LLM 與 Agent

Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities.

This skill should be used when the user asks about "Cloudflare", "Workers", "Pages", "R2", "D1", "KV", "Durable Objects", "Queues", "Vectorize", "AI Gateway", "Hyperdrive", "Cloudflare API", "Wrangler", "Cloudflare documentation", "how to deploy to Cloudflare", "Cloudflare best practices", "Cloudflare pricing", "Cloudflare limits".

Hybrid skill for OpenCode plugin development - behavioral patterns for agents and technical reference for humans

Integrate cadrianmae marketplace plugins into CLAUDE.md. Scans installed plugins and generates documentation section listing available skills and commands. User chooses between user-level (global) or project-level (current project only) integration.

Sophisticated multi-agent AI research system that conducts comprehensive, academic-quality research on complex topics through orchestrated specialist agents. Use for deep research requiring academic, technical, and data-driven perspectives with quality assurance and comprehensive reporting.

Pattern-based bulk code transformations across multiple files

Interact with the MicroTutor Moodle LMS via REST API to manage courses, users, enrollments, assignments, quizzes, forums, and grades. Use when the user says "use the api" or asks to query, create, update, or manage any Moodle content including course data, student enrollments, activity modules, submissions, or grades.

Search and download royalty-free images and videos from Pixabay. This skill should be used when the user needs stock photos, illustrations, vectors, or videos for projects. Supports filtering by type, category, color, orientation, and more.

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.