Land completed Fallow work after review, run pre-push parity, monitor merged-commit CI, and leave repositories clean. Use when asked to ship, merge, or move approved work to main.
83%
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 instructs the agent to interact with GitHub pull requests, commits, and workflow runs via GitHub CLI (`gh`), which processes repository content and metadata.
fallow-rs/fallow
6194072
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.