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 →Configure ArgoCD Applications and ApplicationSets for GitOps-based Helm deployments with sync policies and multi-environment support. Use when setting up ArgoCD Applications for Helm charts, configuring multi-environment deployments with ApplicationSets, implementing GitOps workflows, configuring sync policies and strategies, or setting up progressive delivery with Argo Rollouts.
>
Expert-level Helm 3 package management, chart development, templating, and production operations
hetzner-cloud-management
Connect to HeyReach for LinkedIn automation. Load when user mentions 'heyreach', 'linkedin outreach', 'linkedin campaigns', 'heyreach campaigns', 'add leads', 'campaign stats'. Meta-skill that validates config and routes to operations.
HeyReach LinkedIn automation integration. Load when user mentions 'heyreach', 'linkedin outreach', 'linkedin campaigns', 'list campaigns', 'add leads', 'campaign stats', or any LinkedIn automation operations.
Guidance for deploying HuggingFace models as inference APIs/services. This skill applies when tasks involve downloading pre-trained models from HuggingFace Hub, creating REST APIs for model inference, building Flask/FastAPI services around ML models, or setting up sentiment analysis, text classification, or other NLP inference endpoints.
Visualize Hi-C contact matrices, TADs, loops, and genomic features using matplotlib, cooltools, and HiCExplorer. Create triangle plots, virtual 4C, and multi-track figures. Use when visualizing contact matrices or genomic features.
A three-level framework for building, scaling, and dominating a marketplace. Use it when launching a new marketplace to determine initial scope, when deciding whether to expand into new categories/geographies, or when diagnosing why a marketplace is growing but not becoming more profitable.
Create sophisticated economic data analyses and visualizations for higher education stakeholders using FRED (Federal Reserve Economic Data). Use this skill when users request: (1) Analysis of student loan debt, unemployment by education level, or earnings data, (2) Dashboard or visual presentations of higher ed economic indicators, (3) Narrative reports on higher education ROI or economic value, (4) Data-driven communications for institutional stakeholders (trustees, enrollment management, financial aid offices), or (5) Integration of FRED API data into interactive visualizations.
Use when working with the scikit-hep hist library in Python to create, fill, slice, and plot histograms (1D/2D/multi-axis), including UHI indexing, categorical axes, and mplhep plotting conventions.
Statistical methods for calling hits in CRISPR screens. Covers MAGeCK, BAGEL2, drugZ, and custom approaches for identifying essential and resistance genes. Use when identifying significant genes from screen count data after QC passes.
Narya interactive proof development with typed holes
A premium, minimal, animated Todo App homepage with a strong hero message, refined typography, floating icons, and a single focused CTA — visually aligned with black-pink glassmorphism used across auth and dashboard.
Unified homoiconic graph rewriting - λ-calculus, interaction nets, ACSets, CUDA parallelism
Design hook-based event systems for ADW observability. Use when implementing real-time event broadcasting, creating hook pipelines, or building agent activity monitoring.
React Hooks patterns including custom hooks and dependency management. Use when implementing component logic.
Imported skill how_to_guide from openai
HTML Reporting Standards Skill
Imported skill html2pptx from anthropic
HtmlGraph workflow skill combining session tracking, orchestration, and parallel coordination. Activated automatically at session start. Enforces delegation patterns, manages multi-agent workflows, ensures proper activity attribution, and maintains feature awareness. Use when working with HtmlGraph projects, spawning parallel agents, or coordinating complex work.
HtmlGraph workflow skill combining session tracking, orchestration, and parallel coordination. Activated automatically at session start. Enforces delegation patterns, manages multi-agent workflows, ensures proper activity attribution, and maintains feature awareness. Use when working with HtmlGraph projects, spawning parallel agents, or coordinating complex work.
Angular 21+ functional HTTP interceptors for auth, error handling, loading states, retry logic, caching, and security best practices
Connect to HubSpot CRM for contact, company, deal, and engagement management. Load when user mentions 'hubspot', 'crm', 'contacts', 'companies', 'deals', 'list contacts', 'create contact', 'search deals', or any HubSpot CRM operations. Meta-skill that validates config, discovers CRM objects, and routes to appropriate operations.
Project dashboard that guides you through setup and tracks progress
Runs ML models in the browser and Node.js with Transformers.js and Hugging Face Inference API. Use when adding local inference, embeddings, or calling hosted models without GPU servers.
Train and fine-tune LLMs using HuggingFace TRL, Transformers, and cloud GPU infrastructure with SFT, DPO, GRPO methods
Use Hugging Face Transformers for local model inference, embeddings, and fine-tuning. Covers pipelines, model selection, quantization, and optimization. Use when working with local LLMs, embeddings, or custom model training.
GPU-accelerated pipeline for detecting, tracking, and classifying humans in dashcam footage. This skill should be used when users need to extract human presence from videos, analyze dashcam footage for people detection, perform investigative analysis of human subjects in recordings, or classify individuals with optional head covering detection.
Coordinate multi-tool workflows with guardrails; use when asked to chain retrieval, analysis, and action steps.
Hydrodynamic analysis using BEM, RAOs, added mass, damping, and wave loads for offshore structures
HyJAX Relational Thinking Skill
Comprehensive Hyprland Wayland compositor configuration skill. Use when users need help with: (1) Creating or modifying Hyprland config files, (2) Setting up keybindings, window rules, monitors, or animations, (3) Troubleshooting Hyprland configuration issues, (4) Searching for valid config variables and values, (5) Understanding Hyprland syntax and structure, (6) Setting up multi-monitor configurations, (7) Configuring input devices, decorations, or layouts, or (8) Any other Hyprland-related configuration tasks.
This skill should be used when creating, modifying, or troubleshooting custom themes for iA Presenter.
Create cohesive icon sets and design systems
Complete idea-to-exit pipeline for solo builders with 8 interconnected agents managing the entire product lifecycle
Transform bullet points into enhanced, prioritized items for MASTER_PLAN.md. Process ideas inbox and integrate with project tracking.
Automate Ideal Direct finance and supply chain SOPs with browser-based workflow guidance. Handles payroll, working hours, purchase orders, and audits using Playwright MCP.
DAG and potential outcomes frameworks for causal mediation identification
Extract the fundamental requirement from user requests before any research or implementation.
Identify section boundaries and content sequences within a scraped webpage for AEM Edge Delivery Services import. Performs two-level analysis (sections, then sequences per section) and surveys available blocks.
Extract quantities from IFC/Revit models for quantity takeoff. Uses DDC converters to get element counts, areas, volumes, lengths with grouping and reporting.
IIoT Database interaction patterns. TimescaleDB + Apache AGE queries, helper functions, mock data generation.
Creates image carousels with hover-activated auto-advance, touch swipe support, and animated progress indicators. Use when building image galleries, product showcases, or any multi-image display with navigation.
Image processing for basic edits and color adjustments. Use this skill when users request image operations like resize, rotate, crop, flip, or color adjustments (brightness, contrast, saturation). Supports both uploaded images and images from URLs.
Extract EXIF metadata from images including GPS coordinates, camera settings, and timestamps. Map photo locations and strip metadata for privacy.
Extract data from construction images using AI Vision. Analyze site photos, scanned documents, drawings
Upload images to ImageKit from file paths or clipboard, returning the CDN URL for easy sharing and embedding