Menú
Two-layer memory system with grep-based recall.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Schedule reminders and recurring tasks.
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
Business process analysis and improvement. Use when mapping, analyzing, or optimizing processes.
Requirements gathering and documentation. Use when eliciting, documenting, or validating requirements.
Cross-functional company operations: status tracking, decision logging, and inter-department coordination. Use when managing company-wide processes.
| name | memory |
| description | Two-layer memory system with grep-based recall. |
| always | true |
.agents/memory/MEMORY.md — Long-term facts (preferences, project context, relationships). Always loaded into your context..agents/memory/HISTORY.md — Append-only event log. NOT loaded into context. Search it with grep.grep -i "keyword" .agents/memory/HISTORY.md
Use the exec tool to run grep. Combine patterns: grep -iE "meeting|deadline" .agents/memory/HISTORY.md
Write important facts immediately using edit_file or write_file:
Old conversations are automatically summarized and appended to HISTORY.md when the session grows large. Long-term facts are extracted to MEMORY.md. You don't need to manage this.