staffreview/staffreview
A local, staff-engineer-grade code review tool with AI-coding-agent skills
A local, staff-engineer-grade code review tool with AI-coding-agent skills
npx add-skill staffreview/staffreviewA local, staff-engineer-grade code review tool with AI-coding-agent skills
Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models.
Generate and publish AI explainer documents from any agentic coding tool (Claude Code, Cursor, Copilot, Codex)
Local-first shared memory layer for AI agents. Markdown vault, hybrid keyword+semantic search, autonomous coherence daemon. Works with Claude Code, Claude Desktop, Cursor, any MCP client.
Local-first spec-driven development platform. Pure markdown + git storage. L0/L1/L2/L3 spec hierarchy, 24 validation rules, agent task lifecycle, decision cards, delta changes. CLI + Claude Code skill. No network, no MCP, no backend.
Claude Code plugin marketplace: 145 framework-aware code-review skills plus AI-writing detection, doc and test-plan generation, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, iOS/Swift, and AI frameworks. Installable for Codex and other agents too.
Better Skill Creator - A comprehensive guide for creating effective AI agent skills with dynamic architecture