LLM 與 Agent

7 product marketing skills + 6 specialist agents for go-to-market strategy,positioning, messaging, competitive intelligence, and launch coordination.

Optimize cloud storage across AWS S3, Azure Blob, and GCP Cloud Storage with compression, partitioning, lifecycle policies, and cost management.

Expert guide for Kaggle 5-Day AI Agents Intensive course materials (Day 1-5), VaaS capstone project, Google ADK, A2A protocol, multi-agent systems, and competition submission. Use when user asks about agent architectures, tools, memory, evaluation, A2A communication, VaaS business model, or capstone implementation.

Skill testing methodology - run scenarios without skill (RED), observe failures,write skill (GREEN), close loopholes (REFACTOR).

Development cycle feedback system - calculates assertiveness scores, analyzes promptquality for all agents executed, aggregates cycle metrics, performs root cause analysison failures, and generates improvement reports to docs/feedbacks/cycle-{date}/.

Implement offline-first mobile apps with local storage, sync strategies, and conflict resolution. Covers AsyncStorage, Realm, SQLite, and background sync patterns.

Implement secure session management systems with JWT tokens, session storage, token refresh, logout handling, and CSRF protection. Use when managing user authentication state, handling token lifecycle, and securing sessions.

Implement secrets management with HashiCorp Vault, AWS Secrets Manager, or Kubernetes Secrets for secure credential storage and rotation.

Concurrent investigation pattern - dispatches multiple AI agents to investigateand fix independent problems simultaneously.

Implement secure file upload handling with validation, virus scanning, storage management, and serving files efficiently. Use when building file upload features, managing file storage, and implementing file download systems.

Generates a complete fullstack application template with Python FastAPI backend and React Vite frontend. Includes OpenAI ChatGPT integration, CORS configuration, comprehensive error handling, and a modern Tailwind CSS + shadcn/ui React UI. Use this skill when the user wants to bootstrap a new fullstack web application project with both API backend and web frontend components ready to go.

Multi-model AI consultation and research. Supports CONSULTATION MODE (ask single expert), RESEARCH MODE (parallel multi-agent), or DELIBERATION MODE (agents debate and refine). USE WHEN user says 'ask gemini', 'consult codex' (consultation), 'do research' (research), or 'deliberate on' (deliberation).

Write comprehensive unit tests with high coverage using testing frameworks like Jest, pytest, JUnit, or RSpec. Use when writing tests for functions, classes, components, or establishing testing standards.

Fundamental reading and writing capability for the OCTAVE format. Inject this to give an agent basic structural competence without the overhead of full architectural specifications. Triggers on: octave format, write octave, octave syntax, structured output.

Advanced semantic vocabulary and architectural patterns for the OCTAVE format. REQUIRES octave-literacy to be loaded first. Use for designing agents, crafting high-density specifications, or system architecture. Provides access to the Semantic Pantheon (Archetypes) and holographic patterns. Triggers on: octave architecture, agent design, semantic pantheon, advanced octave.

Optimize warehouse and storage space utilization. Use this skill when maximizing storage density, planning storage layouts, calculating volume efficiency, or minimizing empty space in warehouses and containers.

Create well-defined task specifications from plans or user prompts. Use when user wants to define a task, create a work item, break down a plan into actionable work, or write a spec for implementation. Triggers on "create task", "define task", "write spec", "break this down", "make this actionable", or when moving from planning to execution.

UI/UX Designer for Claude Orchestrator. Creates design specifications with design tokens (colors, fonts, spacing) and component specs. Use when asked to create design specifications or define design tokens for the orchestrator.

Tech Lead for Claude Orchestrator. Creates implementation instructions based on planning documents and design specifications. Use when asked to create developer instructions or technical implementation guides for the orchestrator.

Perform vector similarity search using embeddings. Use when implementing semantic search, finding similar documents, or building recommendation systems. NOT needed for basic content aggregation or API integration.