Use when upgrading a Rails application from one version to another, assessing upgrade readiness, planning a multi-hop upgrade path, or investigating breaking changes, deprecation warnings, gem compatibility issues, or config.load_defaults transitions between any Rails versions from 5.2 through the latest release.
76
95%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required runtime workflow ingests outsider-authored free text from GitHub compare content by fetching railsdiff.org config diffs via the GitHub API (URL-based fetching using WebFetch) in Step 2, which reads file-change text that can include attacker-controlled content from GitHub branches/commits.
lucianghinda/superpowers-ruby
99fac3d
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.