Offer Desk

Paste rough candidate/offer notes — a ready-to-send offer letter, the gaps worth filling, the assumptions made and why, out.

Back to SkillSafe
Or pick a file: it is read locally, nothing uploads until you run.
How it works

Nothing to hand? Load the — notes with role, comp, and a start date all stated, and a clean offer with zero gaps — the , where there isn't enough to draft from and the honest reply says so, or the , where the notes compare the offer to a named colleague's pay and the letter has to work around it.

1

Paste your notes — the prescan is free

No upload, no AI: the prescan reads your notes in your browser and reports word, sentence, paragraph and heading counts, and two families of flag — missing essentials (no compensation figures, no start date, no clear candidate/role) and named-colleague pay-comparison language ("matches what we pay Alex"). Each family explains why it matters. This part costs nothing and happens while you type.

2

The AI drafts it — this is the metered part

A pass over your whole notes: the gaps worth filling before sending (each with a category and severity), the assumptions made to produce a complete letter (each with why it was reasonable), a full offer letter with compensation, start date and terms plus negotiation guidance for the hiring manager, and plain-English highlights of the notable choices made. For every prescan flag, the model addresses it or explains why it left it as a gap — and a named-colleague pay comparison is never repeated in the letter itself. Pricing is honest: a worst-case amount is reserved before the run and only what the run actually uses is charged — the meter next to the button shows both.

3

Export and iterate

Copy the generated offer alone, or the full report as Markdown. Download the offer as plain text, the full report as Markdown or JSON. Past offers are saved to your SkillSafe account, so they are there on your laptop and your phone: restore one, tweak the notes, and re-run.

A derived work of @anthropics/draft-offer (github.com/anthropics/knowledge-work-plugins).