Audit
Eleven open-source, MIT-licensed skills for AI coding agents — /preflight, /audit, /ship, /remember and more. Plain-Markdown agent guardrails for Claude Code, Codex, Cursor & Hermes. Free layer of SlashStack.
npx -y skills add mverab/slashstack-skills --skill auditAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 18 days oldThe repository was created 18 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when reviewing changes for bugs, regressions, and missing tests.
SKILL.md
1.1 KB, as published. Nobody here has run it
Audit
Purpose
Review changes for bugs, regressions, and missing tests.
When to Use
Use when reviewing changes for bugs, regressions, and missing tests.
Workflow
- Review the diff against the original goal. Verify the changes address what was intended.
- Detect issues:
- Bugs: logic errors, off-by-one mistakes, null dereferences.
- Missing edge cases: empty inputs, error paths, boundary conditions.
- Potential regressions: changes that could break unrelated behavior.
- Unintended modifications: files changed outside the intended scope.
- Verify test coverage: confirm tests exist and exercise the changed behavior.
- Look for security issues: injection risks, unsafe defaults, exposed secrets.
Output
If approved: state approval with concrete evidence (files reviewed, tests observed, verification steps taken).
If rejected: list each issue with:
- File reference: the specific file and line context
- Severity: Critical / High / Medium / Low
- Suggested fix: a concrete correction or next step