agent-memorylisted

Memory management for AI agents: Ebbinghaus forgetting curve, YAML frontmatter, tiered recall (core/active/warm/cold/archive), decay maintenance, creative random recall. Triggers: "memory management", "organize vault", "memory decay", "forgetting curve", "context budget", "memory bloat", "tier search", "creative recall", "memory health". Does NOT use for: general note-taking, project documentation, or CLAUDE.md configuration.
bestmark1/Agent-memory-skill · ★ 0 · AI & Automation · score 62

Install: claude install-skill bestmark1/Agent-memory-skill

# Agent Memory Management Memory system with automatic decay, tiered search, and creative recall. Works with any directory of markdown files. ## When Invoked 1. **Pick the command** from the request; ask only if it's ambiguous: - **Setup**: bootstrap YAML frontmatter on existing markdown files (`init`) - **Maintenance**: run decay to update relevance scores and tiers (`decay`) - **Health check**: show tier distribution and context budget (`stats`, `scan`) - **Creative recall**: surface random forgotten cards for brainstorming (`creative`) - **Search**: find cards by query filtered by tier (`search`) - **Promote/demote**: manually change a card's tier (`promote`, `demote`) - **Touch**: mark a card as recently accessed (`touch`) - **Compress**: generate L1 summaries and cache token counts (`compress`) - **Generate L1**: regenerate L1 summary for cards (`generate-l1`) 2. **Determine target directory** — take it from the request or context; ask if it isn't clear 3. **Run the appropriate command** via `python3 <skill_dir>/scripts/memory-engine.py <command> <args>` 4. **Report results** — summarize what changed (files modified, tier distribution, recommendations) 5. **Suggest next steps** — e.g., "run `decay` daily via cron", "consider promoting X to core" ## Quick Start ### 1. Scan existing files ```bash python3 scripts/memory-engine.py scan <directory> ``` Reports: file count, YAML coverage, size, recommendations. ### 2. Bootstrap YAML frontmatter