Find the AWS keys hiding in your git history before someone else does
Scans your repos, config files, and environment for hardcoded secrets, API keys, passwords, and credentials. Checks git history too — that "removed" API key from 6 months ago is still in the commit log.
Create a skill called "Secret Sweeper". Scan for leaked secrets and credentials: 1. Run gitleaks or trufflehog on the git repo (including full history) 2. Scan current files for patterns: API keys, passwords, tokens, private keys, connection strings 3. Check `.env` files, docker-compose files, and CI configs for hardcoded secrets 4. For each finding, indicate whether it looks potentially active based on context or metadata; only attempt active validation if I explicitly approve it 5. For each finding, provide: - File and line number (or commit hash for historical leaks) - Secret type and risk level - Whether it appears to still be active - Remediation: exact steps to rotate and move to a secret manager Also suggest pre-commit hooks and CI checks to prevent future leaks.
Secrets leak in predictable ways: committed to git, left in `.env` files,
hardcoded in Docker configs, or buried in CI/CD variables. This skill
checks all the usual hiding spots.
Faster builds, smaller images, fewer headaches
Paste your Dockerfile and get it back cleaner, smaller, and easier to cache. Good starter recipe for developers because the advice is concrete and the output is easy to compare against the original.
Tame the Dependabot PR flood — auto-merge the safe ones, flag the risky ones
Reviews dependency update PRs by reading changelogs, checking for breaking changes, running tests, and auto-merging patch updates that pass CI. Turns 50 Dependabot PRs per week into 3 that need your attention.
A calm checklist when fraud hits
Immediate steps, reporting sequences, and long-term hardening for scams and identity theft. Organized by urgency so you know what to do first.
Verify brand offers before you click anything
Screens incoming partnership offers for phishing and scam patterns: suspicious domains, attachments, fake checks, requests to "connect your account," and vague contracts. Outputs a risk rating and safe verification steps.