Update to Adspirer

{
  "description": "Write and refresh ad creative with Adspirer — headlines, descriptions, primary text, and ad copy for Google, Meta, TikTok, LinkedIn, and Amazon, plus diagnosing and fixing creative fatigue when CTR falls and frequency rises. Respects each platform's character limits.",
  "included_files": [],
  "name": "adspirer-creative",
  "skill_md_contents": "---\nname: adspirer-creative\ndescription: Write and refresh ad creative with Adspirer — headlines, descriptions, primary text, and ad copy for Google, Meta, TikTok, LinkedIn, and Amazon, plus diagnosing and fixing creative fatigue when CTR falls and frequency rises. Respects each platform's character limits.\n---\n\n# Ad creative\n\nFollow `adspirer-mcp` before any tool call. Load the platform skill for its exact limits.\n\n## Write from evidence, not imagination\n\nBefore writing a single headline, look at what already works:\n\n- `analyze_search_terms` (Google) or `get_amazon_search_terms` — the actual words people typed to\n  find this business. Those words belong in the copy.\n- `get_ad_performance` / `get_meta_ad_performance` — which existing ad has the best CTR, and why.\n- The landing page. Copy that promises something the page doesn't deliver converts once and never\n  again.\n\nAsk what makes this business different if it isn't obvious. Generic ad copy is a choice, not a fate.\n\n## Character limits\n\n| Platform | Field | Limit |\n|---|---|---|\n| Google Search | Headline | 30 |\n| | Description | 90 |\n| | Long headline (PMax) | 90 |\n| Meta | Headline | 255 (~40 visible) |\n| | Primary text | 2200 (~125 visible) |\n| | Description | 255 (~30 visible) |\n| Meta carousel | Card headline | ~40 |\n| LinkedIn | Headline | 70 |\n| | Introductory text | 600 (~150 visible) |\n| TikTok | Ad text | 100 |\n| Amazon SB | Headline | 50 |\n\nWhere the hard limit and the visible limit differ, **write to the visible one.** Meta's 2200-character\nprimary text truncates at about 125; anything after that is read by nobody.\n\n## What good looks like\n\n- **Lead with the offer or the outcome**, not the company name. Nobody searched for your brand.\n- **One idea per headline.** Google rotates them independently; a headline that only makes sense\n  next to another headline will appear alone.\n- **Specifics beat adjectives.** \"Same-day callout, no fee\" beats \"Fast, reliable service.\"\n- **Match the search intent.** Someone searching \"emergency plumber near me\" wants availability and\n  a phone number, not your 30-year heritage.\n- **Give Google variety.** Fifteen headlines that all say the same thing give the system nothing to\n  test. Vary the angle: price, speed, proof, risk reversal, outcome.\n\nWrite more than you need and cut. Then check every claim is one the business can actually make —\n\"#1 in the UK\" is a legal problem, not a headline.\n\n## Refreshing fatigued creative\n\nRising frequency plus falling CTR is fatigue. The same people keep seeing the same ad. **No bid or\nbudget change fixes it** — a fatigued ad set with more budget just annoys the same people faster.\n\nDiagnose: `detect_meta_creative_fatigue`, `detect_tiktok_creative_fatigue`,\n`analyze_linkedin_creative_performance`. On Meta, a 7-day frequency above ~3 with declining CTR is\nthe signal.\n\nFix, in order of leverage:\n\n1. **New creative concept** — a different hook, not the same image recoloured.\n2. **New format** — video where there was static, carousel where there was a single image.\n3. **Broaden or rotate the audience** — fatigue is partly an audience-size problem.\n4. Only then touch budgets.\n\nChange one variable at a time. Swapping the image *and* the copy *and* the audience teaches you\nnothing about which one mattered.\n\n## Show the variants together\n\nCopy is judged by comparison. Fifteen headlines in a bulleted list all read the same; the same\nfifteen laid out as cards, grouped by angle, with character counts and the truncation point marked,\nare a decision the user can actually make.\n\n\nFor a set the user will circulate for approval, offer a **Site** — invitation-only, since it carries\ntheir unreleased campaign copy. For a quick pick, a table in the conversation is faster than a\ndeployment.\n\nEither way, render each variant against its platform's **visible** limit, not the hard one. A Meta\nprimary text that looks fine at 2,200 characters is worthless if the offer sits past 125.\n\n## Applying it\n\nUpdate in place with `update_ad_headlines`, `update_ad_descriptions`, or `update_ad_content` on\nGoogle; the platform's ad-update tools elsewhere. Keep the winning ad running while the new one\ngathers data — pausing the control before the challenger has proven itself is how accounts go\nbackwards.\n\nAds may need review before serving. Say so, rather than letting the user think it's live.\n\nCreative fatigue is a recurring problem, not a one-time fix. Rather than promising to check back,\noffer to schedule a fatigue check on this host — frequency and CTR, every couple of weeks — so the\nnext refresh is prompted by the data instead of by someone remembering.\n"
}