Automated generator for strongly typed Pydantic v2 data models and basic catalogs across any A2UI protocol version (v0.8, v0.9, v0.9.1, v1.0, etc.).
a2ui-project/a2ui
Open-source generative UI framework: agents stream layout data, and apps render it with native components in React, Angular, Lit, Flutter, SwiftUI and Jetpack Compose.
Repository statistics
Indexed skills
23
Skill groups
1
GitHub stars
17,668
Forks
1,430
Skills
23 totalMigrates an app, renderer, catalog or agent that uses A2UI (or a predecessor such as Flutter `genui`) to a newer SDK or protocol version. Use when a task mentions migrating, upgrading, porting or moving A2UI code between SDKs, packages or protocol versions (v0.8, v0.9, v0.9.1, v1.0), when a dependency such as `genui`, `a2ui_core`, `@a2ui/web_core`, `a2ui-core` or an A2UI Swift package needs a major bump, or when payloads or fixtures must change wire version. The skill first identifies the language, the source and the target, then routes to a case-specific guide where one exists.
Step-by-step phased instructions for building new A2UI Core SDKs, Framework Adapters, and Inference SDKs from scratch in any client language.
Auditing codebase implementations for synchronization drift with the user documentation, readmes, and code comments.
Provides instructions on implementing feature specs or module blueprint commit diffs in a specific codebase.
Instructions and best practices for updating CHANGELOG.md files across A2UI packages. Use when adding or modifying a CHANGELOG.md file, when a PR adds, modifies, deprecates, or removes public exports or consumer-observable behavior in a published package, or when resolving merge conflicts in a CHANGELOG.md file.
Automates the triage of GitHub issues in the A2UI repository. Helps the oncall engineer by fetching untriaged issues, generating AI-suggested priorities, assignees, and responses, launching a local review dashboard, and bulk-applying approved decisions to GitHub. Use when tasked with triaging new GitHub issues or managing the repository backlog.
Build agent-generated / AI-generated UI with A2UI (Agent-to-User Interface), the open protocol where an agent streams layout data and the app renders it with its own native components (React, Angular, Lit, Flutter, SwiftUI, Jetpack Compose). Use when developers want an AI, LLM or agent to generate or update UI at runtime ("generative UI", "GenUI", "agent-generated UI", "AI renders widgets/forms/cards", "server-driven UI from an LLM"), especially on Flutter, Angular, native mobile, more than one platform, or when a remote or third-party agent must not send executable code. Triggers on: "A2UI", "generative UI", "GenUI", "Flutter GenUI", "genui", "agent UI", "AI-generated UI", "dynamic UI from LLM".
Defines authoring, multi-version tabbing, multi-SDK code example, diagram, and PR preview standards for the A2UI developer site (docs/site/). Progressively routes by page type (guides, concepts, components/landing pages, and specifications/agent manifests) so agents load only the rules relevant to their task.
Step-by-step workflow for adding and verifying new evaluation data points in the A2UI evaluation suite, by importing a real trace or authoring a sample by hand.
Main coordination skill to run the blueprint compliance, documentation synchronization, and test quality audits, posting the combined results as a labeled GitHub issue.
Verification of platform codebase blueprint compliance against the latest module blueprints.
Manage the evolution, merging, archiving, and cleanup of specifications and blueprints across the workspace.
Analytical navigation of A2UI Spec-Driven Development module and codebase blueprints.
Provides instructions on how to create a new language-agnostic A2UI Feature Blueprint, ensuring consistency and ease of cross-language implementation.
Releases the Python SDKs (a2ui-core, a2ui-agent-sdk, a2ui-a2a, a2ui-adk) to PyPI by running preflight checks, dispatching the release workflow as a dry run, confirming with the maintainer, publishing, and following the changelog pull request through to merge. Use when asked to cut, publish, or release a Python SDK version.
Remediates a specific recommendation from an A2UI compliance report issue, or resolves any general GitHub issue, by inspecting context, implementing minimal targeted fixes, verifying tests, creating a branch, and opening a developer-signed Pull Request. Use when asked to fix or remediate an A2UI compliance audit finding, recommendation, or repository issue.
Auditing test suites for assertion utility, boundary cases coverage, and verification strength.
Enforces engineering, architecture, public API, and code quality standards distilled from human reviewer feedback across A2UI pull requests. Use when authoring new code, refactoring, addressing review feedback, or reviewing PR diffs. Don't use for release publishing or spec blueprint generation without code or PR changes.
Iterative benchmarking, evaluation, and algorithmic optimization of alternative A2UI inference formats (such as Express, Atom, and Elemental). Trigger when asked to: (1) Run optimization passes or loops on an inference format, (2) Evaluate or benchmark format accuracy, latency, or token efficiency, (3) Create parallel worktree subagents for format iteration, or (4) Benchmark format trade-offs against baselines.
Useful when working with the Inspect AI evaluation framework (e.g., in the eval/ directory). Provides instructions on how to access Inspect AI documentation.
Contains well-defined rules for creating natural, accurate, and readable writing. Use this skill whenever authoring longer text, including reports, PR descriptions, READMEs, system designs, analysis documents, or general documentation.
Enforces pull request scope, atomicity, and software design standards distilled from human reviewer feedback across A2UI pull requests. Use when authoring, preparing, splitting, or reviewing a pull request, or when a change introduces new modules, abstractions, or comments.
Add to your README
The badge links readers to this page. It shows the skilld mark and no counts, and it follows the reader's light or dark GitHub theme.
<a href="https://skilld.dev/gh/a2ui-project/a2ui">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/a2ui-project/a2ui?theme=dark">
<source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/a2ui-project/a2ui?theme=light">
<img alt="Skill repository on skilld.dev" src="https://skilld.dev/b/a2ui-project/a2ui?theme=light">
</picture>
</a>