Best fit
CRM, ticketing, payroll, event, and mailing exports strip marks or normalize names inconsistently, creating disrespectful display errors and false deduplication.
// Business & Operations
Name & Diacritic Integrity Auditor
Find diacritic loss, normalization drift, mixed scripts, and unsafe identity-record collisions without auto-merging people.
What problem does Name & Diacritic Integrity Auditor solve?
CRM, ticketing, payroll, event, and mailing exports strip marks or normalize names inconsistently, creating disrespectful display errors and false deduplication.
Use it to
- Audit name display after a system migration
- Find distinct people collapsed by accent stripping
- Catch invisible controls and mixed scripts in identity data
What it returns
- result.json with PASS, REVIEW, BLOCK, or CANNOT_ASSESS
- report.md human-review handoff
- manifest.json with stable output declarations and SHA-256 hashes
A representative input and result
input Supply records with recordId, sourceSystem, rawName, displayName, and canonicalPersonId. Preserve source strings exactly.
result A deterministic PASS, REVIEW, BLOCK, or CANNOT_ASSESS result with stable finding codes, report, manifest, and SHA-256 receipts.
Access and approval boundaries
- Terminal permission to run the bundled local Python gate.
- Read access to one owner-selected UTF-8 JSON packet.
- Write access only to one new owner-selected local output directory.
- No browser, network, credential, account, messaging, payment, import, upload, merge, delivery, or publication permission.
Known limitations
- It does not decide a person's preferred name or identity.
- It never merges, deduplicates, or updates records.
- Mixed scripts and normalization differences are review signals, not proof of fraud or error.
// choose with context
Is Name & Diacritic Integrity Auditor the right skill?
It returns
result.json with PASS, REVIEW, BLOCK, or CANNOT_ASSESS. report.md human-review handoff.
Do not use it as
It does not decide a person's preferred name or identity.
Compatibility, access, version, and licence
- Reads or accesses
- Declared local scope: one owner-selected local JSON input, one new owner-selected local output directory.
- Compatibility
- SKILL.md-compatible agents that can run a local Python helper. Python 3.10 or newer on Windows, macOS, or Linux using only the standard library. One documented UTF-8 JSON evidence packet; no API key or provider account.
- Version
- 1.0.0
- Licence
- Review the package licence and seller terms at the linked destination.
Questions
Does it connect to or change a live system?
No. It reads one local packet, writes one new local output directory, and makes no network request.
Does PASS prove the evidence or language is correct?
No. PASS only means no encoded rule fired in supplied normalized evidence.
What happens when evidence is missing?
The gate returns CANNOT_ASSESS or BLOCK; missing evidence never becomes a pass.
Is the result deterministic?
Yes. Findings are sorted and persisted outputs carry stable SHA-256 receipts.
Does the skill publish or make first-person claims?
No. It never publishes, contacts anyone, or adopts a founder, candidate, artist, or reviewer voice.
Name & Diacritic Integrity Auditor keeps proof and approval boundaries visible.
The listing includes the tested package, realistic samples, declared permissions, and known limitations.
Get Name & Diacritic Integrity Auditor on Agensi