1---2name: meta-serp-copy3description: >-4 Writes the title tag and meta description for one B2B SaaS page, matched to the search intent and checked against5 what already ranks: length in characters and approximate pixels, keyword position, brand, punctuation, stock6 phrases, duplicates on the site, voice and claims. Returns a primary pair and one alternative with READY, READY7 WITH NOTES, NOT READY or BLOCKED. Use it for a new page, a refresh, or a page that ranks but loses the click. Not8 for choosing the keyword (use keyword-selection) or for writing the page itself.9license: MIT10compatibility: >-11 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Reads the live results if the agent can12 browse, otherwise pasted titles. Python 3 is optional, for the length and pixel check.13metadata:14 author: SHAKEUP15 version: "1.0.0"16 stage: make17 plugin: seo-ai-search18 homepage: https://www.shakeuphq.com/skills/meta-serp-copy19---20 21# Title and description22 23Writes the 2 lines a buyer reads before deciding to click, so a page that earns a position also earns the visit.24 25## Purpose26 27- One job: write and check one title tag and one meta description for one page.28- Stage: make. It runs its own check and the voice and claim checks, fixes, and checks again, at most 2 rounds.29- The title and description describe the page as it is. They never promise what the page doesn't deliver.30- It never puts a number or a claim in the copy that isn't on the page or in the profile's approved claims.31 32## Use when / not33 34| Situation | Use |35| --- | --- |36| A new page needs its title and description | this skill, after `keyword-selection` |37| `content-triage` marked a meta quick win (ranks, loses the click) | this skill |38| `refresh-audit` flagged the title or description | this skill |39| The keyword isn't chosen | `keyword-selection` first |40| The whole page needs work | `refresh-audit` |41 42## Inputs43 44| Input | Required | Ways to provide, in order | If missing |45| --- | --- | --- | --- |46| Primary keyword and intent (learn, compare, buy, navigational) | yes | the `keyword-selection` handoff; the reader's request | ask once; without a keyword, `BLOCKED` |47| The page: its H1, its main points, any figures it states | yes | the draft or URL; a summary the reader pastes | `BLOCKED`, since the copy must describe the page |48| The live results: top 10 titles and descriptions | no | browse the results; titles and descriptions the reader pastes | written from intent alone; a warning: not compared with what ranks |49| The site's existing titles | no | a crawl or sitemap; a pasted list | a warning: duplicates not checked |50| Current click rate and position | no | the `content-triage` handoff; Search Console | none needed; noted |51 52## Profile read53 54From `company-profile.md`: `## Company` (name and brand terms, for the brand at the end), `## Buyers` (the role to name in the title), `## Voice` (point of view, words to use and avoid), `## Claims and proof` and `### Never say` (the only figures the copy may carry beyond the page's own sourced ones), `## Competitors` (mention policy, for comparison titles), and every `## Learnings` entry for `meta-serp-copy` with status `noted`, `fact` or `accepted`.55 56No profile: ask for the brand name as it should appear in titles and any claims the company can make in public, in one message. Say that `company-profile` saves this next time.57 58## Steps59 601. **Apply learnings.** Read them first. A learning such as "our titles test better without the brand" overrides the default.61 622. **Read what ranks.** From the top 10: the common title shape (list, question, guide, brand first, comparison), modifiers (a year, a number, "for <team>"), how descriptions open, and the words Google bolds for the query. Then name the gap in one sentence: what the page offers that none of the 10 say. Without the results, write from intent and mark it.63 643. **Pick the frame by intent.**65 66 | Intent | Title | Description |67 | --- | --- | --- |68 | learn | the topic first, or the buyer's own question | what the reader will understand or be able to do; no sales language |69 | compare | the category plus the criteria or the count ("<n> <category> tools compared on <criterion>") | the evaluation criteria and what the list includes |70 | buy | the outcome or the product for the audience | speed, setup or what happens next, with the lowest-friction next step |71 | navigational | the brand or product first | confirm the reader is in the right place |72 73 B2B calibration: name the role or company type where it fits ("for RevOps teams", "for sales-led SaaS"), and avoid consumer urgency ("don't miss out").74 754. **Write 3 titles.** Rules:76 77 | Rule | Why |78 | --- | --- |79 | Under about 580 pixels (roughly 50 to 60 characters) | Google cuts titles to fit the screen; wide letters like W and M run out sooner |80 | The keyword, or a close variant, in the first half | it is what the searcher scans for |81 | Brand last, after a pipe: `<copy> \| <Brand>` | recognizable at a glance; brand first only on the homepage or a navigational page |82 | No dashes, no exclamation marks, no words in capitals | dashes and exclamation marks read as filler |83 | No stock phrases ("everything you need to know", "ultimate guide") | they say nothing a buyer can check |84 | A superlative ("best", "#1") only on a ranked list, or with proof from `claim-check` | an unproven superlative breaks trust and policy |85 | A year only when the query is time-sensitive and the page is kept current | a year dates an evergreen page |86 | One title per page, different from every other title on the site | Google rewrites duplicate or stuffed titles more often |87 885. **Write 2 descriptions** in 140 to 160 characters: open with what the reader gets (the hook), add one specific value signal (a number from the page or the approved claims, a named method, the criteria), and end on what to do or what they leave with. Include the keyword's words once, so Google can bold them. Never open with the brand or with "This article".89 906. **Check.** With Python, write the keyword, brand, site titles and candidates to JSON and run:91 92 ```93 python3 scripts/snippet_check.py --json snippets.json94 ```95 96 Without Python: count characters; estimate pixels as characters times 10 for mixed text and add 2 for each W or M; check each rule above by eye; say which way you ran it. Then run `voice-check` on the copy (or check dashes, the profile's words to avoid and the AI patterns inline) and `claim-check` on every number and comparison (or match each against `## Claims and proof` inline).97 987. **Pick the pair.** The primary pair, plus one alternative that tests a different frame (a question against a number-led title, say), each with what it is built to win.99 100## Check and verdict101 102| Finding | Severity |103| --- | --- |104| Title over about 580px; description over 160 characters; empty | critical |105| A dash or an exclamation mark | critical |106| The keyword missing from the title | critical |107| A near-duplicate of a title already on the site | critical |108| A number or claim not on the page or in the approved claims; anything from `### Never say` | critical |109| Title outside 50 to 60 characters; keyword in the back half; brand not last | warning |110| Description under 140 characters; keyword words missing; a generic call to action; a self-describing opener | warning |111| Not compared with the live results; duplicates not checked | warning |112| `voice-check` warnings | warning |113 114| Verdict | Condition (first match wins) |115| --- | --- |116| `BLOCKED` | No keyword, or nothing about the page, after asking |117| `NOT READY` | Critical findings remain after 2 rounds |118| `READY WITH NOTES` | Warnings only |119| `READY` | No findings |120 121No named stops. A request for a claim the profile can't back is not a stop: write the copy without it and say why.122 123## Loop124 1251. Run the check on all candidates.1262. Fix critical findings first: shorten from the end of the copy (keep the keyword and the brand), swap wide words for narrow ones, replace an unbacked figure with an approved one or the mechanism, rewrite a duplicate around the page's own gap.1273. Check again. At most 2 rounds; then hand over the best pair with what is still open, labelled.128 129## Learn130 131Append a learning to the profile when:132 133- the reader picks the alternative over the primary, or rewrites the copy (a `proposal` with the frame they preferred);134- the click rate is remeasured 30 to 60 days after the change (a `fact`: CTR before and after at a similar position, with the source);135- Google shows a different title than the one written (a `fact`: what it showed, so later runs avoid the pattern that got rewritten).136 137Example: `- 2026-10-24 | meta-serp-copy | fact | Number-led title lifted CTR on /blog/pipeline-by-channel-report from 0.9% to 1.8% at position 8 to 9 | Why: Search Console, 45 days before and after | Status: noted`138 139## Output140 141```142Verdict: <READY | READY WITH NOTES | NOT READY | BLOCKED> · Coverage: <complete | partial (what's missing)> · Check: <script | by hand> · Rounds: <n>143Keyword: <keyword> · Intent: <intent> · Gap in the results: <one sentence, or "not checked">144 145Primary146Title: <title> (<n> characters, about <n>px)147Description: <description> (<n> characters)148Built to win: <one line>149 150Alternative151Title: <title> (<n> characters, about <n>px)152Description: <description> (<n> characters)153Built to win: <one line>154 155| Finding | Severity | Fixed? |156Claims used: <each figure and its source, or none>157Learnings applied: <list, or none>158```159 160Then the handoff block.161 162## Hand off163 164```handoff165skill: meta-serp-copy166version: 1.0.0167verdict: READY168coverage: complete169for: https://example.com/blog/attribution-software170outputs:171 title: Attribution Software Compared for Sales-Led SaaS | Example172 description: <the description>173 alternative_title: <the alternative>174 remeasure: compare CTR at a similar position 30 to 60 days after it goes live175next: []176open: []177```178 179## Failure modes180 181| Problem | Do this |182| --- | --- |183| The keyword plus the brand won't fit | Keep the keyword and the differentiator; shorten the brand to its shortest recognizable form, or drop it on long titles and say so |184| The reader wants a figure the profile can't back | Leave it out, say why, and offer the approved figure or the mechanism instead |185| The page is a list but doesn't rank the items | Don't write "best"; use "compared" or the count |186| Google already rewrites the current title | Read what it shows; the rewrite usually comes from the H1, so align the title with the H1 |187| A competitor name is in the keyword | Follow the profile's mention policy; without one, ask before naming them |188| The page has no description field in its CMS | Hand over the copy anyway and flag it; Google then writes the snippet from the page |189 190## Influenced by191 192- SHAKEUP's meta copy rules, also used by the site's search result preview: titles measured in pixels, the brand last after a pipe, no dashes or stock phrases, and descriptions that sell the click.193- Google's title link documentation, which explains how titles are cut and when Google rewrites them: https://developers.google.com/search/docs/appearance/title-link194- Google's snippet documentation, which says the meta description is used when it describes the page better than the page text: https://developers.google.com/search/docs/appearance/snippet