Building a temporal layer so your AI never lies about time
How Claudriel’s temporal subsystem pins time per request, resolves timezones from context, and detects clock drift before it corrupts AI reasoning.
Ai
Generate Claude Code skills from any documentation URL
Use the skill-gen plugin to turn any library’s documentation into a reusable Claude Code skill in seconds.
Git hooks are your best defense against AI-generated mess
Git hooks have always enforced standards before code enters a repo. With AI agents writing commits autonomously, they’ve become essential.
The entity system at the heart of Waaseyaa
How waaseyaa’s EntityInterface, ContentEntityBase, and field system work — and how the entity-system specialist skill made cross-session development possible.
Three skills for governing multi-repo co-development with Claude Code
A skill set that governs framework-app co-development across three repos: enforcing patterns, auditing divergence, and extracting shared code.
Skills for applying codified context to your own codebase
Two Claude Code skills for applying and maintaining the three-tier codified context architecture — what they do, how they work, and how to get started.
Waaseyaa: building a Drupal-inspired PHP CMS with AI
What waaseyaa is, why it exists, and how planning with GitHub issues before coding changes the dynamic of building complex software with AI.
Cold memory: specs, MCP tools, and on-demand context retrieval
How subsystem specs and MCP retrieval tools handle architectural knowledge too large for hot memory — and why stale specs are worse than no specs.
Domain specialist skills: teaching AI to think like your senior dev
What specialist skills are, why the 50% domain knowledge rule matters, and how waaseyaa’s spec-backed orchestration keeps AI consistent across a 29-package PHP monorepo.
Writing a CLAUDE.md that actually works
How to structure your CLAUDE.md as a routing layer so AI agents always know where to look.