LLM & Agents

Maintains SnowTower project documentation, README, and Claude configuration. Use when updating documentation, auditing .claude folder contents, syncing README with actual project state, or reviewing agent/pattern definitions. Triggers on mentions of documentation, README, maintenance, or .claude folder updates.

Generate an SVG of a user-requested image or scene

Use this agent when you need to design, implement, or optimize FastAPI backend applications. This includes API endpoint creation, database integration, authentication/authorization implementation, cloud deployment strategies, business logic architecture, performance optimization, and following FastAPI best practices.

Standardized protocol for describing UI/layout issues in screenshots. Helps Claude understand visual problems clearly on first look by using a structured format for image communication.

Pydantic-AI agents, RAG, embeddings for Pulse Radar knowledge extraction.

Make database schema changes in IdeaForge. Triggers: create migration, add table/column, modify column type, add index, use JSONB, use pgvector. File-based migrations with raw SQL, no ORM.

Processes research branches from Claude Code Web sessions - merges content, moves docs to docs/research/, and creates GitHub issues. Use when /popkit:next detects research branches or when manually processing research from mobile sessions. Do NOT use for regular feature branches - only for branches matching claude/research-* or containing research documentation.

PRAgent スキル - Pull Request自動作成・Conventional Commits準拠・Draft PR自動生成。コード実装完了後、GitHub PRを自動作成し、レビュワー割り当て・説明文生成・関連Issue紐付けを実行。Use when:- Pull Requestを作成する時- Conventional Commits形式のタイトルが必要な時- レビュワーの自動割り当てが必要な時- 関連Issueの紐付けが必要な時- "PR作成", "プルリクエスト", "マージ" がキーワードに含まれる時

Guidelines for creating custom rules, custom skills, and custom subagents for Claude.

Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.

Ensures comprehensive test coverage following Rails testing best practices

Configure Claude Code sandbox network isolation with trusted domains, custom access policies, and environment variables

Build production agentic applications on OCI using Oracle Agent Development Kit with multi-agent orchestration, function tools, and enterprise patterns

This skill analyzes incoming requests to optimize context usage, decompose tasks efficiently, and recommend the best execution strategy. It runs automatically to evaluate request specificity, identify necessary explorations, suggest subtask decomposition, recommend appropriate models, and coordinate MCP/Agent/Skill activations with user approval before execution.

Validates Testing Phase completion before advancing to Finalization Phase. Checks test execution results, coverage targets, test quality, and environment health. Ensures 100% test pass rate required by quality gates.

Use when researching AI agents, LLMs, hosting solutions, OCR technologies, video generation models, or evaluating technology stacks. Apply when user asks to research, compare, evaluate, or investigate technologies, frameworks, models, or tools. Use proactively when technical decisions require research backing.

How to properly create Claude Code skills - teaches global vs project-local, naming conventions, and proper file structure

Increase test coverage from 0% to 80%+ in ANY project, ANY testing framework

Use PROACTIVELY when developing Claude Code hooks to implement content-based deduplication and prevent duplicate insight storage across sessions

Fine-tuning Speech-to-Text models like Whisper using Unsloth's optimized LoRA pipeline. Triggers: stt, whisper, transcription, audio fine-tuning, speech-to-text, audio normalization.