← ClaudeAtlas

budget-reallocationlisted

Ranks every line on both platforms by what a conversion actually costs there, names which are donors and which are recipients, and models three transfer sizes with the projected conversions and blended return for each, including moving money between platforms rather than only within one. Proposes scenarios for approval and moves nothing. Use when the split between platforms was set by history rather than by evidence. Boundary: `scaling-facebook-ads` adds budget to one proven winner in small steps without resetting its learning, `paid-media-audit` finds waste without proposing where it should go instead, and `stockout-alerts` pauses for stock reasons; this shifts money between existing lines.
sidchaudhary/gtm-skills · ★ 1 · AI & Automation · score 74
Install: claude install-skill sidchaudhary/gtm-skills
# The Budget Reallocator Ranks every line across both platforms, names donors and recipients, and models three transfer sizes with projections - as scenarios the user approves by name. Moves nothing. ## Before you write **Depth and currency.** This skill works on platforms that change. Before answering, check the current state of anything version-dependent against vendor documentation, then practitioner sources, and cite what you find with the date. Under the answer, give the reasoning with the arithmetic shown, what you ruled out and why, and what would change the recommendation. House rules 2b and 2c govern. A thin, templated output is a failure here even when every field is filled in. **Run the input list below before you write anything. If one of those inputs is missing, ask for it and stop. Do not return a draft with a warning on it.** The user copies the draft and leaves the warning behind, so a caveat protects you and not them. **Ask at most THREE questions. Hard cap.** Before anything becomes a question, get it yourself: read `.agents/product-context.md`, fetch the site or page they named, compute it from numbers they already gave, or look up the platform default. Whatever is left after that, and everything past the third question, becomes a stated assumption the user corrects in one word rather than a question that stops the work. Number them, and say what you will assume if one goes unanswered. Check `.agents/product-context.md` first so you never ask for somet