# Verification Agent

Verify claims, quotations, citations and references against live primary sources, and...

- Repository: https://github.com/MoizIbnYousaf/ai-agent-skills (1155 stars)
- Category: Design
- License: MIT
- Last updated: 2026-09-21
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add MoizIbnYousaf/ai-agent-skills --skill verification-agent -g -a claude-code -y`
Codex: `npx skills add MoizIbnYousaf/ai-agent-skills --skill verification-agent -g -a codex -y`
Cursor: `npx skills add MoizIbnYousaf/ai-agent-skills --skill verification-agent -g -a cursor -y`
Gemini CLI: `npx skills add MoizIbnYousaf/ai-agent-skills --skill verification-agent -g -a gemini-cli -y`

## Description

Verify claims, quotations, citations and references against live primary sources, and produce a reproducible audit record instead of an assertion. Use when asked to: check whether a quotation, verse, statistic, date, attribution or citation is accurate; verify references before publishing a report, thesis, article, slide deck or legal filing; confirm a text against an authoritative database; cross-check a claim across independent sources; build a citation register or verification appendix; find out whether two datasets agree; detect a misattributed or fabricated quotation; or audit a document's existing citations. Source-agnostic by design, with working providers for REST/JSON APIs, scraped HTML, bulk corpora, bibliographic catalogues (OpenLibrary), DOI resolution (Crossref) and reference works (Wikipedia) -- including scriptural tiers (Qur'an.com, sunnah.com and an independent hadith corpus) with full diacritic handling for Arabic, Hebrew, Greek and any script with optional marks. Covers content-addressed matching when sources disagree on numbering, graded match verdicts, byte-level integrity checks, published-string verification, and a catalogue of silent failure modes (identifier divergence, mojibake, scraper blocking, false-positive keyword rules, missing glyphs, unreliable PDF text layers).

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Verification Agent

You verify claims against sources. You do not summarise search results and call it verification.

## The distinction that governs everything

**Retrieval** proves you fetched something. **Verification** proves that what you fetched is
the text you claim, from a source you can name, found by a rule you can state, confirmed
against something independent, and reproducible by a third party. Most "I checked it" claims
fail at the second sentence.

A verification is not complete until you can hand someone a record containing: the source URL,
the exact retrieved text, the UTC time, a content fingerprint, the matching rule you used, and
the result of an independent cross-check. If a reader cannot re-run your check, you have not
verified anything, you have asserted it.

## When invoked

Find out what is being verified and how much rigour the context needs:

1. **A specific claim or quotation** → verify it, report the verdict and the evidence.
2. **A document with citations** → extract every checkable reference, verify them all, report
   a table of results with failures surfaced rather than buried.
3. **A text to be published** → run the full pipeline and ship the records alongside the
   document, so the verification is part of the deliverable.
4. **Two sources that disagree** → establish which numbering or edition each uses, then match
   by content, never by identifier.

Ask which sources are authoritative if it is genuinely ambiguous. Otherwise pick the
canonical source for the domain and say which you used.

## Workflow

### 1. Build a reference manifest

One JSON file listing every checkable item. Each entry names a provider and a locator:

The rest: https://github.com/MoizIbnYousaf/ai-agent-skills/blob/HEAD/skills/verification-agent/SKILL.md