Sipcode
Inspect token usage, costs, and usage limits from local coding-agent logs.
Discover, translate, and manage skills across AI coding agents

SkillKit is a local command-line package manager for AI agent skills. It gathers skills from multiple sources and translates their instructions into formats used by coding assistants such as Claude Code, Cursor, and Codex. Developers can search for skills, install collections, and receive recommendations based on a codebase.
The toolkit also includes persistent session memory, codebase-derived agent instructions, workflow composition, and a Git-based manifest for sharing a team's setup. Scanning and testing tools help inspect skills before they enter development workflows. REST, MCP, and Python interfaces support programmatic discovery. SkillKit suits developers who maintain reusable instructions across several assistants and projects.
Tried it? Share a useful thought or ask a question.
Good conversations start with a hello.
Sign in to comment