Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity
cat ~/الأعلى
تصفح أفضل المهارات مرتبة حسب نجوم GitHub
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration
Agentica server + Claude proxy setup - architecture, startup sequence, debugging
Spawn Agentica multi-agent patterns
AST-based code search and refactoring via ast-grep MCP
Async REPL Protocol
Background Agent Pings
Analyze Claude Code sessions via Braintrust
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Save session state (continue working or exit safely)
Claude Code CLI commands, flags, headless mode, and automation patterns
A complete skill for E2E testing
Completion Check: Verify Infrastructure Is Wired
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup",...
Manage Clorch configuration (Braintrust, API keys, features)
Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
Environment Triage
Explicit Identity Across Boundaries
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
Scrape web pages and extract content via Firecrawl MCP
Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit...
UI/UX visual design, styling, and aesthetic validation
Git Commit Rules
Search GitHub code, repositories, issues, and PRs via MCP