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 where-to-start playbook: saves the founder's answers and the agreed first move with the brand, so later visits and other playbooks don't ask again. Run where-to-start instead; not for direct use.
$ npx -y skills add gooseworks-ai/goose-skills --skill where-to-start-situation-save --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/where-to-start-situation-saveContext preview
The summary Claude sees to decide when to auto-load this skill.
Step of the where-to-start playbook: saves the founder's answers and the agreed first move with the brand, so later visits and other playbooks don't ask again. Run where-to-start instead; not for direct use.
name: where-to-start-situation-save description: >- Step of the where-to-start playbook: saves the founder's answers and the agreed first move with the brand, so later visits and other playbooks don't ask again. Run where-to-start instead; not for direct use. version: 0.1.0
The founder's answers (their words), the brand (id, slug, `coworker_agent_id`) unless there is no real brand, what the short look at the site showed, the constraint you named, the recommendation and whether they agreed, and today's date.
No real brand (none, or an empty placeholder): save nothing, and say so plainly ("I can't save these yet — there's no brand set up"). If a brand is set up later in this same conversation, run this atom then, before anything else asks the founder again.
1. **The situation file.** `gooseworks:file_read` `brand/situation.md` (brand coworker scope; no coworker → default workspace under `brands/<brand-slug>/`, and say so once). Replace the "Latest" section; move the previous "Latest" under "History" (keep the last three). Format:
# Situation — <Brand> Do this first, because: <the constraint in one clause> → <the agreed first move>. ## Latest — <YYYY-MM-DD> Founder said [owner, <date>]: sells <…> to <…>; where it sells <…>; stage <…>; goal <…> by <date>; can put in <…>/month and <…> h/week; does the work: <…>; next big date <…>; tried <…>; has <list / audience / network…>. Seen on the site [site, read <date>]: <offer, price, first reason to buy, list sign-up>. Unknown: <what they didn't know>. Agent's read [guess, <date>]: constraint <…>; first move <…> (<agreed | adjusted to … | not agreed>); not yet <…>; worked if <…>; come back when <…>. ## History <earlier "Latest" sections, newest first, at most three>
Keep the founder's words, what the site showed and your read on separate lines. Never put a guess on the "Founder said" line. No plan names or credit sums. 2. **Save it** through the `save-to-brain` skill (`../save-to-brain/SKILL.md`): path `brand/situation.md`, artifact `Situation`, title `Situation — <Brand> — <YYYY-MM-DD>`, tags `[where-to-start, situation]`, `versioned: supersede`. 3. **Profile fields** (only those the founder stated, only clear matches to the listed values): `gooseworks:brand_update` with `brand_id`, `knowledge_intent: "user_correction"`, `user_statement` = the founder's words that gave them, and `patch.onboarding`: `role`; `ad_spend` only if they said what they spend on ads today (question 4 asks what they *can* put in, which is not the same); `goals` and `platforms` only where a listed value plainly matches. 4. **Check the answers.** If a write failed, say in one line that it wasn't saved, and carry on.
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,…