1---2name: landing-page-critic3description: >-4 Reviews one B2B SaaS page for message match, clarity, proof and friction, with pass, fail or not run per check,5 severities weighted by the page type (homepage, pricing, comparison, campaign landing page, feature), fixes6 ranked by impact with rewritten lines, and a PASS, PASS WITH NOTES, FAIL or BLOCKED verdict. Use it before a page7 goes live, when a page converts poorly, or to tear down a competitor's page. Not for a full funnel diagnosis with8 analytics (use conversion-research), for checking ads (use ad-creative-critic) or for tone alone (use9 voice-check).10license: MIT11compatibility: >-12 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Reads the live page and takes13 screenshots if the agent can browse; otherwise works from screenshots or pasted copy and names the checks it14 couldn't run.15metadata:16 author: SHAKEUP17 version: "2.0.0"18 stage: check19 plugin: creative-conversion20 homepage: https://www.shakeuphq.com/skills/landing-page-critic21---22 23# Landing page critic24 25Checks a page the way its buyer meets it, straight from the ad or the search, and ranks what to fix first.26 27## Purpose28 29- One job: run a fixed set of checks on one page and rank the failures by impact.30- Stage: check. It ends in a verdict with severities.31- It judges against the page's buyer, its traffic source and its goal, never against taste. It never marks a check it couldn't run as a pass, and never fixes copy by adding a claim the profile doesn't support.32 33## Use when / not34 35| Situation | Use |36| --- | --- |37| A page is about to go live, or was just rebuilt | this skill |38| A page converts poorly and you want the likely causes on the page | this skill, then `conversion-research` if the cause isn't on the page |39| Tearing down a competitor's page | this skill (P4 is `not run`: their sources aren't visible) |40| Diagnosing a whole funnel with analytics and device data | `conversion-research` (it runs this skill as its heuristic pass) |41| Checking ads before they run | `ad-creative-critic` |42| Only the wording and tone | `voice-check` |43| Testing whether buyers understand the message | `message-test` |44 45## Inputs46 47| Input | Required | Ways to provide, in order | If missing |48| --- | --- | --- | --- |49| The page | yes | the live URL, read in a browser at desktop and phone width; screenshots the reader uploads (first screen on desktop and phone, then the full page); the copy pasted in order, with button labels and form fields | ask once; with nothing readable, `BLOCKED` |50| The traffic source | no (yes for a campaign page) | the ad (headline, text, image, offer), the search terms or the email that sends people here; one per main source | M checks are `not run`; on a campaign page coverage is `partial` and the verdict can't be `PASS` |51| The page's goal | yes | the reader's note; inferred from the primary button and confirmed | ask once; if no answer, infer and say so |52| Buyer phrases | no | a `message-mining` handoff; buyer quotes the reader pastes | use `### Buying group` objections only |53| Analytics for the page | no | a connected analytics tool; an export (conversion rate by device, form starts against submits, scroll depth) | judge from the page alone; nothing marked `confirmed by data` |54 55What each form of the page allows:56 57| You have | Not run |58| --- | --- |59| Live page or desktop and phone screenshots | nothing |60| Desktop screenshot only | F5 |61| Pasted copy only | C7, C9, M4, F5, F6, F7 |62 63## Profile read64 65From `company-profile.md`: `## Company` (category, business model), `## Buyers` and `### Buying group` (who the page is for and each role's objection), `## Positioning` and `## Messaging house` (what the page should say), `## Voice` (for rewrites), `## Claims and proof` and `### Never say` (P4), `## Competitors` (mention policy, for comparison pages), and every `## Learnings` entry for `landing-page-critic` with status `noted`, `fact` or `accepted`.66 67No profile: ask in one message who the page is for, what the product does, and which figures on the page the company can source. Say that `company-profile` saves this next time. Without claims, every first-party number on the page is `unsourced` in P4.68 69## Steps70 711. **Apply learnings.** An accepted learning that changes a weight or a severity overrides the defaults here. Name it when it fires.72 732. **Record what you can see.** Note which forms of the page you have (table above) and list the checks that are `not run` and why before you start.74 753. **Set the page type, the goal and the weights.** Page type, first match wins:76 77 | Signal | Page type |78 | --- | --- |79 | Built for a campaign: the reader says an ad or email sends traffic here, or a campaign URL (such as /lp/) with one goal. A full site menu on it is an F3 fail, not a different type | campaign landing page |80 | The URL or H1 says vs, alternative or compare | comparison |81 | Plans with prices, or a /pricing URL | pricing |82 | The domain root | homepage |83 | One capability, a /product or /features URL | feature |84 85 Area weights by page type:86 87 | Page type | Match | Clarity | Proof | Friction | Its own checks | Why |88 | --- | --- | --- | --- | --- | --- | --- |89 | Campaign landing page | 3 | 2 | 2 | 3 | none (M, F2, F3 carry it) | Each visit was paid for, so a broken promise or a hard next step wastes the click |90 | Homepage | 1 | 3 | 2 | 1 | H, weight 3 | Visitors arrive from everywhere; the page must make the category and the path clear |91 | Pricing | 1 | 3 | 2 | 3 | PR, weight 3 | Buyers come to check fit and cost; unclear plans and hard steps lose them at the last step |92 | Comparison | 2 | 2 | 3 | 1 | CP, weight 3 | Readers are skeptical and comparing; proof and fairness decide it |93 | Feature | 2 | 3 | 2 | 1 | FE, weight 2 | One capability must be clear and tied to a result |94 95 Findability checks (T) run only on pages meant for search or AI answers, at weight 1.96 974. **Read the first screen only.** Before scrolling, write the 5-second read as a stranger would: who it's for, what it does, what they get, what to do next (C1). Then run M1 to M4 against each traffic source. Most visitors decide here, so these findings come first in a tie.98 995. **Run the rest of the checks.** Work through `references/checks.md` for every area and the page type's own group. Record pass, fail or not run for each, and quote the page for every fail. Use buyer phrases from `message-mining` to judge C2 and P5: a headline in the company's words when buyers use different ones fails C2's "could no one else say it" more often.100 1016. **Check the claims (P4).** Run `claim-check` on the page copy. Without it: list every number, comparison and quote, and match each to `## Claims and proof`; anything unmatched is `unsourced`, anything on `### Never say` is `forbidden`. Prices, plan limits and product facts on the company's own page are its offer, not claims; results, customer counts, ratings and comparisons are claims.102 1037. **Rank by impact.** Score each fail: severity points (critical 10, major 3, minor 1) times the area weight. The gap between 10 and 3 makes a critical outrank any major on any page type. Ties: first screen first, then the cheaper fix (a copy change before a layout change before a rebuild). If analytics back a finding (the phone conversion rate is far below desktop on a page that fails F5), mark it `confirmed by data`; never raise a severity from someone else's benchmark.104 1058. **Write the fixes.** For every critical and major: the change, and for copy, the rewritten line in the company's voice. Build rewrites from the source's promise, buyer phrases and `## Claims and proof` only. Recommend a new section only to fix a failed check (an objection with no answer); page length alone is not a finding. Then run `voice-check` on the rewrites and `claim-check` on any rewrite with a number or a comparison. Without those skills: no dashes, nothing from `### Words to avoid`, the 3 copy tests, and every number traced to `## Claims and proof`. Fix what fails and recheck, at most 2 rounds; label any rewrite still failing.106 107## Check and verdict108 109| Verdict | Condition (first match wins) |110| --- | --- |111| `BLOCKED` | Nothing of the page could be read (no live page, screenshot or copy), or the first screen is missing |112| `FAIL` | 1 or more critical findings, or 3 or more majors (each loses some buyers, and they add up along the page) |113| `PASS WITH NOTES` | Fewer than 3 majors, or minors only; or no fails but a weight-3 area for this page type was `not run` |114| `PASS` | No fails, and every check in the weight-3 areas ran |115 116Named stop: `BLOCKED` asks for screenshots or the pasted copy. No other stops: an unknown goal is inferred from the primary button and stated; an unknown page type is inferred and stated.117 118## Learn119 120Append to `## Learnings` in the profile:121 122- The reader rejects a finding ("our buyers expect a long form, sales needs these fields"): a `proposal` to change that check's severity for this company, with their reason.123- A fix ships and a result comes back (conversion rate before and after from the reader's analytics, or a test result): a `fact` with both rates, the dates and the source.124- 2 or more results point the same way (every proof fix on comparison pages lifted demos): a `proposal` to change that area's weight for this company.125 126Example: `- 2026-10-24 | landing-page-critic | fact | Moving the customer quote beside the demo form lifted form completion from 2.1% to 2.9% | Why: GA4, demo page, Aug against Sep 2026 | Status: noted`127 128## Output129 130```131Verdict: <PASS | PASS WITH NOTES | FAIL | BLOCKED> · Coverage: <complete | partial (what's missing) | blocked>132Page type: <type> (<given | inferred from ...>) · Goal: <action> · Traffic source: <source or not given>133Seen: <live page | desktop screenshot | phone screenshot | copy> · Not run: <ids and why>134Counts: <n> critical, <n> major, <n> minor · Learnings applied: <list or none>135 1365-second read: For: <...> | Does: <...> | Get: <...> | Next: <...> (<n> of 4)137 138| Rank | Check | Area | Result | Severity | Evidence (quoted) | Fix |139(fails ranked by impact, then passes, then not run)140 141Top 3 fixes, in order:1421. <change> | Rewrite: "<line>" | First because: <severity x weight, first screen>1432. ...1443. ...145 146Keep: <up to 3 things that work, quoted, so a rewrite doesn't lose them>147Rewrites checked: voice-check <verdict>, claim-check <verdict> (<or: checked inline>)148```149 150Then the handoff block.151 152## Hand off153 154```handoff155skill: landing-page-critic156version: 2.0.0157verdict: FAIL158coverage: partial (no phone screenshot)159for: <page URL or name>160outputs:161 page_type: campaign landing page162 critical: 2163 major: 3164 top_fix: <one line>165 failed: [M2, C5, F1]166 not_run: [F5]167next: [conversion-research, message-test]168open: [phone screenshot for F5]169```170 171`conversion-research` reads `failed` as its heuristic pass for this page. After the fixes ship, `message-test` can pre-test the new first screen.172 173## Failure modes174 175| Problem | Do this |176| --- | --- |177| The page is behind a login, blocked, or drawn by JavaScript so a fetch shows almost no text | Ask for screenshots and the copy; on a search page, the empty HTML is itself a T2 fail |178| Several traffic sources make different promises | Run M checks per source; if they conflict, flag that one page can't match them all (split the page or align the ads) as a major |179| The reader asks for opinions on colours or brand style | Answer only through a check with a rule (C7 hierarchy, M4 continuity); taste is not a finding |180| A competitor's page | Run everything except P4 and CP checks that need their sources; compare their first screen with the reader's |181| The page has 2 goals (book a demo and start a trial) | Ask which one counts; until then, C4 fails as major and the review uses the one higher on the page |182| The reader asks for more sections | Add a section only where a failed check needs one; say which check |183 184## Influenced by185 186- CXL's conversion research framework (ResearchXL), whose heuristic pass reviews each page against fixed questions about relevance, clarity, friction and distraction, and treats the result as an informed opinion to confirm with data. We turned the questions into checks with severities, weighted by page type.187- Harry Dry's 3 copy tests (can I picture it, can it be proved wrong, could no one else say it), used in C2: https://www.demandcurve.com/newsletters/growth-newsletter-202188- SHAKEUP's landing page teardown method: message first, then the next step, then findability and weight, with the first screen read before anything else.