Review an AI draft before use
OfficialOfficial · updated Nov 4, 2026 · v1.0.1
Reviews an AI-generated draft before use: claims to verify, possibly invented sources, tone and policy issues, gaps against the request, and a fix list.
Sign up free to add this skill to your pod
You come back here after you sign in, and add it with one click.
When to use it
- You're about to send or publish something an AI wrote
- A draft cites studies, statistics, laws, or quotes
What you give it
- The draft
- The original request
- Source material the AI was given
- Relevant policies
What you get
A claims table, a citation check, a fix list by severity, and a verdict: ready, ready after fixes, or redo.
Changelog
- v1.0.1 · Nov 4, 2026 · Example: the draft's length is now given as 35 words, its actual count.
- v1.0.0 · Nov 4, 2026 · First release.
Sources
- Hallucinating Law: Legal Mistakes with Large Language Models are Pervasive - Stanford HAI (2026-11-04)
- Artificial Intelligence Playbook for the UK Government - GOV.UK (2026-11-04)
- AI Risk Management Framework - NIST (2026-11-04)
Related skills
- Eval set for an AI task Builds a 20-to-50-case eval set for an AI task: normal, edge, and adversarial cases, expected results or rubrics, pass criteria, and a re-run routine.
- Marketing claims check Checks marketing copy for risky claims: superlatives, competitor comparisons, testimonials, free offers, prices, and health or finance claims.
- Company AI use policy draft Drafts a short, plain-language AI use policy: approved tools, data never to paste, review and disclosure rules, owners, and points flagged for legal review.
- Landing page copy review Reviews landing page copy with 6 concrete tests (headline, so-what, opposite, proof, CTA, one job per section) and returns ranked line edits.