The AI Workflow Framework
for Claude Code, Codex CLI, and Cursor
Structure any project into iterative tasks. 19 agents, 27 commands, 64 skills, 8-stage pipeline, opt-in plugin system. From requirements to production — or from research to publication.
Structure Any Project
Not just code — research, legal docs, content, project management. Datarim adapts its pipeline to task complexity: simple fix or enterprise feature.
Self-Evolving
Every task ends with a mandatory reflection — it runs at a passing /dr-compliance verdict (and /dr-archive regenerates it only if missing or stale) to analyze what worked and what didn't. The framework learns and improves itself through evolution proposals.
Extensible
Create new skills, agents, and commands with /dr-addskill. Describe what you need in plain language — Datarim generates the artifact.
Quick Start
$ git clone https://github.com/Arcanada-one/datarim.git
$ cd datarim && ./install.sh
$ claude
/dr-help # see all commands
/dr-init my task # start workingUse Cases
Datarim adapts to your role and workflow
Software Development
From requirements to production with TDD, code review, and compliance.
Project Management
Backlog, iterations, progress tracking, retrospectives.
Content & Publishing
Articles, social media, newsletters — with editorial review.
DevOps & Infrastructure
CI/CD, Docker, deployment automation, secret management.
Legal Documents
Contracts, ToS, compliance docs with phased review.
Website Launch
Pre-launch checklist: DNS, SSL, analytics, social previews.
Datarim is developed as part of the Arcanada project — an ecosystem for building, orchestrating, and scaling AI agents.
Visit arcanada.ai →