設計

Specialized agent for creating, maintaining, and organizing comprehensive documentation for the BarqNet project. Records all changes, creates technical specifications, API documentation, user guides, deployment guides, and maintains documentation consistency across the entire codebase. Use when documenting features, creating guides, or organizing project knowledge.

Guidance for developing and editing legal casebooks

Expert HomeAssistant development skill for creating custom sensors (template, REST, command line, Python components), building Lovelace dashboards with custom cards and layouts, and developing custom integrations with config flows, coordinators, and multiple platforms. Use this skill when working with HomeAssistant YAML configuration, Python integration development, or dashboard customization.

CI/CD pipeline configuration for monorepo testing including GitHub Actions workflows, Turborepo integration, two-tier quality gates (typecheck→lint→test→build), preview branch integration, retry logic, and environment management. Use when configuring CI pipelines, troubleshooting CI test failures, implementing preview deployments, or optimizing CI performance. Triggers on: CI configuration, github actions testing, CI pipeline, turborepo CI, quality gates, preview integration, CI troubleshooting.

Creates elaborate, multi-component React artifacts using modern frontend technologies (React, Tailwind CSS, Framer Motion). Use when building new pages, sections, or complex component hierarchies. Triggers on requests for new features, landing sections, or UI components.

Manage computer storage and clean up disk space. Use this skill when the user needs to find large files, detect duplicate files, remove unused applications, clear caches, or clean up Docker resources. Supports macOS, Windows, and Linux with platform-specific commands for storage analysis and cleanup operations.

Confidence-based code review that filters issues to 80+ threshold, eliminating false positives and noise. Reviews implementation against plan or requirements for bugs, quality issues, and project conventions. Use after completing major features, before merging to main, or after each task in multi-step workflows. Do NOT use for quick fixes, single-line changes, or when you need immediate feedback - the thorough review adds overhead best reserved for significant changes.

Performance guidelines and patterns for this system.

Generates comprehensive synthetic fine-tuning datasets in ChatML format (JSONL) for use with Unsloth, Axolotl, and similar training frameworks. Gathers requirements, creates datasets with diverse examples, validates quality, and provides framework integration guidance.

Master index of all available skills for development workflows. Use when needing guidance on which skill to apply or when starting work on any project.

Build and iteratively refine physics analysis specifications using analysis-specification-template.md. Use when the user asks to create or update an analysis spec, requests plots/histograms for a dataset, or describes a quick analysis task that should be formalized into a specification document.

Expert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent performance, or crafting system prompts.

Use this skill when implementing game UI addon interactions in SND macros. Covers crafting addons, shop addons, node access, and general game addon patterns.

Detects when a Claude Code session reaches a "wow moment" worth sharing with the team. A wow moment occurs during intensive back-and-forth discussions where both user and Claude deeply engage on a topic - repeatedly refining ideas, pushing back, questioning assumptions, and ultimately producing brilliant insights about effective human-AI collaboration. Triggers when the conversation shows signs of deep "cooking" - multiple sustained exchanges on the same topic, productive disagreements, or breakthrough moments emerging from persistent dialogue. This skill should stay alert throughout the session and invoke /show-ropes when a genuinely valuable agentic mindset insight emerges.

Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.

This skill should be used when docs-researcher agent needs guidance on "how to search documentation", "WebSearch query patterns", "filtering search results", "documentation research strategy", or "creating knowledge files". Provides systematic methodology for effective technical documentation research.

Use PROACTIVELY when creating new Claude Code skills from scratch. Automated generation tool following Claudex marketplace standards with intelligent templates, pattern detection, and quality validation. Supports guided creation, quick start templates, clone-and-modify, and validation-only modes. Not for modifying existing skills or non-skill Claude Code configurations.

Standard Operating Procedure for /plan phase. Covers research depth, code reuse detection, design pattern selection, and architecture planning.

Master AI and machine learning tools including TensorFlow, PyTorch, scikit-learn, LLMs, and prompt engineering. Use when building machine learning models, working with AI agents, or implementing data science solutions.

Build and run AI agents using Claude Code CLI. Use when developing autonomous agents, multi-agent systems, CI/CD automation, or scripting Claude for programmatic tasks. Covers authentication, headless mode (-p), JSON output parsing, tool restrictions, subagents, and orchestration patterns.