One-click install
npx skills add https://github.com/Arcanada-one/datarim --skill datarim-system
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: datarim-system
Source: https://github.com/Arcanada-one/datarim/tree/main/skills/datarim-system
Command: npx skills add https://github.com/Arcanada-one/datarim --skill datarim-system

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents inconsistent, untraceable, and poorly structured AI-assisted work by centralizing Datarim’s workflow and storage invariants into a single “load first” ruleset.

Core Features & Use Cases

  • Canonical workflow state & storage boundaries: keeps iterative state strictly in datarim/ while long-term archives live in documentation/archive/.
  • Thin operational indexes with strict schemas: standardizes tasks.md, backlog.md, and activeContext.md as one-line-per-task pointers rather than full content.
  • Deterministic routing and invariants: defines L1–L4 stage routing, command namespace rules (/dr-), archive mapping, and reflection behavior at archive Step 0.5.
  • Safety-critical conventions: enforces task ID formats, disallows forbidden directories, blocks overrides for security-critical skills, and mandates path resolution rules.

Quick Start

Load the datarim-system skill first so subsequent fragments correctly apply paths, numbering, backlog/routing rules, and archive/reflection invariants for your current project.

Frequently Asked Questions about datarim-system

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I prevent schema drift in iterative AI-assisted project execution?▼

To prevent schema drift in iterative AI-assisted project execution, load a centralized workflow ruleset first to enforce strict YAML frontmatter identity discovery, thin index file schemas, and canonical routing invariants across all project tasks.

How do I standardize task routing and lifecycle management for requirements, planning, and QA?▼

Standardize task routing by applying deterministic L1–L4 stage routing rules and a unified command namespace (/dr-) to manage the full task lifecycle from requirements and planning through execution, QA, compliance, reflection, and archival.

What is the best way to maintain traceable state tracking in AI-assisted workflows?▼

Maintain traceable state tracking by using thin operational indexes like tasks.md, backlog.md, and activeContext.md as one-line-per-task pointers, keeping iterative state in datarim/ while routing long-term archives to documentation/archive/.

Do I need specific path resolution rules to enforce workflow invariants safely?▼

Yes, enforcing workflow invariants requires strict path resolution rules that mandate correct task-ID formats, block forbidden directories, disallow overrides for security-critical skills, and define safe storage boundaries.

Why does my workflow state become inconsistent during complex task archival?▼

Workflow state becomes inconsistent during archival without enforced reflection behavior at archive Step 0.5 and canonical archive mapping, which prevent untraceable state transitions and ensure safe long-term knowledge storage.

Can I use standard workflow commands to manage project compliance and reflection stages?▼

Yes, you can manage compliance and reflection stages using the standard /dr-* command workflow, which applies canonical routing invariants to safely transition tasks through execution, QA, and archival.