docs(planning): frontend milestones M6-M10 + alignment with M1-M5

docs/hackathon/README.md

@@ -0,0 +1,15 @@
+# Built with Opus 4.7: a Claude Code hackathon
+
+## About Event
+
+Join us again for Built with Opus 4.7: a Claude Code virtual hackathon!
+
+Opus 4.7 is our most capable model yet, and we’re excited for you to push the limits of what it can do. Whether you’re a seasoned engineer or newly a builder, show us what you can build in one week with Claude Code.
+
+Some projects will start from what you already know — show us the thing only you'd know to build, the problem in your work or community that takes weeks but should take hours. Others will start from what's next — show us something that's easier to demo than to explain, an idea that doesn't exist yet but should.
+
+We’ll select 500 participants and give each one $500 in Claude API credits to build for a week. Compete to win $100k in Claude API credits.
+
+Judges include Boris Cherny, Cat Wu, Thariq Shihipar, Lydia Hallie, Ado Kukic, and Jason Bigman from the Claude team.
+
+Note: This event is fully virtual. Space is limited to 500 participants. Maximum team size is two. All participants must submit an application for approval.

docs/hackathon/rules.md

@@ -0,0 +1,250 @@
+# **Participant Resources**
+
+Thank you for being part of the [Built with Opus 4.7: a Claude Code hackathon](https://cerebralvalley.ai/events/~/e/built-with-4-7-hackathon) as a builder 👋 This document contains all the key details you’ll need to make the most of the event.
+
+## **1. Discord Server Information**
+
+Join the hackathon Discord server here: [https://anthropic.com/discord](https://anthropic.com/discord)
+
+Please note: We will assign a custom role to your discord handle so you will be able to see the hackathon specific channels.
+
+## **2. Hackathon Schedule**
+
+- **Tuesday, April 21st**
+
+  - **12:00 PM (EST):** Virtual Kickoff – rules, prizes, judging, technical talks
+
+  - **12:30 PM (EST):** Hacking officially begins; team formation on Discord
+
+  - **5:00–6:00 PM (EST):** Anthropic office hours (#office-hours)
+
+- **Wednesday, April 22nd**
+
+  - **12:00–1:00 PM (EST):** Live Session One - AMA with [Thariq Shihipar](https://x.com/trq212), Member of Technical Staff at Anthropic (Claude Code)
+
+  - **5:00–6:00 PM (EST):** Anthropic office hours (#office-hours)
+
+- **Thursday, April 23rd**
+
+  - **All Day:** Hacking continues
+
+  - **11:00 AM–12:00 PM (EST):** Live Session Two - Overview of how to use Claude Managed Agents with [Michael Cohen](https://www.linkedin.com/in/michael-cohen1995/), Member of the Technical Staff at Claude Labs
+
+  - **5:00–6:00 PM (EST):** Anthropic office hours (#office-hours)
+
+- **Friday, April 24th**
+
+  - **12:00–1:00 PM (EST):** Live Session Three - with Mike Brown, 1st place winner of Built with Opus 4.6: insights, learnings, and where is he now?
+
+  - **5:00–6:00 PM (EST):** Anthropic office hours (#office-hours)
+
+- **Saturday, April 25th**
+
+  - **All Day:** Hacking continues
+
+  - **5:00–6:00 PM (EST):** Anthropic office hours (#office-hours)
+
+- **Sunday, April 26th**
+
+  - **12:00–1:00 PM (EST):** Live Session Four - Michal Nedoszytko, 3rd place winner of Built with Opus 4.6: insights, learnings, and where is he now?
+
+  - **5:00–6:00 PM (EST):** Anthropic office hours (#office-hours)
+
+  - **8:00 PM (EST):** Submissions due via CV platform
+
+- **Monday, April 27th**
+
+  - **All Day:** First Round Judging (asynchronous)
+
+- **Tuesday, April 28th**
+
+  - **12:00 PM (EST): Final Round Judging**
+
+    - Top 6 teams announced (#announcements)
+
+    - Final round Judging
+
+  - **12:45 PM (EST): Closing Ceremony**
+
+    - Top 3 revealed, celebration & closing remarks
+
+## **3. Hackathon Rules**
+
+To keep things fair and aligned with our goals, all teams must follow these rules:
+
+- **Open Source:** Everything shown in the demo must be fully open source. This includes every component - backend, frontend, models, and any other parts of the project - published under an approved open source license.
+
+- **New Work Only:** All projects must be started from scratch during the hackathon with no previous work.
+
+- **Team Size:** Teams may have up to **2** members.
+
+- **Banned Projects:** Projects will be disqualified if they: violate legal, ethical, or platform policies, use code, data, or assets you do not have the rights to.
+
+## **4. Problem Statements**
+
+### **1. Build From What You Know**
+
+Start from a real problem in a real place: your work, your community, a field you're close to. The process that takes weeks and should take hours. The thing someone you know still does by hand. Domain expertise beats credentials — show us the thing only you'd know to build.
+
+*Looks like:* the process that takes weeks and should take hours. The decision was made on gut because the data's too scattered to use. The thing someone you know still does by hand.
+
+### **2. Build For What's Next**
+
+Start from something that doesn't exist yet: a new way to work, learn, or make that only makes sense now that the tools have changed. An interface without a name. A workflow from a few years out. The best projects here are easier to demo than to explain
+
+*Looks like:* an interface that doesn't have a name yet. A workflow that changes how you do the thing, not just how fast. A first draft of how this will work in a few years when Claude is even more capable. 
+
+## **5. Anthropic-Provided Resources**
+
+### **Quickstarts**
+
+[Claude Code Quickstart](https://code.claude.com/docs/en/quickstart)
+
+[Claude API Quickstart](https://platform.claude.com/docs/en/get-started)
+
+[Claude Models Overview](https://platform.claude.com/docs/en/about-claude/models/overview)
+
+### **Docs**
+
+[Claude Code Docs](https://code.claude.com/docs)
+
+[Claude API Docs](https://platform.claude.com/docs/en/home)
+
+[MCP Docs](https://modelcontextprotocol.io/docs/getting-started/intro)
+
+[Agent Skills Docs](https://agentskills.io/home)
+
+### **Claude Managed Agents**
+
+[Docs](https://platform.claude.com/docs/en/managed-agents/overview)
+
+[Overview video](https://www.youtube.com/watch?v=NLWiIj47IdI)
+
+[Claude Managed Agents: get to production 10x faster](https://claude.com/blog/claude-managed-agents) (*blog*)
+
+[Scaling Managed Agents: Decoupling the brain from the hands](https://www.anthropic.com/engineering/managed-agents) (*blog*)
+
+### **Blogs**
+
+[Claude Code Best Practices](https://code.claude.com/docs/en/best-practices)
+
+[Building Effective Agents](https://www.anthropic.com/engineering/building-effective-agents)
+
+[Building Agents with the Claude Agent SDK](https://claude.com/blog/building-agents-with-the-claude-agent-sdk)
+
+[Building multi-agent systems: when and how to use them](https://claude.com/blog/building-multi-agent-systems-when-and-how-to-use-them)
+
+[Best practices for prompt engineering](https://claude.com/blog/best-practices-for-prompt-engineering)
+
+[Effective Context Engineering](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents)
+
+[Extending Claude’s capabilities with skills and MCP servers](https://claude.com/blog/extending-claude-capabilities-with-skills-mcp-servers)
+
+[Skills explained: How Skills compares to prompts, Projects, MCP, and subagents](https://claude.com/blog/skills-explained)
+
+[Building agents with Skills: Equipping agents for specialized work](https://claude.com/blog/building-agents-with-skills-equipping-agents-for-specialized-work)
+
+[Claude Code power user customization: How to configure hooks](https://claude.com/blog/how-to-configure-hooks)
+
+### **Courses**
+
+[Claude Code in Action](https://anthropic.skilljar.com/claude-code-in-action)
+
+[Agent Skills with Anthropic](https://www.deeplearning.ai/short-courses/agent-skills-with-anthropic/)
+
+[Claude Code Courses GitHub](https://github.com/anthropics/courses)
+
+### **Other**
+
+[Claude Quickstarts](https://github.com/anthropics/claude-quickstarts) - A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API 
+
+[A Complete Guide to Building Skills for Claude (eBook)](https://claude.com/blog/complete-guide-to-building-skills-for-claude)
+
+[Claude Cookbooks](https://platform.claude.com/cookbook/) and [Cookbooks Github Repo](https://github.com/anthropics/claude-cookbooks)
+
+[Agent Skills Github Repo](https://github.com/anthropics/skills)
+
+## **6. Judging**
+
+Judging for the Anthropic Virtual Hackathon happens in **two stages**:
+
+### **Stage 1 – Asynchronous Judging**
+
+- **Date:** April 26th - April 27th
+
+- **How it works:**
+
+  - Judges review your **submitted projects asynchronously** via the judging platform.
+
+  - Each team will have uploaded:
+
+    1. A **short demo video** (3 minute maximum)
+
+    2. Open Source Project repository / code
+
+    3. Written summary (100–200 words)
+
+  - Judges independently evaluate projects using **standardized criteria**.\
+    **Judging Criteria:**
+
+    1. **Impact (30%) -** What's the real-world potential here? Who benefits, and how much does it matter? Could this actually become something people use? Does it fit into one of the problem statements listed above?
+
+    2. **Demo (25%) *—*** Is this a working, impressive demo? Does it hold up live? Is it genuinely cool to watch?
+
+    3. **Opus 4.7 Use (25%) -** How creatively did this team use Opus 4.7? Did they go beyond a basic integration? Did they surface capabilities that surprised even us?
+
+    4. **Depth & Execution (20%) —** Did the team push past their first idea? Is the engineering sound and thoughtfully refined? Does this feel like something that was wrestled with — real craft, not just a quick hack?
+
+  - After evaluation, the **team aggregates scores** to determine the **Top 6 projects** for the final round
+
+### **Stage 2 – Final Round Live Judging**
+
+- **Date & Time:** April 28th, 12:00PM EST
+
+- **Format:**
+
+  - During the live session, **pre-recorded demos** from each team will be played (3 minutes per team).
+
+  - Judges will deliberate after all demos to determine the 1st, 2nd, and 3rd place along with extra prizes.
+
+  - **The top three and special prize winners** will be announced during the closing ceremony at **1:45PM EST.**
+
+## **7. Submission Instructions**
+
+- Submit your project below:
+
+  [linkEmbed]
+
+- Required for submission:
+
+  - **3-minute demo video** (YouTube, Loom, or similar)
+
+  - **GitHub repository or code link**
+
+  - **Written description / summary**
+
+- **Deadline:** April 26th, 8:00 PM EST
+
+- Make sure your project was **built entirely during the hackathon**; no pre-existing work is allowed.
+
+## **8. Prizes**
+
+- **1st Place:** $50,000 in Claude API Credits
+
+- **2nd Place:** $30,000 in Claude API Credits
+
+- **3rd Place:** $10,000 in Claude API Credits
+
+- **Most Creative Opus 4.7 Exploration**: $5,000 in Claude API Credits
+
+  - For the project that treated Opus 4.7 as a creative medium, not just a tool. We're looking for the project with a voice, a point of view — something expressive, playful, strange, or alive. The one that made us feel something.
+
+- **The “Keep Thinking” Prize**: $5,000 in Claude API Credits
+
+  - For the project that didn't stop at the first idea — and landed somewhere nobody saw coming. We're looking for the team that found a real-world problem nobody thought to point Claude at. The one that changes how we think about where this technology belongs.
+
+- **Best use of Claude Managed Agents:** $5,000 in Claude API Credits
+
+  - For the team that leveraged the Claude platform the best. We're looking for the project that best uses Managed Agents to hand off meaningful, long-running tasks — not just a demo, but something you'd actually ship.
+
+## **❓If you have any questions, please ping in #questions on Discord or reach out to moderators.**