1---2name: ad-creative-critic3description: >-4 Checks a set of B2B SaaS ads (static, carousel, video or text) for an early hook, early brand, one clear message,5 proof, message match to the landing page and real variety across the set, where near-duplicate concepts count as6 one. Returns pass, fail or not run per check, severities, fixes ranked by impact, a count of real concepts, and a7 PASS, PASS WITH NOTES, FAIL or BLOCKED verdict. Use it before ads launch or when a set stops performing. Not for8 writing the brief (use creative-brief), for reviewing the landing page itself (use landing-page-critic) or for9 search term waste (use search-terms-triage).10license: MIT11compatibility: >-12 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Reads ad images, scripts and exports;13 reads landing pages if the agent can browse. Python 3 is optional, for counting real concepts.14metadata:15 author: SHAKEUP16 version: "1.0.0"17 stage: check18 plugin: creative-conversion19 homepage: https://www.shakeuphq.com/skills/ad-creative-critic20---21 22# Ad creative critic23 24Checks every ad in a set, then checks the set: how many real ideas it holds once near-copies are merged.25 26## Purpose27 28- One job: check one ad set (one campaign or ad group) per run, ad by ad and as a whole.29- Stage: check. It ends in a verdict with severities.30- It never judges creative from metrics alone, never quotes a benchmark the reader didn't give, and never fixes an ad with a claim the profile doesn't support.31 32## Use when / not33 34| Situation | Use |35| --- | --- |36| Ads are ready to launch | this skill |37| A set's results are falling and you suspect the creative | this skill, with the performance export |38| Several ads look different but you suspect they are one idea | this skill (S1) |39| You need a brief for new ads | `creative-brief` |40| The landing page needs its own review | `landing-page-critic` |41| Copy variants within platform limits | `ad-variants` |42 43## Inputs44 45| Input | Required | Ways to provide, in order | If missing |46| --- | --- | --- | --- |47| The ads: images, video, and their copy (intro text, headline, button) | yes | a connected ad account; an export of the ads with image files; screenshots or pasted copy | ask once; metrics or ad names alone are `BLOCKED` |48| For video: the timing | no | the video if the agent can watch it; a script or storyboard with timestamps; a transcript | judge from order; timing `approximate` |49| The landing page each ad sends to | no | the URL, read in a browser; the first-screen copy pasted; a `creative-brief` handoff | A5 `not run`; coverage `partial`; verdict can't be `PASS` |50| Platform, placement and objective | no | the export; the reader's note | infer from the format; say so |51| Labels per ad: angle, hook type, visual concept, offer | no | the `creative-brief` handoff; the reader's sheet | label them yourself in step 2 and show the labels |52| Performance by ad (impressions, clicks, view rates, frequency) | no | a connected ad account; an export | judge the creative alone; nothing marked `confirmed by data` |53 54## Profile read55 56From `company-profile.md`: `## Company` (brand terms), `### Buying group` (roles and objections), `## Buying moments`, `## Messaging house` (pillars, to label angles), `## Voice` (for rewrites and humour), `## Claims and proof` and `### Never say`, `## Competitors` (mention policy), `## Channels`, and every `## Learnings` entry for `ad-creative-critic` with status `noted`, `fact` or `accepted`.57 58No profile: ask in one message for the brand name, who the ads are for, and the figures the company can use with their sources. Say that `company-profile` saves this next time. Without approved claims, every first-party figure in the ads is `unsourced`.59 60## Steps61 621. **Apply learnings.** A learning that changes a rule (a hook type that never works for this company, a different variety bar) overrides the defaults. Name it when it fires.63 642. **Inventory the set.** One row per ad: id, format, placement, the hook (first line, image headline or first 5 seconds), headline, offer, button, landing page. Label each ad's angle (the pillar or idea), hook type (problem, trigger, outcome, proof, question, contrast, story) and visual concept (comparison, product screen, person to camera, single figure, and so on). Show the labels: S1 depends on them.65 663. **Check each ad.** Run A1 to A9 from `references/checks.md`, using its B2B table for how the attention guidelines apply. Quote the ad for every fail. For video without timestamps, judge from the order of the script and mark timing `approximate`.67 684. **Check the claims (A4).** Run `claim-check` on the copy of every ad. Without it: list each figure, comparison and quote, and match it to `## Claims and proof`; unmatched is `unsourced`, anything on `### Never say` is `forbidden`.69 705. **Check the match (A5).** For each ad, put its promise and offer next to its landing page's first screen. The offer must be the same thing (a tour is not a sales call; a report is not a demo). Ads sharing one page are checked against it once each.71 726. **Count real concepts (S1 to S5).** Run:73 74 ```75 python3 scripts/concept_clusters.py --csv ads.csv76 ```77 78 with columns id, hook, headline, angle, hook_type, visual, format, offer. Without Python: group ads with the same angle, hook type and visual concept; then compare the hook and headline of each pair and join any 2 that differ only by swapped or reordered words. Each group is 1 concept. Required: at least min(3, half the ads rounded up), because 3 is the smallest set where a winner reads as a pattern, and a small set needs half its ads to be different ideas. Say which way you counted.79 807. **Rank and fix.** Order fails by severity, then by how many ads share the fail. For every critical and major, write the fix:81 - Copy fixes: the rewritten line, in the company's voice, from the messaging house, buyer phrases and approved claims only. Run `voice-check` on the rewrites and `claim-check` on any with a figure; fix and recheck, at most 2 rounds; label what still fails. Without those skills: no dashes, nothing from words to avoid, the 3 copy tests, every figure traced to `## Claims and proof`.82 - Variety fixes: name the concepts the set is missing, from pillars and buying moments no ad covers, as briefs for `creative-brief`. Keep the strongest near-copy in each concept and pause the rest (S5), even when S1 passes.83 - Match fixes: change the ad's offer or point the ad at a page that makes that offer.84 858. **Use the data, if given.** Mark a finding `confirmed by data` when the export agrees (the ad that fails A1 has the lowest view-through or click rate in the set). Never raise a severity from an outside benchmark, and never call an ad good on metrics alone.86 87## Check and verdict88 89Per ad: `PASS` (no critical or major), `FAIL` (any critical or major).90 91| Set verdict | Condition (first match wins) |92| --- | --- |93| `BLOCKED` | No creative to look at (only names, ids or metrics), or video with no file, script, storyboard or transcript |94| `FAIL` | Any critical finding; or a major on more than half the ads; or S1 fails |95| `PASS WITH NOTES` | Majors on half the ads or fewer, or minors only; or no fails but A5 was `not run` |96| `PASS` | No fails and every check ran |97 98Named stop: `BLOCKED` asks for the creative. No other stops: missing labels are filled by the skill and shown; a missing landing page leaves A5 `not run`.99 100## Learn101 102Append to `## Learnings` in the profile:103 104- Results come back for a concept (cost per lead, demo rate or pipeline by ad from the reader's ad account and CRM): a `fact` naming the concept, the result and the source.105- The reader rejects a finding ("our buyers respond to the logo-first open"): a `proposal` to change that check for this company, with the reason.106- 2 or more results show a hook type winning or losing for this company: a `proposal` to prefer or avoid it.107 108Example: `- 2026-10-24 | ad-creative-critic | fact | Problem hooks beat question hooks in paid social: 4 opportunities against 0 | Why: the ad account export and CRM deals, Q3 2026 | Status: noted`109 110## Output111 112```113Verdict: <PASS | PASS WITH NOTES | FAIL | BLOCKED> · Coverage: <complete | partial (what's missing)>114Ads: <n> · Real concepts: <n> of <n> required · Formats: <list> · Counting: <script | by hand> · Learnings applied: <list or none>115 116Set117| Check | Result | Evidence | Fix |118(S1 to S5; S1 lists each concept and the ads in it)119 120Per ad121| Ad | Verdict | Fails (id, severity) | Evidence (quoted) | Fix |122 123Top fixes, in order:1241. <fix> | ads: <ids> | why first: <severity, ads affected>125...126 127Concepts to brief next: <angles or buying moments no ad covers>128Rewrites checked: voice-check <verdict>, claim-check <verdict> (<or: inline>)129Not run: <checks and why>130```131 132Then the handoff block.133 134## Hand off135 136```handoff137skill: ad-creative-critic138version: 1.0.0139verdict: FAIL140coverage: partial (no landing page for 2 ads)141for: <campaign or ad set>142outputs:143 ads: 6144 real_concepts: 2145 required_concepts: 3146 critical: 1147 failing_ads: [<id>, <id>]148 concepts_to_brief: [<angle or moment>]149next: [creative-brief, landing-page-critic]150open: [landing pages for <ids>]151```152 153`creative-brief` reads `concepts_to_brief`. When A5 fails because the page is wrong, `landing-page-critic` reviews that page.154 155## Failure modes156 157| Problem | Do this |158| --- | --- |159| Only metrics and ad names | `BLOCKED`: creative can't be judged from its results; ask for the images or copy |160| Labels from the reader disagree with what the ads show | Use what the ads show; list each relabel so S1 can be checked |161| One ad in many sizes | 1 ad: check it once, note the sizes under A7 |162| Dynamic or AI-assembled ads (the platform mixes headlines and images) | Check each asset and the riskiest combination: a headline whose claim needs proof paired with an image without it |163| A competitor named in an ad | Check `## Competitors` mention policy; outside the policy is `forbidden` under A4 |164| The set is for a retargeting audience that already knows the brand | A2 can be `minor`; say so; the rest stands |165 166## Influenced by167 168- Google's ABCD guidelines for YouTube ads (Attract, Brand, Connect, Direct), built on consumer video, used here with the B2B changes in `references/checks.md`: https://www.thinkwithgoogle.com/_qs/documents/8472/ABCD_Complete_V7b_HR_1.pdf169- Meta Blueprint's course on diversified creative, which splits variety into concept, motivator and format: https://www.facebookblueprint.com/student/path/253130170- Harry Dry's 3 copy tests, used in A1 and the rewrites: https://www.demandcurve.com/newsletters/growth-newsletter-202171- What we changed: near-duplicates are counted as one by a rule anyone can check, the set needs a minimum of real concepts, consumer urgency tactics are dropped, and every ad is matched to its landing page's first screen.