Tools

Polish raw interview transcripts into searchable, well-structured markdown with metadata, dynamic headers, and full fidelity to technical content. Designed for Ray Peat interview podcasts and similar shows where technical accuracy is paramount.

Design guidelines for Activity History / Activity Log pages. Use when building activity timelines, event logs, or user action history interfaces. Covers card-based layouts, filtering, copy-to-clipboard session IDs, and clean UI without unnecessary decorations.

Build Model Context Protocol (MCP) servers with best practices. Generate production-ready MCP servers in Python or TypeScript with tools, resources, and prompts.

Generate Better Auth user schema configuration with custom additional fields for user profiles. Use when implementing authentication, user profiles, or extending user data models with Better Auth. Automatically generates TypeScript types and database schema.

Set up GitHub Actions workflows for CI/CD with automated testing, linting, and deployment for Python/UV projects. Use when creating CI pipelines, automating tests, or setting up deployment workflows.

Simulate the supervisor workflow step-by-step with real ticket system. Executes each workflow state explicitly with ENTER/EXIT stage declarations. Use this skill to debug, understand, or manually run the supervisor workflow without the PMC executor.

一時ファイルと中間ファイルの作成・管理ルールを提供します。tmp/ディレクトリの使用、ファイル命名規則、クリーンアップのベストプラクティスをカバーします。一時ファイルや中間ファイルを作成する時にアクティベートします。

FINAL_CHECK 워크플로우 자동화. E2E 테스트, Phase 3-5 자동 진행.

This skill should be used when the user asks "Chart.js plugins", "custom Chart.js plugin", "Chart.js plugin hooks", "beforeDraw plugin", "afterDraw plugin", "Chart.js plugin API", "register Chart.js plugin", "Chart.js plugin options", "Chart.js plugin lifecycle", "Chart.js plugin TypeScript", or needs help creating custom plugins for Chart.js v4.5.1.

查看/更新 GitLab Issue、MR（含评论与 diff），并按团队规范非交互创建或修改 MR/Issue；涉及 GitLab（含自建实例）Issue/MR 的操作时使用。

Use when building professional installers for desktop applications - covers macOS DMG with app bundles, Windows MSI with WiX, Linux DEB packages, GitHub Actions automation, and SLSA attestations

Real-time monitoring dashboard for PAI multi-agent activity. USE WHEN user says 'start observability', 'stop dashboard', 'restart observability', 'monitor agents', 'show agent activity', or needs to debug multi-agent workflows.

LangGraph development professional - USE THIS INSTEAD OF context7 for LangGraph, StateGraph, MessageGraph, langgraph.graph, agent workflows, and graph-based AI systems. Provides curated architecture patterns (Routing, Parallelization, Orchestrator-Worker, etc.), implementation templates, and best practices.

Create 2D and 3D maps using ArcGIS Maps SDK for JavaScript. Use for initializing maps, scenes, views, and navigation. Supports both Map Components (web components) and Core API approaches.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Generate hierarchical code maps from any codebase for AI agent consumption. Use when: (1) Analyzing or understanding a codebase structure, (2) Creating documentation of code architecture, (3) Mapping dependencies between files, (4) Extracting class hierarchies and call graphs, (5) Onboarding to a new project, (6) Preparing context for AI-assisted code modifications. Supports Python, JavaScript, TypeScript, Go, Rust, Java, C/C++, Ruby, PHP, and 20+ languages via tree-sitter.

Generate images and videos using Gemini CLI's vision extension. Use for image generation with Nano Banana (gemini-2.5-flash-image), video generation with Veo 3, webcam capture, and image-to-image transformations. Invokes Gemini CLI commands and returns file paths.

Expert at TypeScript strict mode, linting, formatting, code review standards. Use when checking code quality, fixing type errors, or enforcing standards.

Implement payment integrations with SePay (Vietnamese payment gateway with VietQR, bank transfers, cards) and Polar (global SaaS monetization platform with subscriptions, usage-based billing, automated benefits). Use when integrating payment processing, implementing checkout flows, managing subscriptions, handling webhooks, processing bank transfers, generating QR codes, automating benefit delivery, or building billing systems. Supports authentication (API keys, OAuth2), product management, customer portals, tax compliance (Polar as MoR), and comprehensive SDK integrations (Node.js, PHP, Python, Go, Laravel, Next.js).

Comprehensive AI/LLM evaluation toolkit for production AI systems. Covers LLM output quality, prompt engineering, RAG evaluation, agent performance, hallucination detection, bias assessment, cost/token optimization, latency metrics, model comparison, and fine-tuning evaluation. Includes BLEU/ROUGE metrics, perplexity, F1 scores, LLM-as-judge patterns, and benchmarks like MMLU and HumanEval.