loading
loading
Review an AI-generated diff for real regressions and security risk, ordered by severity with verify commands.
Runs in Codex on a raw diff and orders findings by severity with verify commands — built for plausible-looking AI PRs that hide a regression.
Listed for review
No verified public repo for this skill yet, so this page does not give you an install command. Skills with a verified source install in one command — or fully manual: copy the skill folder into .claude/skills/ and your agent picks it up.
Boostor Quality Score
84/100 · B
PR Risk Reviewer reads a git diff against its base branch and your repo rules, then returns a code-review report ordered by severity. Each finding references exact files, distinguishes a genuine bug from a style preference, and includes the command you'd run to verify it. It is built for AI-written PRs that look plausible while hiding a regression, a missing test, or a security mistake — and it refuses to invent line references or claim a test passed when it never ran.
Analyze and cut GitHub Actions spend by rewriting slow, expensive workflows.
Aimed at the one bill teams forget to read — it profiles your Actions YAML against real billing data and estimates the savings before touching anything.
Transparent + deterministic: every point above is computed from this skill's real fields plus a prompt-injection safety scan. No black box, no pay-to-rank.
Find the first real failure in a CI log and return the owner, fix path, and rerun command.
Points at the first failing command, not the loudest warning — and stops the agent from editing before it has even read the error.
Create, document, and clean up feature flags across your codebase safely.
Solves flag debt: it tracks every flag and tells you which are safe to delete, then strips the dead branches — so old flags stop rotting in your codebase.