Read and curate the Napkin Runbook format at session start.
npx skills add https://github.com/NEXUZ-SYS/devflow --skill napkin-nexuz-sys
Please help me install this Agent Skill. Skill: napkin Source: https://github.com/NEXUZ-SYS/devflow/tree/main/skills/napkin Command: npx skills add https://github.com/NEXUZ-SYS/devflow --skill napkin-nexuz-sys
Keeps a continuously curated runbook of recurring mistakes, corrections, and patterns to guide agents, reducing repeated errors and accelerating reliable execution.
Start a session by loading the napkin runbook and consult it before taking action.
High-intent search queries and answers about installing and using this skill.
A persistent memory runbook prevents repeated mistakes by logging corrections and patterns. The agent reads this guidance at session start to apply learned guardrails, ensuring reliable execution across projects.
Maintaining an agent knowledge-base requires an automated curation policy that re-prioritizes items, merges duplicates, removes stale entries, and enforces category limits on every read, keeping the runbook continuously optimized.
Structure agent memory with dedicated per-agent sections within a standard template. This format separates domain-specific notes and categorized learnings to guide individual agents while maintaining a unified runbook structure.
Yes, you can enforce guardrails using a markdown runbook at .context/napkin.md. The agent reads this file at session start to apply established patterns and restrictions before taking any project actions.
Agent memory curation works across Full, Lite, and Minimal operation modes. It consistently reads the standard template and applies the curation policy to maintain the runbook regardless of the selected mode.
A curation policy for persistent memory prevents unbounded growth and redundancy. It automatically enforces caps, merges duplicates, and removes stale items on every read, keeping the runbook actionable and concise.
DeL-TaiseiOzakiLoad shared project context from the .claude directory for Gemini CLI.
z1439527767Design autonomous AI agents with reliability controls for multi-step tool workflows.
michael-conradCoordinate Playwright browser actions across isolated sub-agents for multi-step automation.
eliottbusinessBuild and maintain interlinked markdown knowledge bases with cross-references.
