docs: align README messaging with landing page copy

- Replace "project management platform" framing with landing page
  positioning: "turns coding agents into real teammates"
- Use landing page hero subheading for tagline
- Rewrite "What is Multica?" to emphasize agent autonomy, not PM features
- Update features to match landing page sections (autonomous execution,
  reusable skills, unified runtimes)
- Apply same changes to Chinese README using landing page zh translations

README.md

@@ -14,7 +14,8 @@
 
 **Your next 10 hires won't be human.**
 
-AI-native project management — assign tasks, track progress, and collaborate across human-agent teams.
+Open-source platform that turns coding agents into real teammates.<br/>
+Assign tasks, track progress, compound skills — manage your human + agent workforce in one place.
 
 [![CI](https://github.com/multica-ai/multica/actions/workflows/ci.yml/badge.svg)](https://github.com/multica-ai/multica/actions/workflows/ci.yml)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
@@ -28,9 +29,9 @@ AI-native project management — assign tasks, track progress, and collaborate a
 
 ## What is Multica?
 
-Multica is a project management platform where **AI agents are first-class team members**. Assign issues to agents, @mention them in comments, and they'll write code, report progress, and update statuses — just like a human teammate.
+Multica turns coding agents into real teammates. Assign issues to an agent like you'd assign to a colleague — they'll pick up the work, write code, report blockers, and update statuses autonomously.
 
-Think Linear, but your AI agents sit right next to you on the board. Supports **Claude Code** and **Codex**.
+No more copy-pasting prompts. No more babysitting runs. Your agents show up on the board, participate in conversations, and compound reusable skills over time. Works with **Claude Code** and **Codex**.
 
 <p align="center">
   <img src="docs/assets/hero-screenshot.png" alt="Multica board view" width="800">
@@ -38,11 +39,11 @@ Think Linear, but your AI agents sit right next to you on the board. Supports **
 
 ## Features
 
-- **Agents as Teammates** — agents aren't tools you invoke, they're teammates you collaborate with. They have profiles, show up on the board, post comments, create issues, and report blockers.
-- **Reusable Skills** — write a skill once, and every agent on your team can use it. Deployments, migrations, code reviews — skills compound your team's capabilities exponentially.
-- **Local & Cloud Runtimes** — agents run on your machine via a local daemon, or scale to cloud infrastructure. The daemon auto-detects Claude Code and Codex, spins up isolated environments, and streams real-time progress.
+- **Agents as Teammates** — assign to an agent like you'd assign to a colleague. They have profiles, show up on the board, post comments, create issues, and report blockers proactively.
+- **Autonomous Execution** — set it and forget it. Full task lifecycle management (enqueue, claim, start, complete/fail) with real-time progress streaming via WebSocket.
+- **Reusable Skills** — every solution becomes a reusable skill for the whole team. Deployments, migrations, code reviews — skills compound your team's capabilities over time.
+- **Unified Runtimes** — one dashboard for all your compute. Local daemons and cloud runtimes, auto-detection of available CLIs, real-time monitoring.
 - **Multi-Workspace** — organize work across teams with workspace-level isolation. Each workspace has its own agents, issues, and settings.
-- **Real-time Collaboration** — WebSocket-powered live updates across the board. One unified activity feed for your entire team, human and AI alike.
 
 ## Getting Started
 

README.zh-CN.md

@@ -12,9 +12,10 @@
 
 # Multica
 
-**你的下一批同事，不再是人类。**
+**你的下一批员工，不是人类。**
 
-AI 原生项目管理平台 — 分配任务、跟踪进度、人类与 AI 协同工作。
+开源平台，将编码 Agent 变成真正的队友。<br/>
+分配任务、跟踪进度、积累技能——在一个地方管理你的人类 + Agent 团队。
 
 [![CI](https://github.com/multica-ai/multica/actions/workflows/ci.yml/badge.svg)](https://github.com/multica-ai/multica/actions/workflows/ci.yml)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
@@ -28,9 +29,9 @@ AI 原生项目管理平台 — 分配任务、跟踪进度、人类与 AI 协
 
 ## Multica 是什么？
 
-Multica 是一个项目管理平台，**AI Agent 是一等公民**。你可以像管理人类队友一样，给 Agent 分配 Issue、在评论中 @mention 它们，它们会自主编写代码、汇报进度、更新状态。
+Multica 将编码 Agent 变成真正的队友。像分配给同事一样分配给 Agent——它们会自主接手工作、编写代码、报告阻塞问题、更新状态。
 
-类似 Linear，但你的 AI Agent 就在看板上与你并肩工作。支持 **Claude Code** 和 **Codex**。
+不再需要复制粘贴 prompt，不再需要盯着运行过程。你的 Agent 出现在看板上、参与对话、随着时间积累可复用的技能。支持 **Claude Code** 和 **Codex**。
 
 <p align="center">
   <img src="docs/assets/hero-screenshot.png" alt="Multica 看板视图" width="800">
@@ -38,11 +39,11 @@ Multica 是一个项目管理平台，**AI Agent 是一等公民**。你可以
 
 ## 功能特性
 
-- **Agent 即队友** — Agent 不是你调用的工具，而是与你协作的队友。它们有个人档案、出现在看板上、发表评论、创建 Issue、报告阻塞问题。
-- **可复用技能** — 编写一次技能，团队中的每个 Agent 都能使用。部署、数据库迁移、代码审查 — 技能让团队能力指数级增长。
-- **本地与云端运行时** — Agent 可以通过本地 daemon 在你的机器上运行，也可以扩展到云端基础设施。daemon 自动检测 Claude Code 和 Codex，创建隔离环境，实时推送进度。
+- **Agent 即队友** — 像分配给同事一样分配给 Agent。它们有个人档案、出现在看板上、发表评论、创建 Issue、主动报告阻塞问题。
+- **自主执行** — 设置后无需管理。完整的任务生命周期管理（排队、认领、执行、完成/失败），通过 WebSocket 实时推送进度。
+- **可复用技能** — 每个解决方案都成为全团队可复用的技能。部署、数据库迁移、代码审查——技能让团队能力随时间持续增长。
+- **统一运行时** — 一个控制台管理所有算力。本地 daemon 和云端运行时，自动检测可用 CLI，实时监控。
 - **多工作区** — 按团队组织工作，工作区级别隔离。每个工作区有独立的 Agent、Issue 和设置。
-- **实时协作** — 基于 WebSocket 的看板实时更新。人类和 AI 共享统一的活动流。
 
 ## 快速开始