Quality

AI Code Review analyzes code changes and produces a structured review with checks, risks, and actionable recommendations. Use it when you need a repeatable review workflow with project context and quality validation.

Check Coverage ensures a CLI handler and its tests cover all documented commands, flags, and edge cases. Use it when adding a new command or auditing existing handler coverage.

Debug helps diagnose incorrect Dippy approval or block behavior from a reported command, expected result, and logs. It guides a minimal fix by reproducing the bug with a failing test first and then verifying it passes.

Verify Counts checks numerical claims in documentation against current values in code and tests. Use it when README or reference docs mention counts that may drift over time.

Accessibility Audit checks web pages for WCAG issues, screen reader support, and keyboard navigation. Use it to find missing alt text, labels, heading structure problems, and broken ARIA references.

CLI Review runs a Greptile review on the current local branch, handling CLI presence and sign-in checks, then summarizes findings. Use it before a PR or from a local checkout when you want branch feedback.

End-to-End Testing simulates user interactions in a web app and verifies expected outcomes. Use it to test pages, forms, navigation, login flows, validation, and deployment checks.

Implement Review runs a staged-change review loop that detects content type, routes changes to a reviewer, categorizes feedback, revises, and iterates. It is used for code, papers, proposals, and other text outputs, including plan-first reviews for larger tasks.

Web Interface Guidelines reviews UI code against the latest web interface rules and reports findings in terse file:line format. Use it for UI reviews, accessibility checks, design audits, and best-practice checks.

Wiki Lint checks a local wiki for broken links, orphan pages, missing frontmatter, empty sections, contradictions, stale content, and index drift. Use it to audit knowledge-base health and generate a lint report with follow-up suggestions.

Analyzing Changes analyzes code diffs to estimate impact scope, flag documentation drift, and check whether tests or design docs need updates. Use it before commits, after refactors, or when reviewing cross-module changes.

Blue Team Detection And Response covers detection rule writing, SIEM/EDR tuning, incident response, forensic analysis, threat hunting, and purple team exercises. Use it when building detection-as-code and closing the loop to ATT&CK.