LLM 與 Agent

Agent Skills のスキルレビューを行い、公式仕様への準拠とベストプラクティスの観点で指摘と改善案を提示する。スキルのレビュー依頼、SKILL.mdの品質確認、スキル構成の妥当性チェック、Agent Skills仕様への適合性評価の文脈で使用する。

Use this skill when implementing, modifying, or fixing ANY scraper, discovery, or extraction code in the packages/scrapers directory. Triggers for tasks involving SmartDiscoveryAgent, SmartDishFinderAgent, PuppeteerFetcher, search engines, platform adapters, or related components. Orchestrates a rigorous test-driven workflow with use case definition BEFORE coding, followed by verification.

Use when executing implementation plans with independent tasks in the current session

Patterns for persisting and retrieving application data. Use when implementing data persistence, caching, or session management.

Guide for creating effective skills. Use this skill when you want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use when distributing multiple tasks across agents or VMs - handles work manifests, dependency graphs, parallel execution, agent coordination, and failure recovery for batch development workflows

Active Directory operational hygiene analyzer for OpsIdentity project. Detects administrative disorder, architectural debt, and suboptimal configurations—not offensive security. Use when (1) improving OpsIdentity PowerShell collection functions, (2) adding AI analysis prompts to server.js, (3) analyzing coverage gaps against 87 industry metrics, (4) implementing smart filtering or anti-hallucination rules. Triggers on AD health, GPO analysis, replication, trusts, token size, FSMO, site topology, DNS/DHCP hygiene, or requests to analyze existing OpsIdentity code.

This skill teaches the agent how to implement the business logic layer in the API project. MANDATORY - You MUST read this skill before modifying any service files.

Create Claude Code skills with proper structure, frontmatter, and best practices. Use when the user wants to create a new skill, write a SKILL.md file, or needs help structuring a Claude Code plugin.

Systematic code review guidelines and checklist. Use this skill when reviewing code, conducting pull request reviews, or establishing code quality standards. Provides comprehensive review criteria covering functionality, design, testing, security, and documentation. Complements the code-quality agent.

Expert on integrating Shelby Protocol decentralized storage into applications. Helps with use case evaluation, architecture design, migration strategies, cost optimization, performance tuning for video streaming, AI training, data analytics, content delivery, and read-heavy workloads. Triggers on keywords integrate Shelby, decentralized storage integration, video streaming storage, AI training data, data analytics storage, migration to Shelby, storage architecture, content delivery, Shelby use case.

Guide for Grafana Pyroscope continuous profiling. Use for Kubernetes Helm deployment, Go/Java/Python/.NET/Ruby/Node.js profiling, storage backends, trace-to-profile linking, and troubleshooting.

Query and interact with Prometheus HTTP API for monitoring data. Use when Claude needs to query Prometheus metrics, execute PromQL queries, retrieve targets/alerts/rules status, access metadata about series/labels, manage TSDB operations, or troubleshoot monitoring infrastructure. Supports instant queries, range queries, metadata endpoints, admin APIs, and alerting information.

Expert guidance for implementing BRC-100 conforming wallets using Go wallet-toolbox. Covers wallet initialization, transaction creation/signing, key management, storage, and certificate operations following the BRC-100 standard in Go.

创建新的 Agent Skill 或优化现有 Skill。当用户需要编写 SKILL.md、审查 Skill 质量、改进 Skill 结构、或学习 Skill 最佳实践时使用。根据官方创作指南自动生成符合规范的 Skill 文件。

Browser automation for development and testing. Use when showing UI progress to user, writing e2e tests, or testing complex interactions (drag/drop, keyboard nav).

Create feature specifications using Specification-Driven Development (SDD) methodology.Use when starting a new feature, documenting requirements, or executing the /specify command.This skill guides the creation of comprehensive feature specifications following the SDDframework's spec-template.md structure. It ensures specifications include all requiredsections, validates completeness, detects domains/agents needed, and prepares for theplanning phase.Triggered by: /specify command, user request for "specification", "requirements","feature spec", or "document requirements".

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Use this skill when creating, optimizing, or improving prompts for large language models. Applies when users need help designing effective prompts, selecting appropriate prompting techniques, or troubleshooting prompt performance. Provides expert guidance through conversational consulting to build prompts using research-backed best practices and proven patterns.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.