# Ultra Research

> Exhaustive deep investigation via GREP (CAN TAKE UP TO 1 HOUR). Use for the most demanding research tasks — security audits, legal research, regulatory analysis, full ecosystem surveys, multi-source synthesis, adversarial threat modeling, or any query where completeness matters more than speed. Use sparingly; this tier is slow and cannot be block-waited in a single call. The skill submits the job then schedules a /loop cron that polls every 5 minutes until complete. Use /research (~5 min) for most tasks, or /quick-research (~25s) for simple lookups.

## Facts
- Page: https://tashan.sh/capability/skill-parcha-ai-ultra-research
- tashan id: skill:Parcha-ai/ultra-research
- Source: https://github.com/Parcha-ai/grepai-skills
- Type: skill
- Category: security
- tashan score: not scored (catalogued only — too little public evidence)
- Adoption: 9.0
- Upkeep: 100.0
- Freshness: 100.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: not yet graded
- Official: no

## Install

```sh
cp -r ultra-research ~/.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 2026-09-12 by tashan (https://tashan.sh) from public evidence. Scorer s5.