LLM 與 Agent

Expert iOS App Store submission and approval system. 9 specialized agents providing senior App Review Team-level expertise across compliance, design, privacy, monetization, metadata, technical requirements, timing, rejection recovery, and learning. Triggers on keywords like app store, iOS submission, apple review, app rejection, aso, privacy manifest, privacy labels, ATT, iap, in-app purchase, subscription, storekit, review guidelines, HIG, testflight, app store connect.

Agentic execution protocols for Claude Code with verification gates, rollback mechanisms, and confidence thresholds. Triggers on any destructive or high-risk operations.

Agent workflow for generating highly diverse creative content using Verbalized Sampling (VS) technique. Use when user requests multiple variations, brainstorming, creative ideas, or when standard prompting produces repetitive outputs. Increases diversity by 1.6-2.1× while maintaining quality. Works for: blog posts, social media captions, stories, campaign ideas, product descriptions, taglines, and open-ended creative tasks.

Guidance for Home Assistant configurations. Use when writing automations, dashboards, or service calls for HA.

创建有效技能的指南。当用户想要创建新技能（或更新现有技能）来扩展Claude在专门知识、工作流程或工具集成方面的能力时，应该使用此技能。

HashiCorp Vault operations including secrets engines (KV, AWS, Azure, GCP, Database, PKI), auth methods (Token, AppRole, Kubernetes, OIDC, AWS), policies and ACLs, dynamic credentials, secret rotation, Terraform integration, agent sidecar patterns, audit logging, high availability, and disaster recovery. Activate for Vault secret management, credentials automation, and security configuration.

Integrate Replicate AI models with background processing, S3 storage, and credit systems

Convert technical blueprints into actionable work orders and implementation tasks

Guide for creating and validating Claude Code plugin.json files with schema validation tools

Help with creating and managing Claude Code skills. Use when the user asks about creating skills, skill structure, or customizing Claude Code behavior.

Agent SDK development utilities for creating, testing, and managing AI agents with comprehensive tooling and debugging capabilities.

Transfer conversation to human agent. Use when customer explicitly requests human support, issue is too complex, customer is frustrated, or situation requires human judgment.

Strategies for continued pretraining and domain adaptation in Unsloth (triggers: continued pretraining, CPT, domain adaptation, lm_head, embed_tokens, rsLoRA, embedding_learning_rate).

Expert guidance for DeepAgents framework - simplified agent creation with tool integration for LangChain/LangGraph workflows.

Expert RPG map creation and generation for tabletop and online games. Specializes in creating visual descriptions and optimized prompts for z-image turbo model in ComfyUI. Covers all map types (world/continent, regional/local, battle/encounter, dungeon/interior) across multiple themes and settings (fantasy, sci-fi, cyberpunk, post-apocalyptic, horror, etc.). Use when Claude needs to: (1) Create RPG maps of any type, (2) Generate image prompts for map visualization in ComfyUI, (3) Design environments, biomes, settlements, or tactical battlefields, (4) Provide expert knowledge of cartography, terrain, and world-building for games, (5) Convert map descriptions into optimized prompts for image generation models, or (6) Help with any map creation or visualization for tabletop RPGs, video games, or online play.

A Claude Code skill for detecting flaky test patterns that cause intermittent CI failures.

Google File Search API templates, configuration patterns, and usage examples for managed RAG with Gemini. Use when building File Search integrations, implementing RAG with Google AI, chunking documents, configuring grounding citations, or when user mentions Google File Search, Gemini RAG, document indexing, or semantic search.

Expert guide for handling file uploads, image optimization, cloud storage (Supabase, S3, Cloudinary), and file management. Use when implementing file upload features or managing user assets.

This skill should be used when reviewing, auditing, or improving existing Claude Code skills to ensure they follow Anthropic best practices, have proper structure, use current domain-specific patterns, and include all necessary resources. It analyzes skill quality, identifies gaps, suggests improvements, and can automatically enhance skills with updated best practices. Trigger terms include review skill, audit skill, improve skill, enhance skill, update skill, check skill quality, skill best practices, fix skill, optimize skill, validate skill structure.

This skill should be used when translating a spec into code using parallel subagents. Use when the orchestrator invokes the implement phase or when executing a well-defined implementation plan.