AI Development Quality Discipline

skill · reused

Evidence record

What is verified
Uses in published workflows: 1
Source
Published workflow connections
Revision
Version 0.1.5
Validation status
Public-sanitized publication; no independent validation is claimed.

What this is and why

Five working disciplines for AI-assisted development: decomposition into methods of at most fifty lines, tests before code with edge-only mocking, an approved architecture skeleton before implementation, one-method-at-a-time focus, and deliberate context management. It presumes gathered requirements and an explicit definition of done before coding starts. The work leaves behind pre-written tests, a named test for every clause of a success criterion, and a clean linter run after each TDD cycle.

Relations

Neighbor diagram: this capability’s direct relations in the knowledge graph uses planner AI Development Quality Discip…
Used by: uses
planner

Show this capability and its neighbours in the catalog

Metadata and provenance

id
datarim-skill-ai-quality
type
skill
version
0.1.5
origin
created in Arcanada
lifecycle
public_sanitized
tags
skill, talo-0029

The source is the private knowledge repository; only the sanitized public projection reaches this site.

verified · datarim-skill-ai-quality · v0.1.5