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…
Step of the make-static-ads playbook: writes the copy the platform shows around each image — two primary texts, headline, description, CTA, destination — and the hook and angle direction that goes into the ad's Variant brief, in the brand's voice and the customers' own words,
$ npx -y skills add gooseworks-ai/goose-skills --skill make-static-ads-ad-copy --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/make-static-ads-ad-copyContext preview
The summary Claude sees to decide when to auto-load this skill.
Step of the make-static-ads playbook: writes the copy the platform shows around each image — two primary texts, headline, description, CTA, destination — and the hook and angle direction that goes into the ad's Variant brief, in the brand's voice and the customers' own words,
name: make-static-ads-ad-copy description: >- Step of the make-static-ads playbook: writes the copy the platform shows around each image — two primary texts, headline, description, CTA, destination — and the hook and angle direction that goes into the ad's Variant brief, in the brand's voice and the customers' own words, within what the brand brain allows. The on-image words are written by the composer, not here. Run make-static-ads instead; not for direct use. version: 0.4.2
**Reads:** the concept grid (concept-grid), brand voice, banned words and tone from `gooseworks:brand_read` `kit` and the `do`/`dont` voice rules, the voice-of-customer bank (`../make-static-ads/references/reading-the-brain.md` §2), the brain facts with their statuses (§1), `../make-static-ads/references/angles-and-hooks.md` §5–6, `../make-static-ads/references/formats-and-placements.md` §4. **Writes:** a copy row per ad.
1. **Mine the customer words** for this angle from the bank's rows (cite row ids): pain phrases, desired outcome in their words, objections, switching stories. Keep their syntax. Customer words may supply the *pain*; the *benefit* must be a usable fact (`../make-static-ads/references/claims-and-policy.md` §2). 2. **Hook direction for the Variant brief.** Write 3–5 hook candidates per ad from different hook formulas (`angles-and-hooks.md` §5); keep the strongest as the ad's hook direction and rank the rest as spares. The direction goes into the ad's Variant brief message (the `make-static-ads-compose` skill (`../make-static-ads-compose/SKILL.md`)); the composer writes the final on-image words from it. A real review or founder line meant to appear verbatim is passed as a quote with its source — a borrowed phrase must not pose as a quote. 3. **Primary text × 2:** short (hook + the concept's proof + CTA, inside ~125 characters) and longer (story or objection handling). The hook leads both. After compose, check neither repeats the on-image words word for word. 4. **Headline** (benefit or offer, not the brand name), **description** (offer terms, shipping — only if true), **CTA** matched to awareness, **destination** (the page that keeps the ad's promise). 5. **Voice pass:** read it against the kit's do/don't lines and banned words. Read it aloud: does it sound like the brand, and like a person? 6. **Policy-safe phrasing from the start:** no "you/your" + condition; third person or situation framing instead ("for skin that feels tight by noon").
Output per ad: hook direction, spare hooks (ranked — copy-variants uses them), primary text A/B, headline, description, CTA, destination, hook source (evidence id or "brand-written"), the brain facts used with their status.
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,…