gooseworks-ai/goose-skills / skills/shared/launch-meta-ad-campaign
launch-meta-ad-campaign
VerifiedTake someone from a business goal to a verified, paused-then-live Meta/Facebook/Instagram campaign without making them learn Meta's hierarchy. Use automatically for requests to launch, run, create, publish, set up, or plan Meta ads; use reporting skills for analysis-only requests.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 22.2 KB |
| agents/openai.yaml | config | 255 B |
| references/direct-meta-adapter.md | markdown | 4.4 KB |
| references/gooseworks-adapter.md | markdown | 4.1 KB |
| references/planning-only.md | markdown | 2.7 KB |
| skill.meta.json | config | 961 B |
| tools/meta_marketing_api.js | script | 38.2 KB |
references/planning-only.md
View on GitHub# Planning-only fallback
## Summary
When no safe write adapter is available, still deliver a complete Meta campaign plan. State that nothing was created and identify the exact access needed for a later launch. Do not delete or weaken campaign architecture, audience, copy, budget, tracking, and monitoring guidance just because publishing is unavailable.
## Intake and recommendation
Collect the product/offer and URL, desired business result, Meta objective, budget and duration, geography, audience/ICP, funnel stage, landing page, tracking status, existing creative, competitors, B2B/B2C context, and any special-ad-category implications.
Recommend the objective and explain tradeoffs. Distinguish awareness, traffic, lead generation, sales/conversions, engagement, and app promotion. If the expected conversion volume cannot support optimization, recommend consolidation or an earlier measurable event rather than pretending the learning phase will succeed.
## Plan contents
Produce a skimmable campaign brief containing:
1. **Campaign overview:** objective, budget, dates/timezone, geography, placements, conversion event, tracking assumptions, and success metrics.
2. **Architecture:** campaign → ad sets → ads tree. Separate prospecting, lookalike, and retargeting only when the budget and available first-party data justify them.
3. **Audience strategy:** demographics, broad/interest/custom/lookalike inputs, exclusions, estimated rationale, and data prerequisites. Do not invent available Meta targeting attributes.
4. **Creative and copy matrix:** angle, format/placement, hook, primary text, headline, description, CTA, destination, and the variable each ad tests.
5. **Budget and bidding:** allocation by ad set, budget type, starting strategy, learning-phase constraints, and conditions for changing bids.
6. **Destination and policy review:** rendered-page result, message/claim match, CTA, redirects, tracking, warnings, blocked claims, and special-category handling.
7. **Tracking checklist:** Pixel/Conversions API, events, UTMs, attribution assumptions, custom audiences, and a test-conversion step.
8. **Launch checklist:** exact Ads Manager fields and a requirement to create everything paused for review.
9. **Monitoring plan:** delivery checks in days 1–3, early signal review in days 4–7, conversion-quality review after sufficient data, and explicit stop/scale rules.
## Handoff
Save the brief to `meta-campaign-plan-YYYY-MM-DD.md` when the environment supports files, or provide it inline. End with:
- **Created in Meta:** No
- **Why:** no approved write adapter was available
- **Next access needed:** either GooseWorks launch tools or a Meta token with `ads_management`, the ad-account ID, and Page access
- **Safety:** no write or activation was attempted
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |