腳本程式

Use when working with Ansible Core 2.19 for automation, configuration management, playbooks, modules, or infrastructure as code

Claude Code hooks configuration specialist. Use when creating hooks for tool validation, logging, notifications, or custom automation in Claude Code.

Delegates coding tasks to Gemini CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.

Creates and edits Claude Code skills with YAML frontmatter, folder structure, and depth-scaled content. Use when building new skills, updating existing skills, designing SKILL.md metadata, organizing skill folders, validating skill structure, or adding Python and TypeScript scripts for deterministic operations.

Use when analyzing website traffic, investigating SEO issues, diagnosing high bounce rates, evaluating content performance, or optimizing site conversions - proactive SEO consultant with Plausible Analytics access that investigates patterns, fetches actual page content, and provides specific actionable recommendations based on real data analysis

Stagehand Python AI-powered browser automation. Use for web scraping, form filling, clicking elements, extracting structured data, and autonomous multi-step browser workflows. Covers act(), extract(), observe() methods and Computer Use Agent patterns.

Implement route-based and component-based code splitting for optimal bundle sizes and load performance.

[Code Quality] Defines clear boundaries and goals for a refactoring session. Use to establish what WILL and WILL NOT change, set success criteria, and create a focused refactoring scope.

Modern ES6+ JavaScript features including classes, modules, destructuring, iterators, proxies, and latest ECMAScript features.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

Master advanced TypeScript patterns including branded types, discriminated unions, conditional types, and design patterns.

This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability. Use this for identifying code smells, architectural issues, dependency problems, missing documentation, security vulnerabilities, and creating comprehensive technical debt documentation.

Manages HEC-HMS version differences (3.x vs 4.x), handles Python 2/3 compatibility,detects HMS installations, and generates version-appropriate Jython scripts. Use whenworking with legacy HMS 3.x projects, upgrading models from 3.x to 4.x, testing acrossmultiple HMS versions, or troubleshooting version-specific issues. Handles 32-bit vs64-bit architecture differences, memory limits, and script syntax variations.Trigger keywords: HMS version, HMS 3.x, HMS 4.x, legacy, upgrade, Python 2 compatible,32-bit, 64-bit, version detection, multi-version testing.

Python package manager and project tooling using uv. Use when working with Python projects, managing dependencies, creating virtual environments, running Python scripts, configuring workspaces/monorepos, or troubleshooting uv issues. Triggers on pyproject.toml projects, uv commands, pip replacement workflows, Python version management, workspace configuration, or CI/CD Python setup.

Build self-contained Python executables using uv script metadata.

Split large Python files into multiple files organized as a package. Use when user says "split this file", "this file is too big", "break this into multiple files", or similar requests for Python (.py) files.

JavaScript security best practices and vulnerability prevention.

Scaffolds a new Python tool file in 'src/tools/' from a template. Use when asked to create a new agent tool.

Analyze GitHub repository security alerts and generate remediation plans. Use when the user asks to review security alerts, fix vulnerabilities, check dependabot alerts, review code scanning issues, or address secret scanning findings for a GitHub repository. Triggers on requests mentioning GitHub security, repo security review, vulnerability remediation, or security audit.

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.