ms
<div align="center" <img src="msillustration.webp" alt="ms - Meta Skill CLI: A local-first skill management platform" </div
<div align="center"
</div
Meta Skill (ms) is a local-first skill management platform that turns operational knowledge into structured, searchable, reusable artifacts. It provides dual persistence (SQLite + Git), hybrid search (lexical + semantic), adaptive suggestions with bandit optimization, multi-layer security (prompt injection defense + command safety gates), dependency graph analysis, provenance tracking, and native AI agent integration via MCP.
<div align="center" <h3Quick Install</h3
cargo install --path .Or run without installing:
cargo run -- <COMMAND><p<emWorks on Linux, macOS, and Windows. Requires the pinned <codenightly-2026-08-25</code toolchain (Edition 2024; manifest API floor Rust 1.89).</em</p </div
---
What ms Actually Is
ms is not just a tool for extracting skills from AI sessions. It's a complete skill management platform with these core capabilities:
| Capability | What It Provides | |-----------|------------------| | Skill Storage | Dual persistence with SQLite for queries and Git for audit trails | | Semantic Search | Hybrid BM25 + hash embeddings fused with Reciprocal Rank Fusion | | Adaptive Suggestions | UCB bandit algorithm that learns from feedback to optimize recommendations | | Security | ACIP prompt injection defense + DCG destructive command safety gates | | Graph Analysis | Dependency insights via bv: cycles, bottlenecks, PageRank, execution plans | | Provenance | Evidence tracking linking skills back to source sessions | | Multi-Machine Sync | Git-based synchronization with conflict resolution strategies | | Bundle Distribution | Portable skill packages with checksums and safe updates | | Effectiveness Loop | Feedback, outcomes, experiments, and quality scoring as first-class data | | AI Agent Integration | MCP server exposing skills as native tools for Claude, Codex, and others | | Anti-Pattern Mining | Automatic detection of failure patterns from session history | | Token Packing | Constrained optimization to fit skills within context budgets | | CASS Memory | Integration with cm for playbook rules and historical context |
Skills can come from anywhere: hand-written SKILL.md files, mined from CASS sessions, imported from bundles, or generated through guided workflows. The CASS integration is one input method, not the defining feature.
---
Quick Example
# Initialize a local ms root (.ms/)
ms init
# Configure skill paths
ms config skill_paths.project '["./skills"]'
# Index SKILL.md files
ms index
# Search and inspect
ms search "error handling"
ms show rust-error-handling