LLM & Agents

Complete Windows file path troubleshooting knowledge for Claude Code on Git Bash and Windows environments. PROACTIVELY activate for: (1) File path errors on Windows, (2) Backslash vs forward slash issues, (3) Edit/Write/Read tool failures, (4) MINGW path resolution, (5) Cross-platform path conversion.

Cloudflare R2 object storage with S3-compatible API and zero egress fees

Single source of truth and librarian for ALL Claude official documentation. Manages local documentation storage, scraping, discovery, and resolution. Use when finding, locating, searching, or resolving Claude documentation; discovering docs by keywords, category, tags, or natural language queries; scraping from sitemaps or docs maps; managing index metadata (keywords, tags, aliases); or rebuilding index from filesystem. Run scripts to scrape, find, and resolve documentation. Handles doc_id resolution, keyword search, natural language queries, category/tag filtering, alias resolution, sitemap.xml parsing, docs map processing, markdown subsection extraction for internal use, hash-based drift detection, and comprehensive index maintenance.

Design multi-agent AI systems including orchestration patterns, tool design, memory management, and error handling for autonomous agents.

Audit a codebase for the 12 leverage points of agentic coding. Identifies gaps and provides prioritized recommendations. Use when improving agentic coding capability, analyzing why agents fail, or optimizing a codebase for autonomous work.

Meta knowledge for creating Claude skills. Provides templates, best practices, and patterns for building effective skills with routing tables and reference files. Load this when creating new skills or understanding the skill system. Triggers: create skill, new skill, skill template, skill architecture, SKILL.md.

Guide creation of focused single-purpose agents following the One Agent One Prompt One Purpose principle. Use when designing new agents, refactoring general agents into specialists, or optimizing agent context for a single task.

Professional software QA and code review skill for ensuring code quality,comprehensive test coverage, standards compliance, and security throughrigorous testing and validation workflows.

claude-in-chrome MCPツールを使用したインタラクティブブラウザ自動化。 最適な用途: デモ、ドキュメントGIF、手動テスト、ライブブラウザ制御。 CI/CDでの自動E2Eテストには、代わりにwebapp-testingスキルを使用。 トリガー: browser automation, ブラウザ自動化, screenshot, スクリーンショット, form fill, フォーム入力, click, navigate, GIF recording, GIF録画, ブラウザ操作, Chrome, demo, デモ, live browser.

Use when switching between LLM providers, accessing provider-specific features (Anthropic caching, OpenAI logprobs), or using raw SDK clients - covers multi-provider patterns and direct SDK access for OpenAI, Anthropic, Google, and Ollama

Guide for creating Claude Code hooks with proper configuration, shell commands, event handling, and security practices. Use when the user wants to create hooks, automate workflows, add event handlers, format code automatically, protect files, log actions, or mentions creating/configuring/building hooks.

Analyze Flutter and mobile applications for OWASP Mobile Top 10 (2024) security compliance. Use this skill when performing security audits, vulnerability assessments, or compliance checks on mobile applications. Performs automated scans for hardcoded secrets, insecure storage, weak cryptography, network security issues, and provides detailed remediation guidance.

Example skill demonstrating Claude Code capabilities. Activates when user mentions "example", "demo", or "template". Shows how to create effective Skills with proper structure. Use when user wants to see skill examples or understand skill creation.

Build observability interfaces for multi-agent systems. Use when monitoring multi-agent execution, tracking agent metrics, implementing logging for parallel agents, or debugging agent workflows.

Guide creation of meta-prompt templates that encode engineering workflows into reusable, scalable units. Use when creating slash commands that generate plans, designing workflow templates, or encoding team best practices into agentic prompts.

Use when planning, scaffolding, validating, or packaging Claude skills inside Advanced Memory MCP.

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

Add console output and logging to make errors visible to agents. Standard out is a critical leverage point - without it, agents cannot see errors or understand application state. Use when agents fail silently, when debugging agentic workflows, or when setting up a new codebase for agentic coding.

릴리스 노트 작성. 시작/끝 태그를 받아 ICJC-Backend, ICJC-Frontend, ICJC-Agent 서브모듈의 변경사항을 분석하여 사용자 친화적인 릴리스 노트를 생성한다. "릴리스 노트", "release notes", "변경사항", "업데이트 내역" 등 요청 시 사용.

Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus.