# Ololand Forensic Qoe Verify

> Use when the user asks to run the OloLand /verify workflow. Verify every dollar and percentage figure in an externally-drafted artifact (an IC memo, analysis, or answer — e.g. one drafted in Claude Cowork) against an OloLand deal's INGESTED data room. For each figure, evidence is retrieved per-claim from the corpus (not pasted by you) — so it confirms a number against the real source, or flags a source elsewhere in the data room that contradicts it, including evidence the author never cited. Per-figure PASS / FAIL / UNVERIFIED with corpus number reconciliation, an NLI derivation check, an independent grader, and a content-hashed provenance pack. No deal yet? It walks you through creating one.

## Facts
- Page: https://tashan.sh/capability/skill-ololand-ai-ololand-forensic-qoe-verify
- tashan id: skill:ololand-ai/ololand-forensic-qoe-verify
- Source: https://github.com/ololand-ai/ololand-plugins
- Type: skill
- Category: security
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 79.0
- Freshness: 94.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- License: Apache-2.0
- Official: no

## Install

```sh
cp -r ololand-forensic-qoe-verify ~/.claude/skills/
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-14 by tashan (https://tashan.sh) from public evidence. Scorer s5.