Browse / Research & science / Teaching & study / ai-workspace
ai-workspace
ariel-rubilar
Central hub for my AI study and experiments.
Open ariel-rubilar/ai-workspace → Checked against the four rules.
Works with any agent
ships AGENTS.md, the cross-tool instruction file.
In its own words
README.mdariel-rubilar/ai-workspace
Central hub for my AI study and experiments. This repo is the single source of truth for the AI-related tooling I collect, build, and learn from: MCP servers, agent skills, agent definitions, and study notes.
Purpose
- Learn: study notes on AI concepts, with practical examples.
- Collect: MCP configs, skills, and agent personas, versioned in one place.
- Install on demand:
scripts/will hold helpers to link or install these configs into~/.config,~/.agents, etc.
How to use
- Edit: add or change configs/notes in the relevant folder.
- Commit: keep every change versioned here.
- Apply (when scripts exist): run
scripts/setup.shto link or install configs into your system.
Status
Scaffolded — empty placeholders ready for content.
- PR Summary Studio — a learning project that combines an MCP server (Go), a skill, and an agent to write PR summaries locally. Spec:
docs/specs/2026-08-14-pr-summary-studio-design.md. - Code Reviewer — a portable agent + skill that reviews changes for bugs, best practices, performance, and regression risk against untested legacy code, saving severity-ranked reports outside the repo. Spec:
docs/specs/2026-08-14-code-reviewer-design.md.
Language
All documentation is written in English.
The whole README. Open the repo ↗
Read from the repository's git tree on 2026-08-17.