Get a new developer up and running with the Chops codebase — prerequisites, build, architecture, and common tasks.
81%
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 skill’s runtime workflow (via SkillScanner/FileWatcher) scans and parses Markdown/frontmatter from tool directories on the local filesystem (e.g., `~/.claude/skills/`, `~/.agents/skills`, etc.), which are user-accessible locations and can contain outsider-authored free text.
Shpigford/chops
9d379d5
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.