Docker orchestration and CI/CD for IntelliFill. Use when configuring containers, writing workflows, or setting up environments.
Dockerfile best practices, multi-stage builds, docker-compose patterns, and Kubernetes concepts
Docker Compose Watch mode for automatic hot reload during local development with sync, rebuild, and restart actions
Guide for using Docker - a containerization platform for building, running, and deploying applications in isolated containers. Use when containerizing applications, creating Dockerfiles, working with Docker Compose, managing images/containers, configuring networking and storage, optimizing builds, deploying to production, or implementing CI/CD pipelines with Docker.
Documentation pipeline automation and docs-as-code workflows
Orchestrates complete single-document workflows with automatic validation and indexing in a write→validate→index pipeline
Extract structured metadata from documents using AI. Classify content types, extract topics and tools. Supports async batch processing.
Unified document lifecycle management. Defines terminal statuses, unified numbering via .next-id, close procedures, and orphan detection. Load at session start.
Document and PDF patterns for Ballee using @kit/documents for document management and @kit/pdf-core for PDF generation. Use when working with file uploads, document viewers, or generating PDFs.
Build complete document knowledge bases with PDF text extraction, OCR for scanned documents, vector embeddings, and semantic search. Use this for creating searchable document libraries from folders of PDFs, technical standards, or any document collection.
Process and manipulate office documents including PDF, DOCX, PPTX, and XLSX files. Use when working with document extraction, conversion, form filling, or spreadsheet operations.
Document processing. USE WHEN document, process file. SkillSearch('documents') for docs.
Use when creating Docusaurus plugins (remark, rehype, theme, content, lifecycle) to extend markdown, modify HTML, or add custom functionality
dojo-react
Five-phase reasoning protocol based on Musashi's Book of Five Rings. Ground (morphemic extraction), Water (pattern matching), Fire (unified derivation), Wind (predictions), Void (meta-closure). Use for cross-disciplinary insight discovery.
Instructions for downloading the ai4space repository, useful when the user wants to start working with the lunar base model.
Download transcripts for all data folders sequentially. Use for overnight batch processing or when you need to download pending transcripts across all channels and collections.
Download firmware hex files and configurator builds for an INAV release
Downloads videos from Youtube. Use when you have a youtube.com URL and you want the video/audio content to be downloaded.
Downloads images, icons, and SVGs from Figma designs. Use when extracting visual assets from Figma for implementation.
Automatically organize and clean up downloads folder by categorizing files, removing duplicates, and optimizing storage space
Background chapter downloads and offline reading
Implement real-time collaborative drawing canvas with brush tools, color picker, undo/clear functionality, and canvas-to-image export. Use when building drawing UI, handling stroke synchronization, managing drawing state, or uploading drawings to storage.
Discover and share design work on Dribbble - browse design inspiration, manage portfolio, and find designers
Google Drive management via DriveACSet schema with GF(3) triadic routing. Transforms files/folders into typed Interactions, routes to queue fibers, detects saturation for organized-drive-as-condensed-state.
Building DuckDB loadable extensions with CMake, FetchContent, and proper metadata handling
ALWAYS USE when building data lakehouse with DuckDB compute, configuring dbt-duckdb with Polaris plugin, or designing catalog-first architecture in floe-platform. Use IMMEDIATELY when reading/writing Iceberg tables via Polaris catalog, creating Dagster assets with DuckDB, or connecting to REST catalogs with inline credentials. Provides research steps for DuckDB + Dagster + Iceberg/Polaris integration patterns.
Query remote Parquet files via HTTP without downloading using DuckDB httpfs. Leverage column pruning, row filtering, and range requests for efficient bandwidth usage. Use for crypto/trading data distribution and analytics.
Why and how to use dynamic imports in LivestockAI server functions for Cloudflare Workers compatibility
Self-regulating Goblins actor implementing Ivan Illich's dynamic sufficiency
ebfe_organize_models
Parse ebooks, extract concepts and entities with citation traceability, classify by type/layer, and synthesize across book collections.
Creates comprehensive ebooks, guides, and downloadable lead magnets with chapter structure and promotional assets. Use when the user asks about ebooks, lead magnets, downloadable guides, gated content, or PDF resources.
EC2操作簡素化（複雑なSSMコマンドをシンプルなインターフェースでラップ）
Ecommerce integration patterns and decomposer/composer
Use when querying data with Ecto.Query DSL including where clauses, joins, aggregates, preloading, and query composition. Use for building flexible database queries in Elixir applications.
Guide for developing EDS blocks using vanilla JavaScript, Content Driven Development, and block decoration patterns. Covers block structure, decorate function, content extraction, DOM manipulation, and EDS best practices for Adobe Edge Delivery Services.
Config loading and Schema validation/transform. Use when defining configuration or validating inputs.
EKS networking configuration including VPC CNI, load balancers, and network policies. Use when setting up cluster networking, configuring ingress/load balancing, implementing network security, troubleshooting connectivity, or optimizing network costs.
EKS security hardening and best practices. Use when configuring cluster security, implementing pod security, managing secrets, preparing for compliance audits, hardening infrastructure, scanning containers, or responding to security incidents.
AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services.
Build Electron desktop applications with IPC, window management, and packaging. Use when working on TitanMirror desktop app or any cross-platform desktop applications.
This skill should be used when developing Electron applications with Feature-Sliced Design (FSD) architecture and React 19. Triggers on requests to create components, features, entities, widgets, or pages following FSD layer structure. Also applies when setting up Electron main/preload/renderer process code organization.
*Transform any project into production-quality software using proven patterns.*