verified-experiments

Hydra is a Claude Code skill for reviews that benefit from several independent perspectives, such as architecture decisions, security-sensitive changes, and difficult refactors. Standard mode uses four advisors plus a chairman; deep mode expands to six advisors, three reviewers, and optional Codex participation. The final report traces recommended actions back to finding IDs and asks for cost confirmation before running.

Run /roast in Claude Code to review a repository across security, architecture, customer flows, and growth readiness, with findings cited to files and lines and the top three priorities summarized at the end. Optional Semgrep, Gitleaks, and dependency checks add deterministic evidence; their own setup may fetch rules, but audit findings are not uploaded by default. Live-URL checks contact the requested site and Google PageSpeed only when explicitly enabled.

roast-my-code analyzes a project across security, architecture, complexity, testing, type safety, performance, and other categories, then presents findings in a configurable roast style. It runs as a pure Claude Code skill without another API key. Its checks are strongest for JavaScript and TypeScript, with fewer ecosystem-specific rules elsewhere.

skill-validator audits a Claude Code SKILL.md for structural problems, missing fields, weak trigger descriptions, unreplaced placeholders, and marketplace readiness. It produces a 0–10 score, a separate triggering score, critical issues, warnings, strengths, and one concrete recommended next step for each problem.