AI & ML

majiayu000 Bundle

Deliver repeatable MotherDuck architectures across multiple clients. Use when standardizing isolation, provisioning, regional deployment, sharing boundaries, and client-specific exceptions for a consultancy or partner delivery model.

majiayu000 Bundle

Add integration tests for type checker inference and checking functions

majiayu000 Bundle

Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.

majiayu000 Bundle

Use local Codex/Claude JSONL logs as evidence, then produce a human-written daily diary summary and write it into Obsidian. Keep directory filtering (for example rag-flow/rag-recall) and avoid mechanical script-style output.

majiayu000 Bundle

Multi-agent debate system. USE WHEN council, debate, perspectives, agents discuss. SkillSearch('council') for docs.

majiayu000 Bundle

Worker that runs parallel external agent reviews (Codex + Gemini) on Story/Tasks. Background tasks, process-as-arrive, critical verification with debate. Returns filtered suggestions for Story validation.

majiayu000 Bundle

Optimize multi-tool workflow chains via MCP server integration for processing large datasets, files, or complex pipelines.

majiayu000 Bundle

LDE（Law-Driven Engineering）のLaw Card作成スキル。 ビジネス上の「守るべき条件」を標準フォーマットで文書化する。 使用タイミング: (1) 新しいLawを追加する時、(2) 既存Lawを更新する時、 (3) Law Catalogに新規エントリを追加する時、(4) Grounding Mapを更新する時

majiayu000 Bundle

LDE（Law-Driven Engineering）のLink Map（連結表）管理スキル。 Law ↔ Term の相互参照関係を可視化し、孤立の検出と影響分析を行う。 使用タイミング: (1) Law Cardを作成した後、(2) Term Cardを作成した後、 (3) 「Link Mapを更新して」「孤立チェックして」、(4) 変更影響分析時

majiayu000 Bundle

タスクの性質を LLM ベースで深く分析し、適切な executor（claudecode/codex/coderabbit/user）を判定する専門 Skill。キーワードベースの単純判定を置き換える。

majiayu000 Bundle

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

majiayu000 Bundle

Cursor ↔ Claude Code 2-Agentワークフローのガイダンスを提供。Use when user asks about workflow, collaboration, or process. Do NOT load for: implementation work, workflow setup, or executing handoffs.

majiayu000 Bundle

Expert guide for crafting high-performance Claude prompts, based on Anthropic's interactive tutorial.

majiayu000 Bundle

LDE（Law-Driven Engineering）のTerm Card作成スキル。 ドメインの語彙（Vocabulary）を標準フォーマットで文書化し、名辞抽象を具体化する。 使用タイミング: (1) 新しいTermを追加する時、(2) 既存Termを更新する時、 (3) Vocabulary Catalogに新規エントリを追加する時、(4) Phase Dでカード化する時

majiayu000 Bundle

Generates TypeScript type definitions for SDK from Rust tool schemas, ensuring type safety between server and client

majiayu000 Bundle

Apply the Agent OS standard for global commenting.

majiayu000 Bundle

Use when working with .swift files, Xcode projects, SwiftUI/UIKit, or iOS-specific features

majiayu000 Bundle

Modern Dart standards (3.x+) including null safety and patterns.

majiayu000 Bundle

LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.

majiayu000 Bundle

Research standards/patterns via MCP Ref. Generates Standards Research for Story Technical Notes subsection. Reusable worker.

majiayu000 Bundle

Create .prompt files for LLM operations in Output SDK workflows. Use when designing prompts, configuring LLM providers, or using Liquid.js templating.

majiayu000 Bundle

Chrome Extension Manifest V3 development specialist covering service workers, content scripts, message passing, chrome.* APIs, side panel, declarativeNetRequest, permissions model, and Chrome Web Store publishing. Use when building browser extensions, implementing content scripts, configuring service workers, or publishing to Chrome Web Store. [KO: 크롬 확장 프로그램, 매니페스트 V3, 서비스 워커, 콘텐츠 스크립트] [JA: Chrome拡張機能、マニフェストV3、サービスワーカー] [ZH: Chrome扩展程序、Manifest V3、Service Worker]

majiayu000 Bundle

Orchestrates the PAW Review workflow, coordinating activity skills to analyze PRs and generate comprehensive review feedback.

majiayu000 Bundle

Apply the Agent OS standard for backend migrations.

majiayu000 Bundle

Generates RBS type signatures from Ruby source files. Triggers when creating type definitions, adding types to Ruby code, or generating .rbs files for classes/modules without existing RBS signatures.

majiayu000 Bundle

Single-agent implementation: executes plans in-place without subagents. Use /implement (default) for complex features; use this for simpler tasks or when subagent overhead is unwanted.

majiayu000 Bundle

Manage git worktrees with PR workflow and multi-agent review (Claude + Codex). Use when developing features in isolation with easy rollback.

majiayu000 Bundle

Configure un serveur MCP (Model Context Protocol) dans Cursor en ajoutant l'entrée appropriée dans le fichier mcp.json. Supporte les serveurs Supabase Edge Functions, n8n et les serveurs locaux via npx. Utilise ce skill lorsque l'utilisateur demande d'ajouter, modifier ou configurer un serveur MCP dans Cursor.

majiayu000 Bundle

AI-powered virtual laboratory orchestrating multi-agent scientific research teams for autonomous hypothesis generation, experimental design, and validation in biomedical research.

majiayu000 Bundle

MUST be loaded before working with any Skill. Covers creating, building, reviewing, assessing, checking, auditing, evaluating, updating, modifying, and improving skills. Invoke PROACTIVELY before writing or changing any SKILL.md file. Provides structure, workflows, and validation for skill development. Supports both personal skills and standalone distributable skills (GitHub repos). (user)

majiayu000 Bundle

Apply the Agent OS standard for global coding style.

majiayu000 Bundle

The LlamaIndex Wolfram Alpha tool enables agents to interface with the Wolfram|Alpha LLM API for computational knowledge queries. It provides concise text-based answers optimized for LLM consumption,

majiayu000 Bundle

Cursor PMでアイデアを検証し、Plans.mdを更新してバトンタッチ。2-Agentワークフロー対応。

majiayu000 Bundle

Set up a Ralph execution loop in Beads by mapping a DevAgent plan into a Beads epic and tasks with the correct fields, dependencies, and routing labels. Use when: (1) Preparing Beads for Ralph autonomous execution, (2) Assigning correct routing labels and agents, (3) Ensuring dependencies and report tasks are wired, (4) Embedding plan references, quality gates, and context into Beads fields.

majiayu000 Bundle

Regenerate skill indexes for IDEs without native skill support (Kiro, Gemini, etc.). ONLY use when the user EXPLICITLY asks to "update skill index", "sync agents", "regenerate index", or "update AGENTS.md". Do NOT auto-invoke after creating/modifying skills - Claude Code has native skill support and does not need this.

majiayu000 Bundle

用于制药和临床研究环境中生成专业临床决策支持（CDS）文档，包括患者队列分析（基于生物标志物分层并结合结局分析）以及治疗推荐报告（基于循证指南并包含决策算法）。支持 GRADE 证据分级、统计分析（如风险比、 生存曲线、瀑布图）、生物标志物整合以及监管合规要求。输出为可发表级别的 LaTeX/PDF 格式，针对药物开发、临床研究和证据综合进行了优化。