$ skills --list

Automated model selection and comparison for optimal forecasting

Resets staging database with full schema drop. Use for schema changes or migrations. SINGLE SOURCE OF TRUTH for staging database reset automation.

A skill for generating and seeding realistic test data into a database. Use this skill for tasks related to database seeding, test data generation, and populating a database for development, testing, or demo purposes. It supports idempotent seeding, relationship data generation (e.g., users and their tasks), and environment-specific data sets (dev, test, demo). Triggers: "seed database", "generate test data", "populate db", "database seeding".

Astro 5.0 + Tailwind CSS landing page with blog, dark mode, and perfect PageSpeed scores.

Run Python code in lesson context with proper uv and venv handling for agent-spike project. Activate when user wants to run tests, demos, or CLI commands for lessons in lessons/ directories. Project-specific for agent-spike multi-agent learning.

Apply Forth AI brand guidelines when creating frontends. Use for UI components, pages, applications, and design systems. Enforces radical simplicity, implicit elegance, abstract graphics, and the Forth AI visual identity.

Comprehensive draft story review with parallel specialist sub-agents. Spawns PM, UX, and SM agents to review stories from product, design, and implementation readiness perspectives before development begins.

Comprehensive Python data engineering patterns for AWS Data Lake, including PySpark, Pandas, Apache Airflow, AWS Glue, ETL pipelines, data quality, schema management, performance optimization, FastAPI services, streaming with Kafka/Kinesis, data validation with Great Expectations, testing strategies, error handling, logging, and production deployment on AWS EMR and Glue.

Playwright E2E testing patterns with chrome-devtools MCP integration.Reference for integration tests, A11y validation, and visual regression.

This skill teaches how to manage stacked PRs (pr1 → pr2 → pr3) after the base PR merges. Covers rebasing dependent PRs onto the updated base branch using cherry-pick workflow. Use this when you have a chain of dependent PRs and need to update them after merging earlier PRs in the stack.

Create a new LEAP feature with proper branch, directory structure, and goals.md. Use when starting a new feature to automate LEAP setup.

Rust error handling patterns and best practices. Use when designing error types, implementing error propagation, adding error context, converting between error types, or debugging error handling issues.

Email operations skill for sending, fetching, and reading emails via IMAP/SMTP.Uses curl with OpenSSL/LibreSSL for reliable TLS compatibility with Tencent Enterprise Mail and other providers.Credentials are securely stored in macOS Keychain.

Comprehensive workflow for managing Linear issues. Use when creating, grooming, or working on Linear issues. Handles research-driven issue creation, project matching, feature decomposition into parallelizable sub-tasks, and execution with automatic state management. Proactively helps when user mentions Linear tickets or planning work.

Systematic debugging approach for ANY codebase, ANY language, ANY bug type. Use when facing unexpected behavior, crashes, performance issues, or intermittent problems.

Manage dependencies with npm/yarn/pnpm. Use for auditing vulnerabilities, checking outdated packages, understanding dependency trees, and upgrading packages safely.

Get Gemini CLI's opinion on code, architecture, or implementation. Use when you want a second AI perspective during coding sessions.

ローカルGitブランチを分析し、安全にクリーンアップします。マージ状態、古さ、リモート追跡状況によってブランチを分類し、削除すべきブランチを特定します。ユーザーが「ブランチを整理」「古いブランチを削除」と依頼した時にアクティベートします。

Creates or updates feature implementation plan documents in doc/plan. Use when planning a new software feature, refining feature scope/name, tracking TODO/DONE progress, or marking a plan as achieved.

Maintain character consistency by cross-referencing canonical character files. Use when writing scenes with established characters, updating character information, or checking for contradictions. Prevents invented physical details, possessions, backstory, and knowledge.