feed · watching · stats · help with your tokens
caru-ini/stack-diagram
An agent skill that generates architecture diagrams with official logos from a one-sentence description of a tech stack.
It solves the problem of manually creating technical architecture diagrams by allowing developers to describe their stack in a sentence and automatically generating a visual diagram with official logos for documentation or sharing. It operates as an agent skill for Claude Code, Codex, and Cursor, fetching official logos from sources like svgl and devicon to render self-contained HTML, PNG, or React components.
Similar
- jyotipmahes/ML-Interview-Prep
A repository containing Machine Learning Engineer interview preparation materials and from-scratch algorithm implementations.
- postmanlabs/postman-app-support
The public support repository where Postman users file feature requests, integration ideas and bug reports.
- aaitor/skill-video-studio
A local video-production workspace driven by a Claude Code skill that turns a product walkthrough into a polished demo video.
- KKKKhazix/agent-autoloop
Agent Autoloop lets a command-line agent pick up work in the background and follow it through, asking for a decision only when something is uncertain.
- storytold/craft-anything
Craft Anything is an open-source, pure Rust engine that studies software to understand its mechanics and uses AI agents to build new versions.
- soml-lang/soml
SOML is a configuration format for humans that keeps JSON's data model and strictness while dropping braces, quotes and commas.
- thedotmack/claude-mem
claude-mem preserves context across coding-agent sessions by capturing tool usage and generating semantic summaries.
- lookfree/cc-harness
A desktop workbench for Claude Code that visualizes subagent topology, token costs, and configuration to improve observability.
sources
Claims below include README evidence. A matching quote or worker agreement does not establish that a claim is correct. Category majority among 2 workers. Version 1.
An agent skill that generates architecture diagrams with official logos from a one-sentence description of a tech stack.
Describe your stack in a sentence. Get an architecture diagram with official logos.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
It solves the problem of manually creating technical architecture diagrams by allowing developers to describe their stack in a sentence and automatically generating a visual diagram with official logos for documentation or sharing.
Describe your stack in a sentence. Get an architecture diagram with official logos.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
It operates as an agent skill for Claude Code, Codex, and Cursor, fetching official logos from sources like svgl and devicon to render self-contained HTML, PNG, or React components.
Works with Claude Code, Codex, Cursor and other agents that support skills. In the Claude apps, upload `stack-diagram.zip` from Releases as a skill.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Generates architecture diagrams from a single sentence description of the tech stack.
Describe your stack in a sentence. Get an architecture diagram with official logos.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Automatically fetches official logos from svgl, devicon, gilbarbara/logos, or vendor repositories.
Official logos, fetched for you. From svgl, then devicon, then gilbarbara/logos, or the brand's own repository.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Routes connection lines around text labels to prevent visual clutter and verifies the render.
No arrows through text. Lines are routed around labels, and the agent renders the diagram and checks it before handing it over.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Outputs diagrams as self-contained HTML, PNG, dependency-free React components, or Claude Artifacts.
A self-contained HTML file (default), PNG, a dependency-free React component, or an Artifact.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Renders diagrams in both light and dark themes while preserving original logo colors.
Every diagram is rendered in both themes. Tiles stay white so logos keep their own colors, and group labels switch to the brand's dark-theme logo.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Produces a single HTML file with inlined fonts and logos that renders offline.
The diagram is one HTML file with its fonts and logos inlined, so it renders anywhere without a network.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Optionally posts the generated diagram to a public gallery at stacks.caru.moe.
After drawing, the agent offers once to post the diagram to the public gallery at https://stacks.caru.moe.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Uses vendor-specific icon packages for AWS, Google Cloud, and Azure architectures.
AWS, Google Cloud and Azure icons come from each vendor's own package: AWS, Google Cloud, Azure.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Converts natural language stack descriptions into visual architecture diagrams instantly.
Describe your stack in a sentence. Get an architecture diagram with official logos.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Automatically fetches and uses official logos from vendors like AWS, Google Cloud, Azure, and others without recoloring.
Official logos, fetched for you. From svgl, then devicon, then gilbarbara/logos, or the brand's own repository.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Ensures clean diagrams by routing connection lines around text labels and validating the final render.
No arrows through text. Lines are routed around labels, and the agent renders the diagram and checks it before handing it over.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Outputs diagrams in multiple formats including self-contained HTML, PNG images, and dependency-free React components.
The format you need. A self-contained HTML file (default), PNG, a dependency-free React component, or an Artifact.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Supports both light and dark themes while preserving logo colors and adapting label styles appropriately.
Every diagram is rendered in both themes. Tiles stay white so logos keep their own colors, and group labels switch to the brand's dark-theme logo.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Generates standalone HTML files with embedded assets that render offline without requiring network access.
The diagram is one HTML file with its fonts and logos inlined, so it renders anywhere without a network.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Integrates with various AI coding agents including Claude Code, Codex, and Cursor as a callable skill.
Works with Claude Code, Codex, Cursor and other agents that support skills.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Allows users to optionally publish their generated diagrams to a public gallery after creation.
After drawing, the agent offers once to post the diagram to the public gallery at https://stacks.caru.moe.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Capable of diagramming complex development tooling stacks including monorepos and CI/CD pipelines.
Draw our monorepo tooling: a pnpm workspace with Turborepo, Biome, Vitest and Lefthook.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Supports creating detailed cloud architecture diagrams for major providers like AWS, Google Cloud, and Azure.
Draw our app on AWS: CloudFront in front of S3 and an ALB in a public subnet.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Requires Python 3.9 or higher and network connectivity to fetch logos, using Playwright for PNG exports.
Requires Python 3.9+ and network access for the logos. PNG export uses Playwright with Chromium.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Uses third-party logos under various open licenses without bundling them, fetching them dynamically during build.
Logos are not bundled with the skill. They are downloaded at build time from svgl, devicon (MIT), gilbarbara/logos (CC0), AWS Architecture Icons, Google Cloud product icons, Azure icons and Lucide (ISC).
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Requires Python 3.9 or higher and network access to download logos.
Requires Python 3.9+ and network access for the logos.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: PNG export functionality depends on Playwright and Chromium.
PNG export uses Playwright with Chromium.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Requires Python 3.9 or higher and active network connectivity to download official logos.
Requires Python 3.9+ and network access for the logos.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Logos are not included in the distribution and must be downloaded at build time from external sources.
Logos are not bundled with the skill. They are downloaded at build time from svgl, devicon (MIT), gilbarbara/logos (CC0), AWS Architecture Icons, Google Cloud product icons, Azure icons and Lucide (ISC).
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: The tool does not recolor or modify logos, limiting customization of brand colors in diagrams.
The scripts never recolor or alter a logo.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: GitHub authentication is optional and only used for managing public gallery posts, not for core functionality.
GitHub login is optional and never shown; it only lets you delete the post later.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: User prompts are not sent to external services, ensuring privacy during diagram generation.
Your prompt is never sent.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Example documentation images may contain third-party logos that are not part of the bundled assets.
The example images in docs/ show third-party logos.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
developer-tools · other