The AI Workflow Framework
for Claude Code
Structure any project into iterative tasks. 15 agents, 19 commands, 9-stage pipeline. 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
After every task, /dr-reflect analyzes 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 Developer
From requirements to production with TDD, code review, and compliance checks.
Project Manager
Backlog management, progress tracking, and documentation archives — without touching CLI.
Solo Founder
One person, full pipeline. From idea to shipped feature with AI assistance at every stage.
Team Lead
Quality standards, coordination, and architectural review for your team's AI workflow.
Researcher
Literature review, methodology, writing, and fact-checking — all in one framework.
Technical Writer
Documentation, articles, editorial review, and AI pattern removal for natural prose.
Datarim is developed as part of the Arcanada project — an ecosystem for building, orchestrating, and scaling AI agents.
Visit arcanada.one →