數據與 AI

This skill should be used when the user asks to "use delphi", "ask delphi", or wants multiple parallel oracle investigations of the same question to discover divergent insights. Delphi launches multiple oracle agents simultaneously with identical prompts, allowing them to independently explore and potentially discover different paths, clues, and solutions. Results are saved to .oracle/[topic]/ and synthesized into a final document.

Risk prioritization framework for engineers. CVSS interpretation, exploitability analysis, blast radius calculation, and decision trees for patch management and vulnerability remediation.

Manage and maintain VRP Toolkit skills through compliance checking, audit tracking, and documentation synchronization. Use when (1) adding or modifying skills, (2) checking skill compliance with project standards, (3) auditing SKILLS.md vs skills directory consistency, (4) recording skill changes to SKILLS_LOG.md, or (5) performing periodic skill health checks. Ensures skills stay independent, under 500 lines, properly structured, and well-documented.

Essential Reinvention Loop based on Elon Musk's First Principles Thinking. A 3-step problem-solving framework for the AI era. (1) Deconstruct problems to fundamental facts, (2) Delete unnecessary processes boldly, (3) Reconstruct 10x faster with AI as partner. Use for complex problem analysis, process optimization, and innovative solution design.

Production-ready scripts for Android app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and emulator lifecycle management. Optimized for AI agents with minimal token output. Android equivalent of ios-simulator-skill.

ALWAYS use this skill proactively for Consumer Affairs Django repositories (located in ../ca/ directory) when ANY of these occur - (1) After writing or modifying ANY Python code files in CA repos (2) After tests pass and before telling user work is complete (3) User mentions linting, formatting, ruff, code style, or code quality (4) After using the ca-django-tests skill successfully (5) Before preparing to commit code. This skill runs 'ca exec ruff format' and 'ca exec ruff check --fix' to ensure code quality. CRITICAL - Always run this automatically after code changes and before declaring work complete.

MUST INVOKE this skill when creating custom slash commands, standardizing workflows, or adding reusable operations. Secondary: understanding command structure, learning YAML configuration, or optimizing existing commands. Create, audit, and maintain custom slash commands.

Execute a Life-of-Mine (LOM) DCF model for mining assets with Unit-of-Production depreciation

Central CLAUDE.md file with project guidelines auto-injected into system prompt, achieving 10% accuracy lift in multi-hop reasoning through consistent context. Use for repo-wide context, coding standards enforcement, project guidelines, or architecture documentation. Auto-loaded by Claude Code CLI. Triggers on "project context", "coding standards", "CLAUDE.md", "project guidelines", "repo documentation".

Practical workflows, context engineering strategies, and real-world execution examples for MoAI-ADK. Use when learning workflow patterns, optimizing context management, debugging issues, or implementing features end-to-end.

Generates Nano Banana Pro prompts for profile icons and SNS images. Use when user mentions "プロフィール画像", "アイコン作成", "SNS用画像", or "ヘッダー画像".

Build WCAG 2.1 AA compliant web applications for University of Sheffield. Covers semantic HTML, ARIA patterns, form accessibility, keyboard navigation, color contrast, alt text, captions, and automated testing. Use when creating websites, web apps, forms, interactive components, or auditing accessibility for WCAG compliance, screen readers, keyboard access, or inclusive design.

Provides patterns and examples for generating test data using factory libraries. Use this skill when you need to create realistic and maintainable test data for your application. It covers factory patterns (e.g., Factory Boy for Python, Polly.js for JavaScript), handling relationships between models, using traits for data variations, sequence generation for unique values, and cleanup strategies. Trigger this skill for tasks involving test fixtures, data seeding for tests, or factory implementation.

Project organization, multi-agent coordination, bug reporting, feature requests, and documentation practices. Use when managing projects, coordinating work, or organizing development workflows.

Claude Codeフックの詳細仕様、設計原則、設定方法。フック、hook、PreToolUse、Stop時に使用。

멀티 AI 코드 리뷰 오케스트레이터. Claude, Codex, Gemini, Droid를 조율하여 종합적 코드 리뷰 수행. "멀티 AI 리뷰", "코드 리뷰", "종합 리뷰" 요청 시 활성화됩니다.

Turns ambiguity into an Uncertainty Register, prioritizes items, and produces observation tasks/experiments with evidence and decision rules. Use when the user mentions uncertainty/unknowns/assumptions/validation/investigation/hypotheses/risks or cannot decide (不確実性, 曖昧, 未知, 前提, 仮説, 検証, 調査, 優先順位, 観測, 意思決定).

Enterprise-grade Python expertise with production patterns for Python 3.13.9, FastAPI 0.115.x, Django 5.2 LTS, Pydantic v2, SQLAlchemy 2.0; activates for API development, ORM usage, async patterns, testing frameworks, and production deployment strategies.

Claude Harness を使用して Plans.md のタスクを実行。Use when user mentions 実装実行, execute tasks, Harness, 並列実装. Do not use for design or review.

Generate learning science-backed feedback templates for Canvas assignments. Use when educators need feedback templates for grading, want to create rubric comments, need encouraging feedback language aligned with Pillar 3 principles (targeted, encouraging, immediate), or want to set up SpeedGrader comment libraries. Works with canvas-mcp for bulk grading.