All authors
Claude Skills by savannahfeder
github.com/savannahfeder8 skills0 installs0 views
- Blast RadiusBefore a change ships, find what it could break outside its own diff, and prove the one fact it is safe because of by running real code rather than writing an argument. Use when a small change touches main/, shared/, the store, worker spawning or anything another part of the app reads, when reviewing a diff you do not trust, or when asked what could this break or what is the blast radius.Votes: 0GitHub stars: 77
- CorrectFind the mistakes agents keep repeating in this repository and make each one impossible, by changing the code's structure first, then a check that fails loudly, then a test, and a written rule only last. Proves each new check goes red on a real past mistake. Use when asked to run /correct, or after the maintainer corrects agents for the same thing twice.Votes: 0GitHub stars: 77
- InterrogateHave two different models, Claude and Codex, try to break a change independently, then sort what they found into act on, consider, noted and dismissed. Findings both models raise on their own are the strongest signal. Reports only and changes no code. Use when asked to interrogate, stress test, tear apart or get a second opinion on a diff, or before shipping a change the blast-radius skill calls wide.Votes: 0GitHub stars: 77
- Maintain Verify AgentboxThe upkeep pass for .claude/skills/verify-agentbox. Re-reads every feature in its map from source, drives every feature live, and fixes the map, drives, stand-in or machine shapes where the app has moved, as one commit of proven corrections. Use when asked to maintain or audit the verify skill, after a change that moves a user path (a shortcut, a screen, how a worker is spawned), or on its weekly repeat.Votes: 0GitHub stars: 77
- Review Pull RequestsOne pass of the maintainer's pull request loop for this repository. Finds open pull requests on GitHub that have no review yet, reviews each one (safety first, then quality, then its tests run walled off from the network and the home folder), and files one summary per pull request into the Agentbox inbox to merge, send back or close. Use when asked to review pull requests, check the PR queue, or run "/loop 30m /review-pull-requests".Votes: 0GitHub stars: 77
- Trim CommentsCut the comments in a change down to the ones that earn their place. A comment stays only when it says why the code is the way it is and the code cannot say it. The story of how a bug was found goes in the commit message and the test, not above the function. Use on your own diff before you commit, when a change reads as over-commented, or when asked to trim comments, cut comments or unslop code.Votes: 0GitHub stars: 77
- UnslopCut the habits that make writing read as machine-made. Use on anything you write while building Agentbox that a person will read, including code comments, commit messages, docs, CLAUDE.md, test headers, pull request text and your answer at the end of a task, or when asked to unslop, de-slop or make writing plain.Votes: 0GitHub stars: 77
- Verify AgentboxProve an Agentbox change works the way a person meets it, before it ships. Runs the app's own tool-finding and worker setup on fake Macs unlike this one, reads this Mac for real, drives throwaway copies of the app by keyboard (agents on Claude Code and Codex, several at once, logins out of usage, restarts, replies landing on the right thread) on stand-ins, on the real tools, and through the installed app, then sets an agent loose to break it. Use before shipping anything under main/, shared/,...Votes: 0GitHub stars: 77