zurbrick

19 production-hardened patterns for AI agents — memory, verification, ambiguity handling, compaction survival, delegation, proof-based handoffs, stale-worker...

Lightweight self-improvement loop for AI agents. Capture errors, corrections, and discoveries in a fast one-line format, dedup them, queue recurring or criti...

Guide for OpenClaw setup, config, commands, routing, and troubleshooting. Use when the user asks how OpenClaw works, how to configure it, why a channel or ag...

Builds lean SKILL.md-based skills: decides when a skill is justified, drafts a minimal skill skeleton, and audits existing skills for bloat and drift. Use wh...

Diagnose and prevent OpenClaw agent failures — session bloat, lane deadlocks, bootstrap truncation, auth errors, compaction timeouts, and more. Use this skil...

Practical memory architecture for OpenClaw agents. Helps agents remember commitments, retrieve context, prevent repeat mistakes, compile reusable procedures,...

First-run setup wizard for new OpenClaw agents. Interviews the user to generate a tailored SOUL.md, scaffolds memory architecture, installs recommended crons...

Lock down any LLM agent against prompt injection, data exfiltration, social engineering, and channel-based attacks. Use when setting up a new agent, auditing...

Route high-value content into a Notion workspace with a quality gate, destination mapping, and exact MCP write patterns. ALWAYS trigger when the user says "s...

Multi-model council review that spawns 3-5 independent AI reviewers and applies mechanical synthesis — votes decide, not orchestrator opinion. Use when you n...

Output validation gates for AI agent systems. Prevents hallucinated data, leaked internal context, wrong formats, duplicate sends, post-compaction drift, and...

Encrypted backup and restore for OpenClaw agents. Creates two-tier archives: cloud-safe operational backups plus optional age-encrypted secrets for local rec...

Audit and improve an agent at the right layer: persona/tone, constitutional and operating rules, memory architecture, or skill portfolio / reusable workflows...