gooseworks-ai/goose-skills / skills/marketing/plan-campaign
plan-campaign
VerifiedCampaign planner: turns a product, offer, goal, budget and date into a plan the marketer can approve and a designer can start from today, with every channel kept or dropped for a reason. Zero paid is a valid answer; it never spends. Use when the ask names a campaign, a launch, drop or season push, a budget or a date: I have this budget and a launch date — what do I run, where?; plan my launch, drop or Black Friday push; plan a campaign; how should I split $5k; plan next month's campaign; our CAC blew up — replan. Not for a broad "grow my brand", "get more customers" or "where do I start" with no campaign, budget or date — use where-to-start; not for pausing ads on a sold-out product — use run-paid-campaigns; not for an email-only send plan — use email-lifecycle; not for reading this week's numbers — use analyze-performance.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.5 KB |
| references/brief-template.md | markdown | 14.9 KB |
| references/budget-and-tests.md | markdown | 7.6 KB |
| references/channel-decision.md | markdown | 11.1 KB |
| references/company-types.md | markdown | 8.1 KB |
| references/intake.md | markdown | 8.4 KB |
| references/launch-and-calendar.md | markdown | 5.2 KB |
| references/replan.md | markdown | 4.2 KB |
| references/run-memory.md | markdown | 11.3 KB |
| references/unit-economics.md | markdown | 10.3 KB |
| skill.meta.json | config | 5.9 KB |
| tests/test-by-hand.md | markdown | 10.5 KB |
skill.meta.json
View on GitHub{
"slug": "plan-campaign",
"category": "playbooks",
"tier": "playbook",
"version": "0.1.4",
"tags": [
"ads",
"brand"
],
"collections": [
"brand-growth"
],
"collection_stage": "research",
"requires_skills": [
"claims-gate",
"marketing-data-access",
"marketing-guide",
"plan-campaign-brief-and-assets",
"plan-campaign-budget-and-tests",
"plan-campaign-channel-decision",
"plan-campaign-goal-chain",
"run-memory",
"save-learning",
"save-to-brain",
"spend-gate",
"write-report"
],
"pillar": "1 — Strategy and planning (also 10 — launches, 18 — promo calendar read)",
"intents": [
"I have this budget and a launch date — what do I run, where?",
"plan a campaign",
"plan my launch / drop / Black Friday push",
"where should I advertise?",
"should we even run ads?",
"how should I split my budget?",
"plan next month / replan the budget",
"we sold out / CAC blew up — what do we change?"
],
"reads": [
"brand brain: summary, kit, products, learnings log, onboarding, competitors (brand_read)",
"claims through the shared claims-gate atom (the sign-off contract: its scoped sign-off, or earlier records by learn-my-brand, unreleased); server scope check for concept proof (knowledge_search claim + product_id)",
"voice-of-customer bank and buyer groups (research/audience/voc-bank.md, buyer-groups.md or brand documents) — research-audience; demand read and market report (research/market/demand.md, <date>-read.md) — research-market",
"angle bank, landscape, competitor files (research/competitors/*.md or documents) and competitor roster (competitor_read) — research-competitors",
"send calendar lifecycle/calendar/<YYYY-MM>.md — email-lifecycle",
"existing campaigns, concepts and pending creative plans (campaign_read, ads_creative_read approvals)",
"weekly and monthly performance reads (reports/performance/) — analyze-performance, replan mode",
"change log (ads/campaigns/<slug>/decisions.md ### dated blocks, incl. the server's Meta outcomes) and fired triggers (state.md) — run-paid-campaigns, replan mode",
"human: goal, budget, date, baseline, margin/ARPA, repeat, stock or capacity, list size, creative capacity, founder hours, tracking state, type-specific items",
"creator roster creators/roster.csv (wave results) — work-with-creators, when a creator leg is Run/Test",
"its own last run record runs/plan-campaign/campaign-plan/<slug>/<date>.md (the plan's bets) — run-memory",
"analyze-performance's run records (runs/analyze-performance/weekly-performance-read/, monthly-read/) and run-paid-campaigns' run records (runs/run-paid-campaigns/weekly-ads-check/<slug>/) — scorecards, money moves, verdicts",
"Brand Brain (brand_knowledge_browse, brand_knowledge_read, brand_knowledge_search where listed): chapters 2, 3, 5, 15, 18, 19, 20 (target_cpa, target_roas, decision.*, experiment.*), 23 (experiment_readout.*, worn_out_angle.*)"
],
"writes": [
"readable campaign plan gooseworks-reports/<brand-slug>/<YYYY-MM-DD>-campaign-plan.md (local file, via write-report) — the marketer",
"brand copy plans/<slug>/<YYYY-MM-DD>-plan-v<N>.md + document 'Campaign plan — <Brand> — <date> v<N>' (save-to-brain, supersede) — the marketer, any host",
"campaign record (campaign_upsert): brief_md with fixed headings — economics box, goal chain, channel decisions, budget split, paid structure, test plan, angles, calendar, asset list, measurement plan, hand-offs, replan triggers; read by run-paid-campaigns, analyze-performance, make-static-ads, make-content, email-lifecycle, run-organic-social, work-with-creators",
"campaign concepts (add_campaign_concept / update_campaign_concept) — read by make-static-ads",
"optional monthly replan schedule (automation_upsert) — only on the human's explicit yes",
"draft brief for an approved live campaign: plans/<slug>/draft-v<N>.md (workspace) until the human's yes",
"run record runs/plan-campaign/campaign-plan/<slug>/<date>.md + brand document (keep-history) — the plan's bets with owner, read date and test — read by its next replan",
"on approval only: kind 20 target_cpa / target_roas, experiment.<slug>-t<n>, decision.<slug>-<yyyy-mm>-<n> via save-learning's fact path — wait for the marketer's yes",
"plans/method/ (copied method for the scheduled worker) — read by the monthly replan automation",
"local mode: the plan in plans/<slug>/ (in place of the campaign record), brand-notes.md and run records under gooseworks-local/<brand-slug>/ — read by its own next replan, run-paid-campaigns and analyze-performance in local mode"
],
"needs": {
"gooseworks": "optional — without it, local mode (the marketing-guide skill, ../marketing-guide/SKILL.md §5): the live site, the marketer's answers and connectors the marketer has (read-only)",
"connectors_optional": [
"ads-platform, store, CRM, billing or product-analytics connector (read-only)"
],
"mcp": [
"gooseworks:get_started",
"gooseworks:brand_read",
"gooseworks:knowledge_search",
"gooseworks:competitor_read",
"gooseworks:campaign_read",
"gooseworks:campaign_upsert",
"gooseworks:add_campaign_concept",
"gooseworks:update_campaign_concept",
"gooseworks:ads_creative_read",
"gooseworks:file_read",
"gooseworks:file_list",
"gooseworks:automation_upsert",
"gooseworks:file_write",
"gooseworks:tools_load",
"gooseworks:account_whoami",
"gooseworks:meta_read",
"gooseworks:social_account_list",
"gooseworks:file_url",
"gooseworks:media_upload",
"gooseworks:knowledge_import",
"gooseworks:job_get",
"gooseworks:brand_knowledge_browse",
"gooseworks:brand_knowledge_read",
"gooseworks:brand_knowledge_search",
"gooseworks:automation_list"
]
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |