audit-verify

Phase 5: Verify all corrections were applied correctly

6 stars

Best use case

audit-verify is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Phase 5: Verify all corrections were applied correctly

Teams using audit-verify should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/audit-verify/SKILL.md --create-dirs "https://raw.githubusercontent.com/edwinhu/workflows/main/skills/bluebook-audit/skills/audit-verify/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/audit-verify/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How audit-verify Compares

Feature / Agentaudit-verifyStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Phase 5: Verify all corrections were applied correctly

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Phase 5: Verify

Re-scan the corrected DOCX to confirm all fixes were applied and no new issues were introduced.

## What This Phase Does

1. Re-extract all footnotes from the corrected DOCX
2. Re-run mechanical checks (small caps scanner, signal checker, etc.)
3. Compare findings against the original audit - all flagged issues should now be clean
4. Report any remaining issues

## Verification Checks

1. **Formatting scanner**: Re-run `scan_formatting.py --docx corrected.docx` - expect 0 findings (or only known false positives like "Institutional Investors" in titles)
2. **Cross-reference check**: All `[_]` placeholders should be resolved
3. **Signal formatting**: All signals should be italic
4. **Terminal periods**: All footnotes should end with periods
5. **Id. chains**: All id. references should have single-source predecessors
6. **Gemini re-audit on fixed footnotes**: Re-run `gemini_audit.py --subset [all previously flagged FNs]` to catch issues introduced by fixes or missed in the initial pass

### Re-Scan Catches Real Issues

In the "Other People's Votes" audit, the Gemini re-scan on fixed footnotes caught a Wells Fargo press release title (FN206) that wasn't in the original "judgment call" list — it was in the same footnote as other fixes but wasn't flagged initially. The verify phase is not ceremonial; it finds real issues.

<EXTREMELY-IMPORTANT>
## Iron Law: Re-Scan Is Not Optional

The verify phase MUST re-run the scanner on the corrected DOCX. Skipping verification was the root cause of missing 41 small caps fixes in the original audit.

If the re-scan finds issues, go back to Correct phase. Do NOT proceed to Archive with unresolved issues.
</EXTREMELY-IMPORTANT>

## Red Flags

- Skipping the re-scan because "all fixes applied" → run the scanner; silent fix failures are common.
- Dismissing remaining findings as false positives → investigate each one; some "false positives" are real.
- Proceeding to Archive with >0 real issues → fix them first; uncorrected issues persist forever.

## Gate: Exit Verify

Before proceeding to Archive phase:
- [ ] Re-scan completed on corrected DOCX
- [ ] Zero remaining issues (or all remaining are confirmed false positives)
- [ ] If issues found: returned to Correct phase and re-verified

## Next Phase

Read `${CLAUDE_SKILL_DIR}/../../../../skills/bluebook-audit/skills/audit-archive/SKILL.md` and follow its instructions.

Related Skills

visual-verify

6
from edwinhu/workflows

This skill should be used when the user asks to 'verify visual output', 'check how it looks', 'render and review', 'visual verify', 'check the slide', 'does this look right', or when any task produces rendered visual output (slides, charts, documents, UI).

source-verify

6
from edwinhu/workflows

This skill should be used when the user asks to 'verify sources', 'check citations', 'fact-check footnotes', 'verify quotes', 'source check', 'are my cites real', 'check for hallucinated citations', or needs to verify that citations in a legal/academic manuscript actually exist and are accurate. Also use when the user wants to check that quoted text actually appears in the cited source.

ds-verify

6
from edwinhu/workflows

This skill should be used when the user asks to 'verify analysis results', 'check reproducibility', 'validate data science output', or 'confirm completion'.

dev-verify

6
from edwinhu/workflows

This skill should be used when the user asks to 'verify completion', 'check that tests pass', 'confirm feature works', or 'verify the feature is done'.

audit-report

6
from edwinhu/workflows

Phase 3: Generate and present audit report for user review

audit-extract

6
from edwinhu/workflows

Phase 1: Extract footnotes from DOCX with formatting annotations

audit-crossrefs

6
from edwinhu/workflows

Phase 7: Convert hardcoded cross-references to auto-updating NOTEREF fields

audit-correct

6
from edwinhu/workflows

Phase 4: Apply corrections to DOCX

audit-check

6
from edwinhu/workflows

Phase 2: Run mechanical checks and Gemini formatted audit

audit-archive

6
from edwinhu/workflows

Phase 6: Archive URLs via perma.cc

bluebook-audit

6
from edwinhu/workflows

This skill should be used when the user asks to 'audit footnotes', 'check Bluebook formatting', 'audit citations', 'run footnote audit', 'check my footnotes', 'bluebook audit', or needs systematic Bluebook compliance checking of a law review manuscript.

audit-fix-loop

6
from edwinhu/workflows

Canonical doctrine for scored iterative improvement, and the generic fallback for ad-hoc 'iteratively improve / audit and fix / grade and improve / hill-climb quality / score and fix' requests that don't map to a domain workflow.