Archify

Archify is an agent skill that turns a description or an existing repository into an interactive, self-contained HTML diagram of an architecture, workflow, sequence or data flow.

Visit website tt-a1i.github.io

A user describes a system to their AI agent, for example a web request flowing through an API, a cache and a database, and Archify produces an interactive HTML diagram that can be refined further through plain-language follow-ups such as adding authentication or switching to a different theme. No existing codebase is required to start; alternatively, the agent can be pointed at a real repository to produce a source-backed diagram.

It installs as a skill into agents including Cursor, Claude Code, Codex CLI and OpenCode, and its output is a standalone HTML file that a user's own agent can keep editing, connect to other tools, or extend with new interactions after the initial diagram is generated.

JavaScript, MIT licensed.

More in Agent skills

See all 581

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents
github.com
A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.
- Agent skills
Vitruvius
github.com
An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.
- Agent skills
- AI evals

More in Agent skills

Provenance gate

Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

Vitruvius

Cookies