ad-policy-check
Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the…
Prices a creator you have already vetted. Gives a low and a target fee from median views and the platform's typical cost per 1,000 views, a walk-away ceiling from your goal and margin, and usage rights priced on their own. Checks against real quoted rates and recommends gift,
$ npx -y skills add gooseworks-ai/goose-skills --skill work-with-creators-rate-and-deal --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/work-with-creators-rate-and-dealContext preview
The summary Claude sees to decide when to auto-load this skill.
Prices a creator you have already vetted. Gives a low and a target fee from median views and the platform's typical cost per 1,000 views, a walk-away ceiling from your goal and margin, and usage rights priced on their own. Checks against real quoted rates and recommends gift,
name: work-with-creators-rate-and-deal description: >- Prices a creator you have already vetted. Gives a low and a target fee from median views and the platform's typical cost per 1,000 views, a walk-away ceiling from your goal and margin, and usage rights priced on their own. Checks against real quoted rates and recommends gift, paid, affiliate or a mix, with one line showing the math. Use alone when you already have the creator's recent view numbers, your goal and your unit cost; otherwise run work-with-creators. version: 0.1.0
**Reads:** verdicts; goal; budget; product unit cost / margin / AOV and any repeat-purchase data from the brain (or the human's answers); past quoted rates (roster, brain learnings); the creator's public media kit or advertise page if found; `../work-with-creators/references/pricing-and-deals.md`.
**Does, per creator:** 1. Base by role: reach/affiliate = median organic views ÷ 1,000 × the platform's CPM band (sponsored median if it is much lower); UGC-for-ads = per asset, with usage as the core fee; LinkedIn = per-post flat-fee band; newsletter/podcast = their published rate, or a conditional range pending the media kit. 2. Apply modifiers that apply (niche, geography, bundle, rush) → floor / target. 3. Price the rights ask separately: organic repost, paid usage / whitelisting term, exclusivity (UGC-for-ads: the per-asset fee includes 30-day usage; longer terms priced with the modifiers). 4. Walk-away ceiling from the goal (reference §6) — sales: organic first order, plus the rights-amplified value = (target CAC − expected CPA on the asset) × expected conversions (planned media ÷ expected CPA), both assumptions labelled; the two add when the deal buys both the post and the usage; awareness: ~2× the brand's paid-social CPM; content: the brand's cost per tested creative, else "no independent ceiling"; B2B: target cost per demo and contract value (asked, never defaulted; missing → "walk-away: not set" and the smallest test); apps: target cost per install or trial. 5. Real evidence beats benchmark: past quoted rates, the creator's media kit. Above ~1.5× benchmark → flag with reason. 6. Deal structure with the reason (gift-first / paid / affiliate / hybrid / UGC per-asset). Target above walk-away → change the structure or cut. 7. One line of math with every input marked "brand number" or "placeholder".
**Writes:** `price_floor, price_target, walk_away, rights_addon, deal_structure, deal_reason, price_math, real_rate_evidence`.
**Rules:** in the free draft, price from public numbers and bands and mark the walk-away "rough — needs your budget and unit cost" instead of asking first; no unit cost or margin (DTC/CPG gifts) → never assume a number; apps are never asked for unit cost. Dollar figures are the human's deal money — never credits. Never present a single number as "the rate". Prices are recommendations; nothing is offered or agreed.
Put your AI agent on the growth team. Research customers and competitors, analyze what is working, create the next campaign, and learn from the result.
Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the…
Step of the analyze-performance playbook: calls ended tests, scores last week's calls, writes this week's kill/scale/hold calls…
Step of the analyze-performance playbook: flags tracking breaks with fixes and explains each big metric move with evidence,…
Step of the analyze-performance playbook: gathers the week's numbers from tools, exports and pastes, cleans them, and writes the…
Step of the analyze-performance playbook: ranks creative by angle, hook and format with spend gates, writes short per-channel…
Step of the analyze-performance playbook: joins cleaned store or CRM numbers with ad spend to build the business-truth table,…