coworker-context

Standardize external LLM generation and editing of Datarim artifacts with YAML frontmatter preservation.

11|1|Updated Apr 10, 2026
One-click install
npx skills add https://github.com/Arcanada-one/datarim --skill coworker-context
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: coworker-context
Source: https://github.com/Arcanada-one/datarim/tree/main/skills/coworker-context
Command: npx skills add https://github.com/Arcanada-one/datarim --skill coworker-context

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents inconsistent formatting, broken YAML frontmatter, and drift in stage-header conventions when an external LLM generates or edits Datarim artifacts.

Core Features & Use Cases

  • Stage header contract: Enforces the exact operator-facing first-line convention for /dr-* outputs (with defined exceptions).
  • Byte-exact frontmatter rules: Preserves YAML delimiters, key order, spacing, and quoting behavior to avoid metadata corruption.
  • Archive/PRD validation mirroring: Requires archive validation checklist items to mirror PRD success criteria 1:1 for traceability.
  • Structured Q&A and status expectations: Standardizes init-task clarification rounds and expectation checklists for reliable iteration.
  • Output discipline & taxonomy constraints: Restricts documentation types to Diátaxis categories and applies a history-agnostic naming gate.

Quick Start

Instruct the external model to read this skill end-to-end before writing or editing any file under datarim/ using the coworker profile datarim.

Frequently Asked Questions about coworker-context

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

FAQPage Schema
How do I keep YAML frontmatter consistent when an external LLM edits my documentation?

To keep YAML frontmatter consistent during external LLM edits, enforce byte-exact preservation rules for delimiters, key order, spacing, and quoting behavior to prevent metadata corruption in generated artifacts.

What is the best way to standardize LLM-generated artifacts across workflow stages?

Standardizing LLM-generated artifacts requires enforcing a strict stage header contract for operator-facing outputs and restricting documentation types to Diátaxis taxonomy categories to maintain consistency across init, plan, and archive stages.

How do I ensure traceability between PRD success criteria and archive validation checklists?

To ensure traceability between PRD success criteria and archive validation, require archive validation checklist items to mirror PRD success criteria on a 1:1 basis, maintaining strict consistency throughout the artifact lifecycle.

Can I use external coworker LLMs to generate Diátaxis taxonomy documentation without formatting drift?

Yes, external coworker LLMs can generate Diátaxis taxonomy documentation without drift by applying output discipline constraints, structured Q&A sections, and history-agnostic naming gates to standardize the generation process.

Why does my YAML frontmatter break when delegating artifact production to an external LLM?

YAML frontmatter breaks during external LLM delegation because models alter byte structure; enforcing strict preservation of delimiters, key order, and quoting behavior prevents this metadata corruption.

How do I structure clarification rounds for init-task artifacts generated by an LLM?

Structure init-task clarification rounds by standardizing structured Q&A and status expectation sections, ensuring reliable iteration and consistent logging when an external LLM generates the initial artifacts.