Remember

Stores decisions, patterns, and outcomes in a knowledge graph that persists across sessions. Useful when you want Claude to remember why you chose Postgres over MongoDB, what anti-patterns to avoid, or which pagination strategy worked. It extracts entities and relationships automatically (detects "X uses Y" patterns, capitalized tech names, agent IDs) and writes them to the MCP memory server. The editor's note at the top is worth reading: it explains when to use filesystem memory versus the graph. Short version: use files for grep-able state, use this for traversable knowledge you'll query later. Supports outcome tracking with success and failed flags, plus agent-specific or global scoping. Auto-detects categories but asks for confirmation before writing.

skills.sh installs: 228
GitHub stars: 301
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yonatangross/orchestkit --skill remember --agent claude-code

Installs into .claude/skills of the current project.

Files

Remember - Store Decisions and Patterns

Filesystem vs MCP memory (Opus 5.5 guidance, CC 2.1.111+): Opus 5.5 reads filesystem memory reliably across multi-session work. Use that to your advantage:

Short-lived handoff state (current phase, task in-progress, pending approvals) → .claude/chain/*.json files. Small, structured, session-scoped.

Durable auto-memory (user facts, feedback, project conventions) → ~/.claude/projects/<slug>/memory/*.md files with a one-line index in MEMORY.md. Read on every session start.

Cross-session knowledge graph (typed entities + relations for query traversal) → MCP memory server (this skill's default path). Best when future sessions will search for patterns.

The three are complementary, not alternatives. Prefer fs for anything you'd want to grep; prefer MCP for anything you'd want to traverse.

Store important decisions, patterns, or context in the knowledge graph for future sessions. Supports tracking success/failure outcomes for building a Best Practice Library.