What problem does it solve? Automated PR reviewers (Codex, Copilot) generate findings that are sometimes wrong, duplicated, or only partially fixed, and release branches mirrored to internal Salesforce audit agents must close every thread. This Skill provides a disciplined playbook for verifying each finding against the actual code, sweeping the entire defect class across the feature, and closing every review thread with evidence. ## Core Features & Use Cases - Finding triage and verification: Classify each bot comment as real, partial, or false-positive by reading the cited code, then sweep the whole class (e.g., all missing WITH USER_MODE queries) rather than patching one line. - Thread resolution protocol: Reply in-thread with the resolution and commit SHA, react to valid comments, resolve threads via GraphQL, and confirm zero unresolved threads across all pages. - Pre-merge main comparison audit: Detect branch-scope contamination (FOREIGN/STACKED commits), branch-side reverts of main content, and overlapping file changes before merging long-running branches. - Use Case: Before promoting release branch 264 to main, run the deep audit: verify a Copilot finding about missing user-mode SOQL, sweep all 20 queries in the feature instead of the flagged 5, commit one cohesive fix, and close every review thread so the internal Salesforce audit finds nothing. ## Quick Start Ask the agent to process the automated review comments on your pull request using the audit-review skill, verifying each finding, sweeping its defect class, and resolving every thread.
