LLM & Agents

Run repo startup: prompt load, checklist sync, optional PR triage, worktree hygiene, and CI pull. Best-effort with structured status.

Creates and configures stdio Model Context Protocol (MCP) server connections for OpenAI Agents SDK

Run .NET tests using dotnet CLI. Use when task involves executing unit tests, generating code coverage reports, or running benchmarks.

Chatbot agent for discovering high-impact AI agent deployment opportunities in potential client organisations. Conducts text-based discovery conversations to identify where Activate Intelligence's AI agent orchestration could deliver maximum value.

Claude Code Web/DesktopでE2Eテストを実行する手順。リモートConvexに接続してPlaywrightテストを実行する方法。

Test design patterns, best practices, and examples for comprehensive Solidity testing. Use when writing tests for smart contracts or improving test coverage.

Interpretive guidance for designing Claude Code hooks. Helps you understand hook lifecycle, when to use hooks vs other patterns, and common pitfalls. ALWAYS use when creating or reviewing hooks.

A skill that configures the agent to design, refactor, validate, and debug Pydantic v2 and v1 models, validators, and settings. Use this skill for structured data modeling, API schema generation, validation logic, or Pydantic version migration tasks.

Smart repo bootstrapping for Agentic flow (AGENTS.md)

Compétence optimisant Claude pour des tâches juridiques en droit français (Version 5.0). Utiliser lorsque l'utilisateur demande une assistance juridique, une analyse de droit français, une rédaction d'acte juridique, une consultation, une recherche juridique, une veille juridique, ou l'analyse de documents juridiques. Protection renforcée anti-hallucination des références. Cette compétence ne remplace pas l'expertise humaine - Ius est ars boni et aequi. Créée par Christophe Quézel-Ambrunaz, Université Savoie Mont Blanc.

Integrate Claude agents into training and live trading (v3.0). Trigger when: (1) setting up multi-agent training, (2) adding agent consultation to live trading, (3) configuring orchestrator, (4) understanding agent roles and safety mechanisms.

Provides CTO-level guidance for AI-first products, platforms, and org design. Makes pragmatic, execution-focused decisions optimized for product moat, safety, and shipping velocity.

Miyabi CoordinatorAgent統合スキル - DAGベースのタスク統括・並列実行制御。GitHub Issueを複数タスクに分解し、依存関係グラフを構築して並行実行を統括。Use when:- 複数タスクの並列実行が必要な時- Issueをタスク分解する時- DAG（有向非巡回グラフ）で依存関係を管理する時- Agent実行の統括・オーケストレーションが必要な時- "agent-run", "並列実行", "タスク分解", "DAG" がキーワードに含まれる時

Expert Node.js and TypeScript development assistant. Use when writing, reviewing, or debugging Node.js code, TypeScript projects, async programming, streams, performance optimization, or npm packages.

Guides creation of ChatGPT Apps with interactive widgets using OpenAI Apps SDK and MCP servers.Use when building ChatGPT custom apps with visual UI components, embedded widgets, or richinteractive experiences. Covers widget architecture, MCP server setup with FastMCP, responsemetadata, and Developer Mode configuration. NOT when building standard MCP servers withoutwidgets (use building-mcp-servers skill instead).

Guide for building applications on Cloudflare's edge platform. Use when implementing serverless functions (Workers), edge databases (D1), storage (R2, KV), real-time apps (Durable Objects), AI features (Workers AI, AI Gateway), static sites (Pages), or any edge computing solutions.

Automated E2E test infrastructure setup with Playwright, Vitest, MSW, and GitHub Actions. Generates 80%+ coverage tests based on REDR-prototype patterns.

Use when integrating MCP servers with Claude Code plugins - MCP configuration with transport types, scopes, and tool naming for November 2025 specifications

Generates complete, runnable RSpec tests for Rails models, services, controllers, and background jobs following project conventions. Use when new code is created without corresponding tests, when refactoring existing code, or when explicitly asked to add test coverage.

Node chain testing templates for quality agent. WorkflowBuilder patterns and tier-based testing. Use when: testing node chains, WorkflowBuilder patterns, tier-based testing, chain execution tests, simple/complex/full chain tiers.