← Back to collections
🎭
Muse & Memory Skills for Claude Code
Curated MUSE collection: session continuity, layered context, and searchable project memory — for creation, productivity, and agent-powered workflows.
About this collection
This collection gathers every muse & memory skill we've evaluated for Claude Code and AI coding agents — 6 skills so far, each scored on the same six-dimension rubric: trigger quality, structure, workflow design, content, engineering, and security.
Every skill below is free and open source. Install any of them in one line with curl -fsSL https://skill123.me/install/<skill>.sh | bash, or open a skill's page to see its full scorecard, documentation, and all install methods before you download.
MUSE Continuity Commands
Productivity
/resume, /save, /bye — preserve role, decisions and evidence across Codex or Claude Code sessions.
8.5
Layered Context Loading
Data & Analytics
L0/L1/L2 three-layer context protocol — cuts token consumption on /resume boot.
8.3
Strategic Compact
Productivity
Manual compaction at logical task boundaries instead of arbitrary auto-compaction mid-phase.
8.2
MUSE Semantic Search
Data & Analytics
Zero-dependency TF-IDF search across MUSE memory, roles and skills.
8.1
Agent Protocol Spec
Developer Tools
Machine-readable role files enabling multi-agent coordination and tool interoperability.
7.9
Context Health Check
Developer Tools
Check real session context metrics; reassess after compaction without guessing model limits.
7.4