Chapter 00 | Course Introduction and Panoramic Roadmap (Syllabus)

Welcome to the future of programming. This isn't your average course on using ChatGPT to solve algorithm problems. Instead, it's about building, arming, and managing a virtual development team fully driven by Agents (Intelligent Agents).

We will build a real, cross-platform "Bidirectional Synchronized Time Block and Calendar Management System" from 0 to 1. You won't need to write tedious CRUD operations yourself; your role will shift to Chief Architect and Product Owner.

---

The 30-Episode Syllabus

Phase 1: Infrastructure & Mindset

• Ep 01: [The Origin: One-Pager from a Human Perspective]: Agents are not psychics. You must learn to write minimal yet highly binding Intent One-Pagers as the project's catalyst.
• Ep 02: [Antigravity Environment Setup]: Build the physical shell and multi-repo structure of the project, understanding why systems need clear scopes and tool boundaries.
• Ep 03: [Soul Implantation via GEMINI.md]: Write the "Code of Hammurabi" for the Agentic era. No erasing old logic; no "clever" over-engineering allowed.
• Ep 04: [Skill Engine using-superpowers]: Parse mandatory interception mechanisms. Force AI to consult local manuals before writing a single line of code.
• Ep 05: [Physical Plugin planning-with-files]: The only rule to break LLM token limits—disk-based memory (task_plan.md, findings.md).
• Ep 06: [Building the First Pipeline]: Create the foundational logic in .agents/workflows/.

Phase 2: Agent-Driven Architecture

• Ep 07: [Human-Agent Debate and PRD Fission]: Feed the One-Pager to the Agent and let an architect with a "skeptic" persona help you foresee system pitfalls.
• Ep 08: [Database Selection Stress Testing]: Let the Agent write research reports in findings.md and you make the final call (e.g., choosing Prisma).
• Ep 09: [Schema Design Automation]: Create database-migration.md and command the system to generate User/Task/Event models.
• Ep 10: [Challenge R&D: Google Calendar OAuth]: Use the system's research tools to collect API specs, avoiding middle-of-development discovery of limitations.
• Ep 11: [Large-Scale Operations: Task Breakdown]: Let the Agent automatically translate a grand PRD into 30 specific [ ] coding actions in task_plan.md.

Phase 3: No Code Without Tests (TDD Workflows)

• Ep 12: [Golden Rules of Refactoring TDD]: Why tests are the guardrails in the Agent era. Without tests, the entire codebase will collapse in three seconds.
• Ep 13: [Configuring test-driven-development Skill]: Establish a Red-Green-Refactor AI workflow.
• Ep 14: [The Battle of Local Time Management Algorithms]: First line of code! Verify how your Agent finds a way out amidst constant error reports.
• Ep 15: [The 3-Strike Safety Protocol]: Learn how the Agent hands over execution to you after 3 failures.
• Ep 16: [Minimalist External Interface Mocking]: Isolate tests to ensure calendar functionality works locally.

Phase 4: External Integrations

• Ep 17: [Security Audit of OAuth 2.0 Implementation]: No guesswork; let the Agent generate code based on a security checklist.
• Ep 18: [Writing the Mental Model for Bidirectional Sync]: The biggest trap in calendar apps: data conflict resolution. "Arbitration logic" written by the Agent and approved by you.
• Ep 19: [Webhook Integration]: Integrate real-time change events and establish an asynchronous queue mechanism for fallback.
• Ep 20: [System-Level Code Refactoring]: When the project reaches 20,000 lines, learn how to isolate "bad code" regions for safe cleaning by AI.
• Ep 21: [Adapter Pattern for Complex Data]: Flatten Google's messy calendar objects into the project's unified Event format.

Phase 5: Autonomous E2E & Delivery

• Ep 22: [Rules of the Game for E2E Testing]: Set up e2e-testing.md and launch automated click tests in a headless browser.
• Ep 23: [Writing Playwright Like a Human]: How the Agent analyzes the DOM and verifies successful page popups.
• Ep 24: [Injecting Doomsday Assertion Mechanisms]: Writing assertions for system behavior under anomalies like network/server downtime.
• Ep 25: [Cyber Reviewer Mechanism requesting-code-review.md]: Trigger a "grumpy" Senior Agent for a code critique before going live.
• Ep 26: [Standardized bug-fix.md Process]: The only correct way to fix bugs: Repro Test -> Change Code -> Sync Docs.
• Ep 27: [Frontend Performance and Packaging Diagnostics]: Use the Agent to run scripts, collect metrics, and implement component splitting.
• Ep 28: [Automated Conventional Commits]: Teach the Agent to proactively push code (Git push workflow).
• Ep 29: [Session Archiving session-archive.md]: How to elegantly archive today's progress for your tomorrow self.
• Ep 30: [Grand Finale: Team Handover Mode]: How to write a README and transition the system into a low-cost maintenance and inspection phase after going live.

---

Author's Note: Don't hand-code business logic. Restrain your hands. Your task is only to conduct the "symphony." In the next session, we will start from the core beginning: how to write "that idea" in your head?