AI & ML

abzhaw Skill

Connecting to MCP servers, tool invocation, session management. Use when the orchestrator or any agent needs to call tools on an MCP server (bridge, cowork-mcp).

abzhaw Bundle

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monor...

abzhaw Skill

Relay incoming Telegram messages to Julia via the local MCP bridge server (http://localhost:3001). Use whenever a user sends a message that requires Julia's intelligence to answer. Forward the message, wait for Julia's reply, then send it back to the user.

abzhaw Skill

Short/long-term memory for LLM agents — vector stores, context window management, memory consolidation. Use when Julia needs to remember user preferences, past decisions, or conversation history across sessions.

abzhaw Bundle

Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance iss...

abzhaw Bundle

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky...

abzhaw Skill

Push notifications, alerting, escalation chains, multi-channel delivery. Use when Julia needs to alert Raphael via Telegram, or when designing escalation paths for agent failures.

abzhaw Skill

OpenClaw CLI, gateway setup, pairing, agent skills, and relay patterns. Use when configuring Julia's Telegram gateway, debugging pairing issues, or extending OpenClaw with new skills.

abzhaw Skill

TODO systems for agents, TASK-NNN format, agent-readable specs. Use when creating, reading, or managing tasks in Julia's todo/ directory.

abzhaw Bundle

Operate and maintain the Julia MCP bridge server (start/stop, health checks, send/receive flows, queue inspection) so OpenClaw and Julia stay in sync.

kortix-ai Skill

Drive OpenAI's Codex CLI (`codex exec`) as a non-interactive coding sub-agent from inside Claude Code. Load WHENEVER you want to delegate a coding/analysis/refactor task to Codex, get a second opinion / adversarial review from another model, fan out parallel agents across files or worktrees, or run a long mechanical job while you stay the planner. Covers the exact `codex exec` flags, sandbox tiers, output capture, JSON/schema modes, session resume, parallel fan-out, and the mandatory "delegate → capture → independently verify, never trust the self-report" supervision loop.

kortix-ai Skill

Drive Anthropic's Claude Code CLI (`claude -p`) as a non-interactive coding sub-agent from inside Codex. Use when you want to delegate a coding/analysis/refactor task to Claude, get a second opinion / adversarial review from another model, hand off long-context planning, or fan out parallel agents. Covers the exact `claude -p` flags, permission modes, output capture, JSON/stream-json modes, session resume, parallel fan-out, and the mandatory "delegate → capture → independently verify, never trust the self-report" supervision loop.

abzhaw Skill

Production deployment principles and decision-making. Safe deployment workflows, rollback strategies, and verification. Teaches thinking, not scripts.

abzhaw Skill

Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying.

abzhaw Skill

Agent-assisted thesis writing loops, draft-review-revise cycles. Use when the thesis agent is writing, expanding, or refining sections of Raphael's master's thesis.

abzhaw Skill

Scaffolding and creating new agents or sub-agents within the juliaz_agents ecosystem. Trigger whenever Raphael wants to create a new agent, add a new sub-agent, define a new agent's personality/identity, set up agent heartbeats, or modify an existing agent's SOUL/IDENTITY/TOOLS/AGENTS files. Also trigger when discussing agent conventions, the SOUL.md pattern, or how agents should be structured in this project. If someone says 'new agent', 'create an agent', 'agent personality', 'SOUL.md', or 'add a bot' — this is the skill to use.

abzhaw Skill

Manage the OpenClaw agent system end-to-end (agents/, skills/, MCP servers) so the workspace stays healthy.

abzhaw Skill

Design effective system prompts, few-shot examples, chain-of-thought instructions, and output constraints for LLM agents. Use when writing or tuning prompts for Julia's orchestrator, cowork-mcp, or any sub-agent.

abzhaw Skill

Queue design, polling vs push, persistence, dead-letter handling. Use when working with the bridge's queue.json or designing message flow between agents.

abzhaw Skill

PM2 config, ecosystem files, restart strategies, log management, cron jobs. Use when configuring Julia's services, debugging crashes, or adding new managed processes.

abzhaw Skill

Retrieval-augmented generation patterns — chunking, embedding, vector search, and reranking. Use when Julia needs to search through documents, research papers, logs, or knowledge bases.

abzhaw Bundle

Generate and maintain OpenAPI 3.1 specifications from code, design-first specs, and validation patterns. Use when creating API documentation, generating SDKs, or ensuring API contract compliance.

abzhaw Skill

Extracting key points, methodology analysis, literature review patterns. Use when Julia's thesis agent needs to process research papers for Raphael's master's thesis.

abzhaw Skill

Architecture patterns and anti-patterns for Julia's multi-agent system. Trigger when making architectural decisions — adding agents, changing message flow, redesigning tool registries, or evaluating the system's structure. Also trigger for: 'architecture', 'system design', 'how should agents work together', 'add a new agent', 'agent patterns', or any structural question about the multi-agent system.

avav25 Skill

Use this skill when assembling a subagent prompt and you need its context kept small and on-topic (db-engineer gets DB sections, ui-ux-designer gets UI/UX sections, etc.) — to load a per-role slice of project context from CLAUDE.md / AGENTS.md / ARCHITECTURE.md / project memory and return Markdown ready to embed in a subagent prompt.

abzhaw Skill

Ambient research agent for tracking Medium articles relevant to the agentic system project. Scans liked posts and discovers new articles on topics like multi-agent orchestration, autonomous AI, tool-calling patterns, and agentic workflows. Summarizes findings and bubbles up skill ideas to Julia.

abzhaw Skill

Telegram Bot API, polling, webhooks, message formatting, inline keyboards, and file sending. Use when building or extending Julia's Telegram communication layer via OpenClaw.

abzhaw Skill

Loop patterns, delegation strategies, retry logic, and multi-agent coordination. Use when designing or debugging Julia's orchestrator loop, sub-agent delegation, or inter-agent communication via bridge/MCP.

abzhaw Skill

Self-management skill for the OpenClaw agent. Use when you need to check your own health, diagnose gateway issues, inspect channel status, or restart the gateway. Run this before reporting any connectivity issue to Raphael.

abzhaw Skill

Audit all skill registries in the juliaz_agents ecosystem for duplicates, near-duplicates, empty skills, and merge candidates. Use this when asked to "clean up skills", "find duplicate skills", "audit the agent system", or "what skills are redundant?". Always produces a JSON findings report and a prioritized list of proposals for Raphael to approve via Telegram.

abzhaw Skill

Scan all open ports on localhost and detect unexpected listeners across all services

abzhaw Skill

Schreibt Erstentwuerfe in deutschem Wissenschaftsstil als LaTeX. Nimmt Notizen, Stichpunkte und Session-Logs als Input und produziert akademische Prosa.

abzhaw Skill

Human-in-the-loop approval via Telegram. Use whenever the ADHD agent needs Raphael's permission before taking an action. Sends a structured proposal message directly via the Telegram Bot API, then polls for YES/NO/LATER reply. Never acts without a YES. Treats timeout as NO and snoozes the finding.

abzhaw Skill

Lokale LaTeX-Kompilierung auf dem Mac Mini. Fehlerbehandlung, Paketverwaltung, Template-Setup. Kompiliert die Thesis zu PDF.

abzhaw Skill

Liest juliaz_agents-Quellcode (READ-ONLY) und extrahiert Architekturmuster, Code-Beispiele und Implementierungsdetails fuer die Thesis. Formatiert als LaTeX-Listings.

abzhaw Skill

Sucht und analysiert akademische Literatur. Findet relevante Papers, erstellt strukturierte Zusammenfassungen. Zitiert NIEMALS — schlaegt nur vor.