Skip to content

gooseworks-ai/goose-skills / skills/marketing/make-static-ads

make-static-ads

Verified

Make new static image ads, a fresh batch, more ads, a winner's variations, copy variants or a rejected ad fix. Reads the brand, its customers and the ads it already runs, turns real product facts and customer situations into distinct visual ideas, shows a concept board, writes each render prompt, quotes, renders and reviews through GooseWorks. Also handles requested branded header/social graphics. Use for static ad creation rather than goose-ads. Not for video, product photos or launching campaigns.

skill.meta.json

View on GitHub
{
  "slug": "make-static-ads",
  "category": "playbooks",
  "tier": "playbook",
  "version": "0.10.3",
  "tags": [
    "ads",
    "design"
  ],
  "collections": [
    "brand-growth"
  ],
  "collection_stage": "create",
  "requires_skills": [
    "ad-policy-check",
    "claims-gate",
    "honest-review",
    "make-static-ads-ad-copy",
    "make-static-ads-claims-extract",
    "make-static-ads-compose",
    "make-static-ads-concept-grid",
    "make-static-ads-copy-variants",
    "make-static-ads-find-references",
    "make-static-ads-fix-rejected",
    "make-static-ads-graphic-request",
    "make-static-ads-render-review",
    "marketing-data-access",
    "marketing-guide",
    "run-memory",
    "save-learning",
    "save-to-brain",
    "spend-gate",
    "write-report"
  ],
  "pillar": "6 — Paid media / performance marketing (creative production with pillar 15)",
  "intents": [
    "I need ten fresh ads this week and I have no designer",
    "make me static / image ads for Meta, Instagram, TikTok or LinkedIn",
    "my ads all look the same — I need different concepts",
    "refresh my fatiguing ads",
    "more like my winning ad — new hooks",
    "same image with different text or another font",
    "my image ad got rejected — fix it",
    "the price or stock changed on ads already running",
    "ads for our sale / launch",
    "a header image or social graphic in our brand style"
  ],
  "reads": [
    "brand brain: core rules and facts with their statuses (confirmed / found / guess / unknown) and sources — brand_knowledge_browse, brand_knowledge_search, brand_knowledge_read (server research and the claims-gate sign-off write them)",
    "brand kit, learnings incl. do/dont/must rules, products and competitors — brand_read (server research)",
    "the brand's recent organic posts and what drew replies — brand_read organic (server research)",
    "voice-of-customer bank: research/audience/voc-bank.jsonl / .md — research-audience",
    "angle bank: research/competitors/angle-bank.md (A-NN) — research-competitors",
    "approved campaign record, read as input only: brief (Status: Approved), concepts — plan-campaign (campaign_read)",
    "weekly performance read: reports/performance/<date>.md ('what to make next') — analyze-performance",
    "request lines 'Rotation needed: for make-static-ads' / 'Fix needed: for make-static-ads' in ads/campaigns/<slug>/rotation-requests.md, and the health line of ads/campaigns/<slug>/state.md — run-paid-campaigns",
    "Goose-made creative performance — meta_read performance",
    "own and competitor Meta ads — ads_template_read mine / competitor, imported with ads_library_scrape (server research); category leaders' live Ad Library pages (host browser, or the data proxy on a yes); the template library and community templates",
    "saved inspiration outliers — research-market, research-competitors (social_inspiration_library)",
    "kept product photos — the marketer, or the goose-product-photos skill",
    "graphic request lines 'Graphic needed: for make-static-ads · …' in lifecycle/flows/<flow-slug>.md (email-lifecycle), social/calendar/<start-date>.md (run-organic-social), content/repurposed/<source-slug>/<date>.md and content/drafts/<date>-<slug>.md (make-content)",
    "the brand's own live ads in the Meta Ad Library and in the library of each other platform it advertises on (LinkedIn, TikTok, Google; host browser, or the data proxy on a yes)",
    "run-memory: previous run and open recommendation outcomes at start; missing first run is explicit"
  ],
  "writes": [
    "lower-case creative tags (concept, style, angle, type, level, template, batch, mode, test, offer-ends, claims, judge:*, try:*, superseded, picked) — read by analyze-performance and research-competitors",
    "the human's picks and verdicts: feedback in the human's words (rating happy only on their pick) + 'picked' tag + the batch file — read by run-paid-campaigns and the brand's learned rules",
    "batch file ads/batches/<YYYY-MM-DD>-<slug>.md: the concept board (what was read, level, each row's angle, message and source, visual idea, on-image text, template, protected choice, critic notes), per-ad copy (primary A/B, headline, description, CTA, destination), creative and render ids per ratio, font, palette, logo, the final prompt and image list per ratio, the judge result per try, copy variants, claims and policy lines, special-category flag, picks, cut list, flags — run-paid-campaigns launches from it verbatim",
    "'Rotation ready:' / 'Fix ready:' answers under run-paid-campaigns' request lines — read by run-paid-campaigns on its next run",
    "'Graphic ready:' answer lines under sibling request lines — read by email-lifecycle, run-organic-social, make-content on their next run",
    "brand learnings through the shared save-learning atom, on the human's own words (incl. claims the marketer confirms in chat) — read by every creative playbook",
    "ad-library charges in research/credits-log/<YYYY-MM>.md (spend-gate branch B) — read by every playbook that estimates proxy spend",
    "board.md: the concept board, shown to the marketer with the quotes",
    "profile.md: the brand profile (positioning, angles it uses, how its ads look and read, what it never does), shown with the board",
    "logo-placed versions of each render (media_upload + ads_save with the render as parent) — the version the marketer receives"
  ],
  "needs": {
    "mcp": [
      "gooseworks:get_started",
      "gooseworks:tools_load",
      "gooseworks:card_wait",
      "gooseworks:brand_read",
      "gooseworks:brand_knowledge_browse",
      "gooseworks:brand_knowledge_search",
      "gooseworks:brand_knowledge_read",
      "gooseworks:knowledge_search",
      "gooseworks:file_list",
      "gooseworks:file_read",
      "gooseworks:file_write",
      "gooseworks:campaign_read",
      "gooseworks:meta_read",
      "gooseworks:social_inspiration_library",
      "gooseworks:social_inspiration_search",
      "gooseworks:photos_read",
      "gooseworks:ads_template_read",
      "gooseworks:ads_library_scrape",
      "gooseworks:media_upload",
      "gooseworks:data_call_provider",
      "gooseworks:ads_render",
      "gooseworks:job_get",
      "gooseworks:ads_creative_read",
      "gooseworks:ads_creative_update",
      "gooseworks:automation_upsert",
      "gooseworks:ads_save"
    ]
  }
}
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: 472kUpdated Claude CodeCodexVerifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall