Update audit skills

[AlexJSully]

Update the audit-docs skills for missing AI generated historical comments and the other audit quality skills for it missing violations of DRY & SOLID.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
portfolio	Ready	Preview	Aug 13, 2026 10:40pm

[Copilot]

Pull request overview

This pull request updates the repository’s audit prompts/skills (docs, PR review, and quality audits) to better catch AI-generated historical comments and to treat structural code-quality issues (DRY/SOLID, module shape) as evidence-backed findings via counts. It also includes a set of dependency upgrades via package.json/package-lock.json.

Changes:

• Extend audit prompts/skills to support “structural findings” evidenced by counts (file length, interface/member size, directory size, repeated blocks) and to re-verify counts during refutation.
• Strengthen comment guidance to flag “comments that explain an absence” using the “name the line it describes” test.
• Upgrade several dependencies (Next.js, Firebase, Sentry, Webpack, tooling) and refresh the lockfile accordingly.

Reviewed changes

Copilot reviewed 15 out of 16 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
package.json	Bumps runtime/dev dependency versions (Next.js/Firebase/Sentry/Webpack, tooling).
package-lock.json	Updates lockfile to match the dependency version bumps.
CLAUDE.md	Expands “current state only” guidance with the “name the line” test for comments.
.github/prompts/audit-quality.prompt.md	Adds structural-findings-by-count guidance and related refutation/evidence clarifications.
.github/prompts/audit-pr.prompt.md	Adds structural finding “Measured” field and updates triage/guidance to include structural triggers.
.github/prompts/audit-docs.prompt.md	Tightens doc creation placement rules (Diátaxis-based) and adds the “name the line” test for comments.
.github/copilot-instructions.md	Mirrors the “name the line each comment describes” guidance in Copilot instructions.
.claude/skills/typescript-code-and-test-standards/SKILL.md	Extends the skill scope to include measured structure (counts) and updates review procedure accordingly.
.claude/skills/typescript-code-and-test-standards/references/comments-and-jsdoc.md	Adds reference section covering “comments that explain an absence”.
.claude/skills/typescript-code-and-test-standards/agents/comment-and-jsdoc-auditor.md	Adds a concrete check for comments describing something the file does not contain.
.claude/skills/audit-quality/SKILL.md	Mirrors audit-quality prompt updates for structural findings and measurement-first guidance.
.claude/skills/audit-pr/SKILL.md	Mirrors audit-pr prompt updates for structural findings, triage triggers, and refutation guidance.
.claude/skills/audit-pr/agents/finding-refuter.md	Extends the refuter to validate structural findings by re-deriving counts and handling premature abstractions.
.claude/skills/audit-docs/SKILL.md	Mirrors audit-docs prompt updates (Diátaxis placement + “name the line” comment test).
.claude/skills/audit-docs/agents/surface-auditor.md	Adds the “comment describes something not in file” pattern as an explicit audit target.
.claude/rules/docs-authoring.md	Updates the “current state only” rule to include the “name the line” comment test.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.