AI Agent Skills

Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 26 languages via tree-sitter. Built for coding agents.

Show ponytail measured impact as a scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display.

Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions. Use for issue triage, change reviews, and code quali…

Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × li…

An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as security vulnerabilities, bugs, and maintainability concerns.