腳本程式

Python testing framework for writing simple, scalable, and powerful tests

This skill should be used for exploring codebases, looking up documentation, investigating how things work, and gathering context without making code changes. Use for "how does X work?", "find where Y is handled", or "explain Z" questions.

This skill provides comprehensive knowledge for building applications with Cloudflare Sandboxes SDK, which enables secure, isolated code execution in full Linux containers at the edge. It should be used when executing untrusted code, running Python/Node.js scripts, performing git operations, building AI code execution systems, creating interactive development environments, or implementing CI/CD workflows that require full OS capabilities.Use when: Setting up Cloudflare Sandboxes, executing Python/Node.js code safely, managing stateful development environments, implementing AI code interpreters, running shell commands in isolation, handling git repositories programmatically, building chat-based coding agents, creating temporary build environments, processing files with system tools (ffmpeg, imagemagick, etc.), or when encountering issues with container lifecycle, session management, or state persistence.Keywords: cloudflare sandbox, container execution, code execution, isolated environment, durable objects

AI-friendly architecture patterns for TypeScript projects including Domain-Driven Design, Clean Architecture, Hexagonal Architecture, and Page Object Model testing patterns

Expert Python package management with uv - fast dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.

This skill should be used for executing detailed implementation plans created by experienced developers. Follow the plan step-by-step, report deviations, and ask for help when blocked. Designed for cheap/light models (Haiku, smaller Sonnet) to maximize cost-effectiveness while maintaining quality.

Shared operational helpers for SAEF slash commands. Provides shell/Python scripts for scaffolding feature folders, validating context, organizing screenshots, and annotating images.

Meta-skill that scaffolds, validates, and packages other Agent Skills. Enforces code-first (MCP is the special case) via archetypes and filesystem-based workflows.

Implement authentication and authorization with Better Auth - a framework-agnostic TypeScript authentication framework. Features include email/password authentication with verification, OAuth providers (Google, GitHub, Discord, etc.), two-factor authentication (TOTP, SMS), passkeys/WebAuthn support, session management, role-based access control (RBAC), rate limiting, and database adapters. Use when adding authentication to applications, implementing OAuth flows, setting up 2FA/MFA, managing user sessions, configuring authorization rules, or building secure authentication systems for web applications.

Automatically check available scripts and tools before creating new ones. Use this when you need to execute bash, python, or npm scripts to avoid duplicating existing tools. This skill lists all tools in .claude/scripts/ and helps you discover reusable scripts.

Python environment setup with uv, shared utilities, and script structure guidelines.

For any project that contains a .git/.graphite_repo_config file, this skill should be used for creating PRs, managing git branches and otherwise all non-read-only git operations.

Expert in rust-script for running Rust files as scripts without compilation setup. Activate when working with .rs or .ers script files, user mentions rust-script, cargo-script, or scripting Rust, writing one-off Rust scripts with dependencies, or using expr, loop, or inline dependency manifests. Proficient in idiomatic Rust patterns, error handling, async, and CLI tooling.

Native Fabric pattern execution for Claude Code. USE WHEN processing content with Fabric patterns (extract_wisdom, summarize, analyze_claims, threat modeling, etc.). Patterns run natively in Claude's context - no CLI spawning needed. Only use fabric CLI for YouTube transcripts (-y) or pattern updates (-U).

Write TypeScript and JavaScript code following Metabase coding standards and best practices. Use when developing or refactoring TypeScript/JavaScript code.

WSL2 Ubuntu administration from Linux side. Profile-aware - reads preferences fromWindows-side profile at /mnt/c/Users/{WIN_USER}/.admin/profiles/{hostname}.jsonUse when: Inside WSL for apt packages, Docker, Python/uv, shell configs, systemd.Coordinates with admin-windows via shared profile ON THE WINDOWS SIDE.

Invoke Claude Code CLI from Python orchestrators and shell scripts. Use when asked to"spawn claude as subprocess", "automate claude cli", "run claude headless","configure --allowedTools", "set up claude hooks", or "parallel claude invocation".Covers permissions, directory access (--add-dir), hooks, sandbox mode, and async patterns.

Fix type assertions and improve TypeScript type safety. Use when encountering 'as unknown as' casts, manual type definitions that duplicate schema types, or unclear type errors in database queries, especially with Drizzle ORM relations. Also use when verifying types

Error rate monitoring, SLO detection, and notification webhooks for automated rollback triggers. Use when setting up automated deployment rollback, monitoring error rates, configuring SLO thresholds, implementing deployment safety nets, setting up alerting webhooks, or when user mentions automated rollback, error rate monitoring, SLO violations, deployment safety, or rollback automation.

This skill should be used when the user asks to "use marimo", "create a marimo notebook", "debug a marimo notebook", "inspect cells", "understand reactive execution", "fix marimo errors", "convert from jupyter to marimo", or works with marimo reactive Python notebooks.