惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

D
DataBreaches.Net
IT之家
IT之家
博客园_首页
博客园 - 【当耐特】
V
V2EX
Apple Machine Learning Research
Apple Machine Learning Research
G
Google Developers Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Recent Announcements
Recent Announcements
F
Fortinet All Blogs
GbyAI
GbyAI
腾讯CDC
H
Hackread – Cybersecurity News, Data Breaches, AI and More
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
I
InfoQ
H
Help Net Security
T
Tailwind CSS Blog
B
Blog RSS Feed
Martin Fowler
Martin Fowler
人人都是产品经理
人人都是产品经理
The Cloudflare Blog
博客园 - 叶小钗
雷峰网
雷峰网
量子位

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - think41/extrasuite: Token-efficient pull/edit/push workflow for AI agents editing Google Workspace files (Sheets, Docs, Slides, Forms) GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw
GitHub - takaakit/superpowers-uml: Superpowers-UML modifi...
2026-04-11 · via Hacker News: Show HN

Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling.

Key modifications to Superpowers:

  • The AI agent represents the specifications, including the software design1, as a UML model.
  • The user and the AI agent collaboratively refine the specifications and the design1 through UML modeling.
  • The AI agent creates an implementation plan based on the user-approved UML model.
  • The AI agent revises the UML model so that it matches the implemented code.
  • Only Claude Code is supported, as this project relies on Claude Code-specific features such as Hooks and Subagents.

Demo

Request: Create a desktop AI chat app in Java
Agent: Claude Code with Sonnet 4.6
Processing time: 90 minutes

Demo

Created UML diagrams and an AI chat application:

Requirements

Info: We have not measured the exact figures, but using Superpowers-UML in Claude Code with Sonnet 4.6 for about 40 minutes reaches the Pro plan's 5-hour token limit. If you want to use Superpowers-UML comfortably, the Max plan may be better. For the AI agent model, we recommend Sonnet or Opus in terms of the quality of the generated UML models and the ability to accurately follow the workflow.

Install

  • Install Claude Code

  • Install Astah Pro

  • Install the Astah Pro MCP plugin in Astah Pro

    Install steps: Launch Astah Pro -> drag and drop the Astah Pro MCP JAR file onto the Astah Pro window -> restart Astah Pro.

  • Install the Superpowers-UML plugin in Claude Code via the marketplace

    /plugin marketplace add https://github.com/takaakit/superpowers-uml.git
    /plugin install superpowers-uml@superpowers-uml-dev
    /reload-plugins

Uninstall

  • Uninstall the Superpowers-UML plugin in Claude Code

    /plugin uninstall superpowers-uml@superpowers-uml-dev
    /plugin marketplace remove superpowers-uml-dev
  • If you want to remove it completely, manually delete the ~/.claude/plugins/cache/superpowers-uml directory.

Update

  • Update the Superpowers-UML plugin in Claude Code

    /plugin update superpowers-uml@superpowers-uml-dev

Usage

  1. It is recommended to disable unused MCP tools to avoid reducing the AI agent's tool-calling accuracy.

  2. Launch Astah Pro with the Astah Pro MCP plugin installed

    Note: Launch Astah Pro before starting Claude Code, and it should remain open throughout the entire workflow.

  3. Open a terminal and go to your project directory

  4. Launch Claude Code with this command to temporarily allow the use of tools:

    claude --allowedTools "mcp__plugin_superpowers-uml_astah-pro-mcp__*"

    A confirmation dialog will pop up on initial connection. Check it and click 'Connect'.

  5. Start the workflow by running this command in Claude Code

    /brainstorming

    Tip 1: In Superpowers-UML, no specific design policy is prescribed; the choice of design approach is left to the AI agent. If you want to specify one, a possible approach may be to have the AI agent refer to a document that describes the design policy (e.g., DDD Reference) before starting the workflow, and then instruct the agent to design in accordance with that policy.

    Tip 2: If you want to start in the middle of the workflow, send the prompt "List superpowers-uml commands" to display the available commands, then use the appropriate command.

Additional Info

  • AI agents refer to information provided by OMG to understand UML.
  • AI agents follow Agile Modeling guidelines when creating a UML model.

License

  • The original Superpowers is copyright © Jesse Vincent and licensed under the MIT license.
  • All modifications and new content added by this project are released under the CC0 1.0 Universal (Public Domain) license.

Contributing

If you have a proposed improvement, please open an issue. Note that any improvements submitted will be released under the CC0 license.

Links

Footnotes

  1. In the future, the specification and design artifacts may be separated. 2