★ 164 Rust NOASSERTION sse 更新 4分钟前

Meta Skill

Local-first skill management platform for AI coding agents: dual SQLite+Git persistence, semantic search, bandit-optimized suggestions, and MCP integration

GitHub

安装配置

暂未识别到可直接复制的 MCP 配置，请查看 GitHub README。后台管理员可以补充配置。

README 摘要

# ms [![License: MIT](https://img.shields.io/badge/License-MIT%2BOpenAI%2FAnthropic%20Rider-blue.svg)](./LICENSE) **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. Quick Install ```bash cargo install --path . ``` **Or run without installing:** ```bash cargo run -- ``` Works on Linux, macOS, and Windows. Requires Rust 1.85+ (Edition 2024). --- ## 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 ```bash # 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 # Get context-aware suggestions ms suggest # Analyze skill dependencies ms graph insights # Start MCP server for AI agent integration ms mcp serve ``` --- ## Why This Architecture ### Dual Persistence: Speed + Accountability Every skill is stored twice: - **SQLite** for fast queries, filtering, full-text search, and metadata operations - **Git archive** for immutable history, diffs, and audit trails This mirrors how production systems balance operational speed with accountability. SQLite handles the "what do I need right now?" questions in milliseconds. Git answers "what happened and why?" when you need provenance. The split also enables resilience: if the database corrupts, skills can be rebuilt from Git. If Git history is unavailable, the database still serves queries. Neither persistence layer is privileged—they serve dif...

Meta Skill

安装配置

README 摘要

相关 MCP

Awesome S

Chrome Devtools

Libre Chat

Playwright

Github

Fast