gooseworks-ai/goose-skills / skills/shared/ads-north-star-strategy
ads-north-star-strategy
UnverifiedTurn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 19.5 KB |
| agents/openai.yaml | config | 250 B |
| references/direct-meta-adapter.md | markdown | 2.1 KB |
| references/gooseworks-adapter.md | markdown | 6.4 KB |
| references/planning-only.md | markdown | 1.3 KB |
| skill.meta.json | config | 885 B |
references/direct-meta-adapter.md
View on GitHub# Direct Meta adapter
## Summary
Use this mode when there is no GooseWorks, but a Meta Marketing API token (with at least
`ads_read`) and the ad account id are available. Account facts are read from the Graph API; the
strategy goes to a local `ads/` folder.
## Launch capability (what the host can launch)
The direct writer bundled with `launch-meta-ad-campaign` creates **Traffic** campaigns only: one
campaign, one ad set, created paused. So decision rule 1's bridge applies exactly as for
GooseWorks. If the user will build the campaign themselves in Ads Manager instead, every objective
is available: write the right objective and skip the bridge.
## Files and the brief
- A local `ads/` folder, ids `local` (see the `meta-ad-manager` skill's direct adapter).
- There is no campaign record: the brief's facts are in the `strategy.md` v1 stub that intake
wrote (goal, offer, destination, audience, budget, success number). Keep them when you write the
full strategy.
## Account facts (decision rule 2)
Read them with Graph API GET calls on the ad account, never from memory:
| Fact | Read |
|---|---|
| Is the account cold? | lifetime spend: the account's `insights` with `date_preset=maximum`, field `spend`, in the account `currency`. (The account's `amount_spent` resets with its spend cap, so it is not always lifetime) |
| Is the account usable? | the ad account's `account_status` (1 = active) |
| Is tracking present? | the account's `adspixels`, with `last_fired_time` |
| Weekly volume of the target event | the account's `insights` for the last 7 complete days, `actions` for that event |
| Existing customers to exclude | the account's `customaudiences` (a customer list, by name) |
Write each result as an `- Observed:` line with its window, the read time as the sync time, and
`source meta:<account id>`.
## The hand-off
There is no generation service. Write one concept per angle (person, message, proof) into the
strategy's Creative plan, and hand the user a creative brief for the ads that will run. If the
user has their own generator, the 3x rule still applies to what they generate.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |