Save session state (continue working or exit safely)
find ~/namesreallyblank/ -name "*.skill"
QLTY During Development
Hook Development Rules
Search past reasoning for relevant decisions and approaches
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Check reference SDK implementations using btca ask
Implement technical plans from thoughts/shared/plans with verification
Use RepoPrompt CLI for token-efficient codebase exploration
A complete skill for E2E testing
External research workflow for docs, web, APIs - NOT codebase exploration
Implementation agent that executes a single task and creates handoff on completion
Comprehensive code review workflow - parallel specialized reviews → synthesis
Agentic Workflow Pattern
LLM Tuning Patterns
Automated accessibility testing via Playwright MCP and axe-core
Agent Orchestration Rules
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Graceful Degradation with Helpful Messages
Browser automation via Playwright MCP - screenshots, interactions, DOM inspection