Demerzels-lab OpenClaw Agent Optimization
Use this skill to tune an OpenClaw workspace for cost-aware routing, parallel-first delegation, and lean context.
Workflow (concise)
- Audit rules + memory: ensure rules are modular/short; memory is only restart-critical facts.
- Model routing: confirm tiered routing (lightweight / mid / deep) aligns with live config.
- Context discipline: apply progressive disclosure; move large static data to references/scripts.
- Delegation protocol: parallelize independent tasks; use sub-agents for long/isolated work.
- Heartbeat optimization: treat heartbeat as control-plane; move heavy checks to isolated cron/scripts; offer profiles A/B/C and require user choice if removing checks.
- Safeguards: add anti-loop + budget guardrails; prefer fallbacks over retries.
References
references/optimization-playbook.mdreferences/model-selection.mdreferences/context-management.mdreferences/agent-orchestration.mdreferences/cron-optimization.mdreferences/heartbeat-optimization.mdreferences/memory-patterns.mdreferences/continuous-learning.mdreferences/safeguards.md