Create Adr Spike

This skill streamlines creation and organization of temporary project work products like architecture decision records, research investigations, spike analyses, and implementation plans. It provides templated Python scripts, standardized naming conventions, and a date-based directory structure within `.claude/artifacts/` to keep artifacts organized and discoverable.

Documentation Criteria provides decision matrices and templates to identify which technical documents your feature or change requires. Use it to navigate PRD, ADR, UI Spec, Design Doc, and Work Plan creation based on scope, complexity, and architectural impact.

This skill provides templates and guidance for creating Architecture Decision Records—lightweight documents that preserve the reasoning behind major technical choices. It walks you through the Nygard format, covering context, decision, consequences, and alternatives, plus best practices for lifecycle management and team review. Use it when evaluating trade-offs or recording decisions that shape your system's future.

Create and maintain architecture decision records (ADRs) using established conventions, templates, and a built-in validator. The skill guides you through prospective and retrospective record creation, enforces quality standards like one decision per record and credible alternatives, and helps manage decision lifecycles with status tracking and supersession links. Use it to build a durable, reviewable record of why architecturally significant choices were made.

Util Manage Todo tracks multi-step work in todo.md files with state indicators (pending, in progress, completed) and enforces integration verification through creation, connection, and runtime proof phases. Claude proactively creates todos when detecting complex work, coordinates task states across sessions, and ensures refactors include architectural decision records.

This skill produces structured technical documentation across four types: architectural decision records for design choices, system overviews for onboarding, API references for integrations, and operational runbooks for procedures. It enforces anti-patterns like documentation drift and future fiction while matching detail to audience—from high-level concepts for new developers to procedural steps for operations teams.