gooseworks-ai/goose-skills / skills/marketing/where-to-start
where-to-start
VerifiedFirst-move advice for a broad growth or marketing ask with no job named: looks at what GooseWorks already knows and at the site, asks a few short questions in one message, names the one thing in the way, and sends the marketer to the right next job. Use when the marketer says "help me grow my brand", "I need to grow my business", "how do I get more customers / sales", "help me with marketing", "where do I start", "sales are flat", "what should I focus on this month", or "I'm back, what's next?". Recommends only; never runs the work. Not for a named job like "make me ads" or "grow my Instagram" (go straight to it); not for a campaign with a launch, budget or date — use plan-campaign; not for why this week's numbers moved — use analyze-performance.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.4 KB |
| references/base-rates.md | markdown | 5.1 KB |
| references/output-shape.md | markdown | 7.0 KB |
| references/playbook-map.md | markdown | 19.8 KB |
| references/questions.md | markdown | 5.1 KB |
| references/situation-lens.md | markdown | 9.7 KB |
| skill.meta.json | config | 3.2 KB |
| tests/test-by-hand.md | markdown | 9.9 KB |
references/output-shape.md
View on GitHub# The first-move recommendation: shape and examples
Load at step 5. Every recommendation has the same parts, in this order, and fits on one screen (at most 250 words).
1. **The read** — two sentences on the situation, citing at least two facts the founder gave.
2. **The constraint** — one sentence naming the one thing in the way, and the evidence that points there.
3. **First move** — one move (two only if the first feeds the second, or one is a quick fix alongside), named by what it does (the map's "Say it as"), never by its internal name, each with: why now, what it produces. If the real first move is a step the founder takes themselves (not covered by any job here), it comes first, said as "You, this week:", with at most one playbook that helps alongside. A small human step can also sit beside a playbook pick, labelled "You, this week:" — never internal labels such as "off the map" or version numbers.
4. **Bring** — what the founder needs to have to run it, including signing off what they may claim (learning the brand) when the move writes copy and no sign-off exists, and the founder's time.
5. **Not yet** — what they might expect to do and shouldn't yet, each with the reason and when it becomes a yes. Include every channel or idea the founder raised that you are not recommending.
6. **Worked if** — an outcome the founder can see in their own numbers (customers, replies, sign-ups who come back, orders), with a number and a date. Finishing a task ("list pulled, account connected") is never a "worked if".
7. **Come back when** — the trigger for the next check-in.
8. **Hand-off offer** — one line, in plain words: "When you're ready, ask me for your welcome emails." This playbook never starts the next job; their own request does. If the first move is only a human step, say instead when to come back and for which job. Never say the answers are saved in the recommendation: the save happens after they agree, and you say so only once it has come back.
Commit. No hedging both ways, no menu of "you could also…", no essays.
If you found earlier work saved on the brand (a campaign plan, research), the read says in one clause whether the founder confirmed it still stands. An unconfirmed plan is never the basis of the first move, and its blockers are not the constraint.
The examples below show the target quality, for a spread of company types and constraints. They illustrate the reasoning, not answers to copy. A different company gets a different answer, and the founder's own assets, dates and limits always beat any pattern here. Never carry a tool, platform, number or asset from an example into a real answer; use only what the founder or the brain gave you.
---
## Example (a): two physiotherapy clinics, owner-run, "we need more patients", $1,500/month, no marketing help
**The read.** Both clinics fill up from doctor referrals and walk-ins, but new-patient bookings are down since a chain opened nearby. Your Google listings show 31 reviews between them, against the chain's 400.
**The constraint.** Demand you're losing at the moment of search — people nearby who look for "physio near me" find the chain first.
**First move.**
- **Getting found when people search**: checks how both clinics show up in local search and AI answers for the questions patients ask, and gives five fixes you can apply this week (listing details, services, photos, a page per clinic).
**Bring.** Admin access to both Google Business Profiles, your services and prices, an hour this week.
**Not yet.** Paid search (fix the listings first, or you pay to send people to a weak profile). Social posting. A new website.
**You, this week:** ask every patient finishing treatment this month for a Google review, with the link on a card at the desk.
**Worked if.** 30 new reviews and more calls from the listings within six weeks.
**Come back when** the fixes are live and a month of calls is in.
---
## Example (b): tutoring marketplace, 400 parents on the waitlist, 25 tutors, "growth has stalled"
**The read.** Parents keep signing up but wait three weeks for a maths tutor; 60% of the waitlist wants secondary-school maths. Demand is fine; supply is the gap.
**The constraint.** Supply — not enough maths tutors.
**First move.**
- **You, this week:** ask your 25 tutors for introductions, with a referral reward when a new tutor completes ten sessions.
- **A list of tutoring businesses to contact**, alongside: tutoring businesses and independent tutors who advertise near your two busiest areas, each with a sourced contact route and why they fit; you check the addresses and send the invitations yourself.
**Bring.** What makes a good tutor for you, your tutor pay rate, your own email tool, three hours a week for interviews.
**Not yet.** Any parent-side marketing (it lengthens the wait and creates refunds). Ads. A referral scheme for parents.
**Worked if.** 10 new maths tutors onboarded in a month and the waitlist under a week.
**Come back when** the wait is under a week; then parent demand is worth buying.
---
## Example (c): coffee subscription, 1,800 subscribers, cancellations up, the founder wants TikTok ads
**The read.** New subscribers are steady, but about one in five cancels after the second bag, and nobody hears from you between deliveries. More traffic would pour into the same leak.
**The constraint.** Retention — the first 60 days.
**First move.**
- **Your automatic emails**: a welcome series, a "how's your second bag?" check-in with a brew guide, a skip-or-swap option before cancellation, and a win-back flow, written to load straight into your email tool.
**Bring.** Your email tool and the flows already running, the offers you're willing to make, the claims you may use about sourcing (first, about 20–30 minutes to sign off what you may claim, if that isn't done).
**Not yet.** TikTok ads (until second-bag cancellations fall). New products. A rebrand.
**Worked if.** Second-bag cancellations drop from about one in five to about one in eight within two months.
**Come back when** a full month of new subscribers has passed through the flows.
---
## Example (d), a step the founder takes: services firm (two-person B2B consultancy), no budget, "help me with marketing"
**The read.** Your last eight clients all came from referrals and you have no pipeline for next quarter. You have ten happy past clients and a founder who writes well.
**The constraint.** Demand — and your strongest channel, referrals, has no playbook here.
**First move.**
- **You, this week:** email your ten past clients, ask each for one introduction, and ask two of them for a short quote you may use.
- **First drafts of your content**, alongside: turns one recent project into a case study and three LinkedIn posts in your voice (claims and client names only with their permission).
**Bring.** The project write-up or a call transcript, the client's written OK to be named, two hours a week.
**Not yet.** Ads. SEO. A new website.
**Worked if.** Three introductions and one new conversation within a month.
**Come back when** the introductions have turned into calls, or haven't.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |