LLM & Agents

Add MCP servers to Claude Code configuration at user level (~/.claude). Supports stdio, HTTP, and SSE transports with environment variable prompting. Use when "add mcp server", "install mcp", "configure mcp server", "new mcp", or "setup mcp server".

Create detailed implementation plans through interactive research and iteration. Use this skill when needing to plan a feature, refactor, or bug fix before implementation. The skill orchestrates research agents (codebase-locator, codebase-analyzer, codebase-pattern-finder) to understand the codebase, then works collaboratively with the user to produce comprehensive technical specifications with phased implementation steps and success criteria.

This skill provides comprehensive guidance for inter-agent communication using the Synapse A2A framework. Use this skill when sending messages to other agents, routing @agent patterns, understanding priority levels, or handling A2A protocol operations. Automatically triggered when agent communication or A2A protocol tasks are detected.

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.

19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.

Search and retrieve information from indexed PDF documentation including IC datasheets, FPGA manuals, and technical specifications. Use this when the user asks about hardware specifications, pin configurations, register details, timing diagrams, or any technical information that might be in datasheets or technical documentation.

Use an AI agent with full access to a certain external repository to research. Useful when writing code involving a library to get code examples and information. Use when the user suggests to research how to do something with a certain library.

Use when transforming presentations from basic to professional quality - employs parallel multi-agent execution, research-driven design, and McKinsey/BCG/Deloitte best practices to create executive-ready decks

Manage TASK_BOARD.md by reading project logs and synchronizing task status. Use when tasks are completed, when progress is made, or when needing to sync task tracking. Reads MIGRATION_LOG.md, DEBUG_LOG.md, GIT_LOG.md to assess actual progress and updates TASK_BOARD.md accordingly. Does NOT modify CLAUDE.md or MIGRATION_LOG.md.

Build intent routers for agent task distribution

Automatically trigger review agents after task completion. Use when strategic-planner finishes planning tasks (calls plan-consultant) or when main agent completes coding tasks in /implement workflow (calls code-reviewer). Triggers on phrases like "plan complete", "implementation done", "coding finished", "ready for review".

Use CloudBase HTTP API to access CloudBase platform features (database, authentication, cloud functions, cloud hosting, cloud storage, AI) via HTTP protocol from backends or scripts that are not using SDKs.

⚡ PRIMARY TOOL for: 'what's tested', 'find test coverage', 'audit test quality', 'missing tests', 'edge cases', 'test patterns'. Uses claudemem v0.3.0 AST with callers analysis for test discovery. GREP/FIND/GLOB ARE FORBIDDEN.

Use when starting work on an unfamiliar project or needing to understand a codebase - performs comprehensive analysis discovering architecture, patterns, dependencies, testing coverage, and improvement opportunities. Do NOT use on projects you already know well or for targeted questions about specific files - use direct exploration instead for focused queries.

Generate comprehensive pytest test suites for CasareRPA components, including nodes, controllers, use cases, and domain entities. Use when: creating new tests, testing nodes, controller tests, use case tests, domain entity tests, test coverage needed, pytest test generation.

Android development assistant for Kotlin, Jetpack Compose, and modern Android apps. Supports project initialization, MVVM/MVI architecture setup, CI/CD configuration, and feature implementation. Activated when users mention "Android", "Kotlin", "Jetpack Compose", or need Android app development help.

Analyze coding agent sessions to improve or create skills for Claude Code, Pi, and Codex.

Testing strategy and test pyramid for EFT-Tracker. Guides when to write unit, integration, E2E, or smoke tests. Includes MSW patterns, Playwright best practices, and contract testing. Activates when user mentions: test, unit test, integration test, E2E, Playwright, MSW, coverage, mock, test pyramid, vitest.

This skill should be used when the user asks to "edit code", "modify files", "refactor code", "update functions", "change implementations", or needs to make code changes using MorphLLM's ultra-fast edit_file tool (10,500+ tokens/sec, 98% accuracy).

This skill should be used when starting any feature or bug fix, exploring unfamiliar code, making commits or PRs, or when unsure which agent or approach to use. Covers agent routing, git discipline, testing workflow, and proactive quality practices.