Scripting

Master unit testing fundamentals with pytest for reliable, isolated testing of individual Python components.

Use when setting up a new dev machine for Claude Code, onboarding to a project, or optimizing development environment - interactive installer that detects existing setup, configures shell, editor, git, templates, and quality gates with configurable enforcement

Comprehensive context engineering and prompt patterns for AI agents. Covers code review, financial systems, KPI systems, data integration MVP, and modern best practices. Based on 2025 research from Anthropic, LangChain, and industry leaders.

ReviewAgent スキル - コード品質判定・静的解析・セキュリティスキャン・品質スコアリング。 生成されたコードに対して100点満点で品質評価し、80点以上で合格判定。 Use when: - コード品質をレビューする時 - 静的解析（ESLint、TypeScript）が必要な時 - セキュリティスキャンが必要な時 - 品質スコアを算出する時 - "レビュー", "品質チェック", "セキュリティ", "スキャン" がキーワードに含まれる時

This skill should be used when the user asks about UV (Python package manager), needs to set up Python virtual environments, install/manage Python CLI tools, run MCP servers with UVX, decide between uv tool install vs uvx, configure VS Code or IDEs for MCP server integration, migrate from pip/pipx/poetry to UV, or troubleshoot UV-related issues. Use when queries mention UV, UVX, Python package management, virtual environments, MCP servers, tool installation, or Python version management.

This skill provides comprehensive automation for GitHub repository setup and configuration. It should be used when creating new projects, setting up CI/CD pipelines, configuring issue templates, enabling security scanning, or migrating existing projects to GitHub automation. The skill prevents 18 documented errors in GitHub Actions YAML syntax, workflow configuration, issue template structure, Dependabot setup, and CodeQL security scanning. It includes 12 production-tested workflow templates, 4 issue templates, security configurations, and automation scripts for rapid project setup. Use when: setting up GitHub Actions CI/CD, creating issue/PR templates, enabling Dependabot, configuring CodeQL scanning, automating GitHub repository setup, fixing YAML syntax errors, integrating security scanning, deploying to Cloudflare Workers via GitHub Actions, or implementing multi-framework testing matrices. Keywords: github actions, github workflow, ci/cd, issue templates, pull request templates, dependabot, codeql, security scanning, yaml syntax, github automation, repository setup, workflow templates, github actions matrix, secrets management, branch protection, codeowners, github projects, continuous integration, continuous deployment, workflow syntax error, action version pinning, runner version, github context, yaml indentation error

Comprehensive knowledge for using the Bash tool in Claude Code effectively. This skill should be used when orchestrating CLI tools, configuring hooks, setting up automation workflows, managing git operations, handling multi-command patterns, or encountering Bash tool errors. Covers: PreToolUse hooks, command chaining patterns, git workflow automation, CLI tool integration, custom commands (.claude/commands/), security configurations, allowlisting, session persistence, output handling, error prevention, and troubleshooting common issues. Use when: setting up Claude Code hooks, configuring bash permissions, creating custom commands, automating git workflows, orchestrating multiple CLI tools, debugging bash command failures, implementing security guards, logging command execution, or preventing dangerous operations.

Generate ESLint configuration files (.eslintrc.js, eslint.config.js) for JavaScript/TypeScript projects with framework-specific rules. Triggers on "create ESLint config", "generate eslint configuration", "eslint setup for", "linting rules for".

Conventions for TypeScript types, interfaces, assertions, and type safety. Use when writing or reviewing TypeScript code.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Shell scripting and Bash programming patterns

Core coding patterns and conventions for Kalahari project. MUST be used by all code-related agents.

Templates and automation for initializing and configuring Foundry projects. Use when setting up new Foundry projects or adding Foundry to existing codebases.

Generate phased implementation plans from requirements and UI wireframes. Use when the user provides requirements documents and/or UI wireframes and wants to create a detailed, phased implementation plan. Triggers on requests like "create implementation plan", "plan the implementation", or when asked to design an implementation approach for a project with existing requirements. Produces description-only plans (no code) with clear phases, dependencies, and testing checklists.

Adapts textbook content complexity based on user's software/hardware background to optimize learning experience.

Manages PostgreSQL database operations including Alembic migrations (creation, application, rollback), database backups and restoration for both development and production environments, shell access, and pgvector extension management. This skill should be used when creating schema changes, running migrations, backing up data, or troubleshooting database issues.

Comprehensive guidance for the AIdev workflow system used for structured software project management with Claude Code. Covers AIdev commands (/constitution, /prd, /plan, /work, /check, /verify, /reflect, /new, /spec), file structure (spec/ directory with constitution, PRD, units), task execution with evidence-based completion, constitutional governance, quality gates, Single Source of Truth principle, Context Discipline, pre-implementation checks, task schema format, automation hooks, template management, and workflow sequences for feature planning and implementation. Use when working with spec/, creating product requirements, designing features, managing tasks, or validating project alignment.

Data science and machine learning platform functions for the East language (TypeScript types). Use when writing East programs that need optimization (MADS, Optuna, SimAnneal, Scipy), machine learning (XGBoost, LightGBM, NGBoost, Torch MLP, GP), ML utilities (Sklearn preprocessing, metrics, splits), or model explainability (SHAP). Triggers for: (1) Writing East programs with @elaraai/east-py-datascience, (2) Derivative-free optimization with MADS, (3) Bayesian optimization with Optuna, (4) Discrete/combinatorial optimization with SimAnneal, (5) Gradient boosting with XGBoost or LightGBM, (6) Probabilistic predictions with NGBoost or GP, (7) Neural networks with Torch MLP, (8) Data preprocessing and metrics with Sklearn, (9) Model explainability with Shap.

Implement Stripe Connect payments for PhotoVault marketplace using destination charges. Use when working with checkout sessions, webhook handlers, platform subscriptions ($22/month), commission splits (50/50), Connect onboarding, failed payment handling (dunning), or debugging payment issues. Includes idempotency patterns and PhotoVault product IDs.

East programming language - a statically typed, expression-based language embedded in TypeScript. Use when writing East programs with @elaraai/east. Triggers for: (1) Writing East functions with East.function() or East.asyncFunction(), (2) Defining types (IntegerType, StringType, ArrayType, StructType, VariantType, etc.), (3) Using platform functions with East.platform() or East.asyncPlatform(), (4) Compiling East programs with East.compile(), (5) Working with East expressions (arithmetic, collections, control flow), (6) Serializing East IR with .toIR() and EastIR.fromJSON(), (7) Standard library operations (formatting, rounding, generation).