Repowise · Codebase intelligence
addyosmani / agent-skills
Production-grade engineering skills for AI coding agents.
Does the health score find the bugs?
Repowise ranks every file by predicted defect risk. Of the 20 files it flags as riskiest, 5 (25%) actually needed a bug fix in the last 6 months — 4.7× better than picking files at random.
Languages
- markdown67.7%
- toml17.2%
- shell7.5%
- json4.3%
- javascript2.2%
- yaml1.1%
Explore addyosmani/agent-skills
Code health
Full report- Code health99
- Dead code100
- Hotspot density98
- Bus factor95
How addyosmani/agent-skills works
Production-grade engineering skills for AI coding agents. This page is an auto-generated, always-fresh map of the addyosmani/agent-skills repository, written primarily in Shell. Repowise indexes the source, parses every symbol, computes a dependency graph, scores per-file code health from complexity, duplication, test coverage and churn, mines git history for hotspots and ownership, and lifts the resulting architectural decisions into a wiki you can read or query through MCP.
The codebase has 93 source files, 14 symbols, and 6 languages. Git churn analysis flags 1 high-frequency files as hotspots — places where bugs, rewrites, and code review tend to concentrate. The dependency graph clusters into 93 tightly-coupled module communities.
Use the panels above to open the interactive dashboards, or connect this repo to your editor via the Repowise MCP server for grounded answers inside Claude, Cursor, or VS Code.