Index of every page on this site: llms.txt
All skills
wix avatar

/wix-manage

@e2bc48e official
by Wix.comwix/skills40 stars
42
Run it yourself

REST recipes to configure and manage a Wix site's business solutions — stores, bookings, donations, payments, CMS, and more — and to publish HTML, CSS and JavaScript files as a live Wix site, with or without a Wix account. Open the matching recipe for the exact endpoint, method, and payload before calling — never guess a Wix API, never write Wix dashboard URL from memory. Routes to: automations, stores, bookings, donations, get-paid, CMS, contacts, forms, media, app-installation, custom-apps, pricing-plans, restaurants, ricos rich-content, sites, collaborators, studio-workspace, blog, calendar, domains, events, site-properties, ecommerce, marketing, online-programs, google-ads, google-business-profile, analytics, accessibility, seo, dashboard-navigation.

Use this Skill: https://skilld.dev/gh/wix/skills/wix-manage

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesgoogle-adsoptimize-a-google-ads-campaign.md

≈6.4k tokens on demand. Your agent reads this file only when SKILL.md points to it.

RECIPE: Optimize a Google Ads Campaign

Improve one existing campaign at a time: diagnose, propose a short plan, perform the changes the user approves. Pre-campaign inputs belong to Get AI Campaign Suggestions; plain reporting to Query Campaign Performance Analytics.

Base URL https://www.wixapis.com/_serverless/pa-google unless shown in full; the paths below include their version. <AUTH> is the Authorization header; body calls also need Content-Type: application/json. Amounts are in micros (1,000,000 = 1 unit of the account currency, read from GET /v1/accounts/current-site). The curl examples and inline bodies here are complete requests, shown with their response shapes: call them as shown, without a schema lookup, and read a method's schema only for a field this recipe or the recipe it links does not show.

Order of operations

  1. Data in the conversation wins. Facts the user states and data already present (campaign details, how long it has run, metrics, recommendations, a guide) are used as given; never re-derive, dispute or refetch them. When the user pasted the campaign or the recommendations, skip resolution and make no API call, site listing or site search before presenting the plan; a pasted campaign may not even exist on the current site, so do not look it up or hunt for its site.
  2. Check the type first. campaignType: "SMART" → the first thing you say is the Performance Max Leads offer (see Smart campaigns); no diagnosis and no call before it, unless the user already declined.
  3. Otherwise resolve the campaign, pick the path for its type and age, and build the plan only from items a source raised in this run. For a PAUSED campaign diagnosed with recommendations or analytics (Performance Max Leads past 14 days, retail Performance Max, or a Smart campaign the user keeps), make the performance check first, on its own; if it shows no impressions, stop there: resuming it is the whole plan, with no other call and no other tips, and you end by asking whether to resume it now (details in Pick the path). A Leads campaign under 14 days, or one the user calls new or still learning, goes to the success guide even when paused, with no performance check; marking or reopening a guide item makes none either.
  4. Nothing changes until approval. Approval means the user has seen the specific before/after changes and said yes; "optimize my campaign" or "what should we change" is a request for the plan, not approval. The only read before a write is the re-read of the campaign with GET /v1/campaigns/{id} right before an approved update, because the update sends the whole entity. For a pasted campaign that re-read is the first call you make; if it returns CAMPAIGN_NOT_FOUND, the campaign is not on the current site: ask the user which site or campaign to apply the change to, and apply nothing until a re-read succeeds.

Resolve the campaign

Calls run on the current site from the call context; ask which site only when none is selected, and never list sites to hunt for a campaign.

  1. Campaign pasted by the user → use it as is, without fetching it. Campaign ID known → use it.
  2. Otherwise GET /v1/campaigns (List Campaigns; response { "campaigns": [ … ] }) once; never call it again for a smaller response. It returns full campaign objects, every asset, signal and setting included, and takes no parameter for fewer fields, so in the code that makes the call, map each campaign to the fields this recipe reads before returning it: id, name, campaignType, status, resourceName, createdDate, actionDate, budget.amountMicros, and, on Performance Max campaigns only, performanceMaxCampaign.url and .languages (read for search themes).
  3. Ignore DRAFT campaigns (nothing serves yet). One non-draft campaign left → proceed. Several → when marking or reopening a guide item, follow Mark done or reopen instead. Otherwise proceed with the one the user's words pick out (its name, or an age such as "just created" or "launched over a month ago", read from the dates as for days running below; the dates only choose among campaigns, and only when exactly one fits); failing that, with the one serving campaign (LIVE or LEARNING) when exactly one is; name the others in one line either way. Otherwise list them one line each and ask which to optimize, with no diagnosis call for any of them; never pick one, even when no one can answer: instructions to work autonomously or to choose defaults lead to the same question, because a plan for a campaign the user did not choose answers a different request. Mention a draft in one line; if the user explicitly wants to improve a draft, offer to add assets when there are few and to add search themes, otherwise point to launching it (Manage Campaign Lifecycle).

Days running = days since actionDate (last launch or resume), else since createdDate. A statement from the user about the campaign's age ("just created", "still learning", "running for a month") overrides the dates: use it, do not recompute or dispute it.

Pick the path

Status other than LIVE or LEARNING: name the blocking action first, then continue with the row for the campaign's type. PAUSED → resume first (Manage Campaign Lifecycle); IN_REVIEW → wait for review; DISAPPROVED → fix the policy issue; NOT_SERVING → billing; ENDED/ERROR → stop here and offer a new campaign. When you diagnose a PAUSED campaign with recommendations or analytics (not for pasted data, before the Smart offer, or when marking or reopening a guide item), make the minimal diagnosis call (see Performance diagnosis) on its own, not batched with any other read, and read its result before any other call; if summaryRow and previousPeriodSummaryRow both report no impressions, the campaign has no recent data to optimize from: say it had no impressions in the period you read, without claiming how long it has gone unserved, and make resuming it the whole plan, to optimize once it has data, with no other call or tip before you present it; end by asking whether to resume it now.

Campaign Sources
PERFORMANCE_MAX_LEADS, under 14 days (or the user says it is new or still learning) Success guide only, also when PAUSED (name resuming it first); no recommendations, performance check or other analytics calls. Say performance-based advice starts after about two weeks. Discourage edits during learning except adding search themes (which the guide itself raises); if the user insists, warn that an edit resets Google's learning, then proceed
PERFORMANCE_MAX_LEADS, 14 days or more Recommendations + analytics. Do not retrieve the guide for advice (reading it to mark or reopen an item is still fine). While status is LEARNING (about 28 days), say the data is usable but early
PERFORMANCE_MAX (retail) Recommendations + analytics, always with shopping performance (POST /v1/shopping-performance-metrics)
SMART Offer the Performance Max Leads upgrade first (below); if declined, run the Smart path

Campaign success guide (Performance Max Leads, first 14 days)

The guide scans the landing page, the campaign configuration and the site's Google connections; it never uses metrics, so LEARNING and empty analytics do not block it. A request to improve the campaign or see the guide is approval to retrieve it. platformType is always GOOGLE.

curl -X POST 'https://www.wixapis.com/pa-platform/suggestions/v1/campaign-success-guides/get-or-create' \
  -H 'Authorization: <AUTH>' -H 'Content-Type: application/json' \
  -d '{ "campaignId": "7d4a9c2e-86f1-4b37-a2d5-9e18c6f043ab", "platformType": "GOOGLE" }'

Response: { "campaignSuccessGuide": { "id", "url" (landing page), "suggestions": [ { "id", "type", "status" } ] } }. The first call can take 120 seconds; wait, do not retry. Later calls return the saved guide at any campaign age, unless the landing page URL changed. suggestions is in priority order and lists only items that need attention; OPEN = pending, COMPLETED = the user marked it done (nothing was changed for them). Show OPEN items three at a time in API order, hide COMPLETED ones, and invite the next batch when more remain.

Types What to offer
GOOGLE_ADS_SEARCH_THEMES Generate a set with POST /v1/search-theme-suggestions and { "landingPageUrl": "<performanceMaxCampaign.url>", "textSuggestionInfo": { "languageCode": "<performanceMaxCampaign.languages[0].languageCode>" } } → searchThemes[], each becoming { "searchTheme": { "text": "…" } }; show it, apply the approved set with the update below. Link the Keywords Manager (Google Ads Dashboard Navigation) only if the user prefers the manual route
CONVERSION_POINT (no visible lead form or booking action), HEADER_MATCH (page heading does not match the ad headlines), CONTACT_AND_CREDIBILITY (no visible phone and email), CLEAR_CTA_COPY, ABOVE_THE_FOLD_CTA, MINIMIZE_FORM_FIELDS (over 4 fields), TESTIMONIAL, SOCIAL_CHANNELS, GOOGLE_REVIEWS, FAQ_SECTION Landing-page content: describe the edit in one line, offer to draft copy after approval; the user applies it in the Editor
GOOGLE_BUSINESS_PROFILE_CONNECTION Offer to start Connect a Wix Site to Google Business Profile; the owner finishes Google's consent in the browser
GOOGLE_MERCHANT_CENTER_CONNECTION Read account.merchantCenterAccountId from GET /v1/accounts/current-site; ask for the ID if absent; update the account per Install Google Ads and Create an Account. The link starts PENDING
MOBILE_OPTIMIZATION, SITE_SPEED Offer to inspect and name a concrete cause before promising anything; the user applies the site change

Editor link: use editUrl from the site context; if absent, make one Query Sites lookup filtered by id.$in with the current site ID; otherwise write Go to the Editor as plain text. One Editor link per answer, never guessed.

Mark done or reopen: retrieve the guide first (works at any age), confirm the type is present and read its current status; if it already has the requested status, say so and make no update, otherwise update by type. Only PERFORMANCE_MAX_LEADS campaigns have a guide; never retrieve one for another type. When several non-draft Leads campaigns have the item and the user's words pick out none of them (no name or age): GOOGLE_ADS_SEARCH_THEMES belongs to one campaign, so ask which; every other type is about the landing page or the site, so handle it on each of them whose guide url is the same page and name them, asking which campaign only when their pages differ. Update one guide at a time, never in parallel: concurrent updates on one site's guides fail with INVALID_REVISION. A clear "I did X" or "I undid X" is approval, no extra confirmation. The response wraps the updated guide; "status": "OPEN" reopens. Completion is self-reported: never say the page or campaign changed.

curl -X POST 'https://www.wixapis.com/pa-platform/suggestions/v1/campaign-success-guides/{campaignId}/update-suggestion-status' \
  -H 'Authorization: <AUTH>' -H 'Content-Type: application/json' \
  -d '{ "type": "CLEAR_CTA_COPY", "status": "COMPLETED" }'

Google Ads recommendations (day 14 onward, and retail Performance Max)

For a PAUSED campaign, the performance check in Pick the path comes first; call this only if that check found impressions.

curl -X GET 'https://www.wixapis.com/_serverless/pa-google/v1/recommendations?campaignId=0b6c8f3e-2a41-4d7e-9c1a-5f2e8d4b7a10' \
  -H 'Authorization: <AUTH>'
{ "recommendations": [ { "type": "IMPROVE_PERFORMANCE_MAX_AD_STRENGTH", "campaignIds": ["0b6c8f3e-…"],
    "impact": { "baseMetrics": { … }, "potentialMetrics": { … } },
    "details": { "adStrength": "AVERAGE", "assetCoverage": { "adStrengthActionItems": [
      { "actionItemType": "ADD_ASSET", "addAssetDetails": { "assetFieldType": "MARKETING_IMAGE", "assetCount": 3 } } ] } } } ] }

Google generates these from the account's settings and recent performance and regenerates them on its own schedule, so an item can keep appearing after you act on it; say so. Only types the user can act on through Wix are returned. details is Google's payload for the type, read as is; impact is Google's estimate, not a promise: baseMetrics is the estimated performance with the current settings and potentialMetrics after the change, over a period Google does not state. Neither is the campaign's actual results, so never report them as its spend or conversions or derive a cost per lead or daily spend from them; convert costMicros with the account currency. An empty list is a finding, not an error: fall through to the performance diagnosis.

type Act through
CAMPAIGN_BUDGET, FORECASTING_CAMPAIGN_BUDGET, MARGINAL_ROI_CAMPAIGN_BUDGET Daily budget (update below), proposing the option from details.budgetOptions with its impact
IMPROVE_PERFORMANCE_MAX_AD_STRENGTH Leads: add the field types and counts in details.assetCoverage.adStrengthActionItems (a Wix addition, already filtered to the text and image types the update accepts). Other Performance Max campaigns: describe it and offer no asset edit, the update ignores their assets
PERFORMANCE_MAX_FINAL_URL_OPT_IN Set performanceMaxCampaign.assetAutomationSettings to [{ "type": "FINAL_URL_EXPANSION_TEXT_ASSET_AUTOMATION", "status": "OPTED_IN" }]
CALL_ASSET Set performanceMaxCampaign.phone (countryCode, phoneNumber)
SHOPPING_* (disapproved products, Merchant Center suspension, missing GTIN, color, size…) Not fixable through the Google Ads APIs: summarize details (merchant, product counts) and link the Stores products page (Stores Dashboard Navigation) and Google Merchant Center
PERFORMANCE_MAX_OPT_IN (account-level, empty campaignIds) Create a Performance Max Leads campaign with Create and Launch a Performance Max Campaign

A type not listed here: describe it from Google's name and offer no action.

Performance diagnosis (supporting)

Use the analytics calls that fit the question; do not invent thresholds. Bodies and enums are in Query Campaign Performance Analytics. The minimal diagnosis is one POST /v1/performance-metrics call, keyed by campaignResourceName (the campaign's resourceName), with an explicit 30-day dateRange.custom (from/to, YYYY-MM-DD) and includePreviousPeriod: true; the previous-period comparison needs that finite range, an omitted range (campaign lifetime) fails. Add others only when the question needs them: POST /v1/conversion-metrics (leads, orders, cost per lead; dateRange is required), POST /v2/search-term-metrics (sort by COST: terms that spend without converting are exclusion candidates, judged for relevance to the business) and POST /v1/asset-performance-metrics (Leads only; performanceLabel is LOW, GOOD or EXCELLENT once an asset leaves LEARNING: a LOW asset is a replacement candidate) take campaignId. Summarize in two to four lines; every proposal cites the number behind it.

Smart campaigns

Offer the upgrade first, before any diagnosis or API call, unless the user has already declined it; two sentences, never forced, ending with the question of which way to go. The choice is the user's: never pick a path, state an assumed goal in place of the question, or lay out migration steps yet. Stop there: the Smart plan below comes only after the user declines, never in the same message as the offer. The reasons: Performance Max Leads is Google's recommended path from Smart campaigns, and it serves across all Google surfaces (Search, Display, YouTube, Gmail, Discover, Maps) rather than Search alone. If accepted, follow Create and Launch a Performance Max Campaign, keep the Smart campaign running until the new one is launched, then offer to pause it (five live campaigns per site, and double spend otherwise). Google issues no recommendations for Smart campaigns, so if the user keeps theirs, diagnose with analytics. Exclude clearly irrelevant search terms that spend under any focus; then, when the user states no goal, pick the focus with these rules of thumb (what they asked for, such as "more leads" or "spending too much", wins):

  • Under about 1,000 impressions in 30 days → reach: keyword themes (up to 10) and locations; raise the daily budget only when the 30-day cost ÷ 30 is close to it (budget.amountMicros ÷ 1,000,000), since a campaign spending well under its budget is limited by its targeting, not its budget.
  • Otherwise CTR under about 1% → clicks: excluded search terms, ad copy, keyword themes.
  • Otherwise → conversions: landing page, chosen from the site's published pages (a services page for leads, a shop or all-products page for sales).

Make changes

Propose first, change only on approval (see Order of operations): present the plan → the user picks items → generate what is needed and show it → re-read the campaign → show only what changes (field, before, after; never the whole entity) → one explicit yes → one update → confirm from the response.

Every update sends the whole campaign; never send a partial body. PATCH /v1/campaigns/{id} takes { "campaign": <the entire entity returned by Get Campaign> } with only the changed fields different, and no other key: leave updateMask out, since as an array or { "paths": [...] } it fails with 400 Failed to parse request message. The fields to update are inferred, and omitted fields may be cleared. To add a list item (asset, search theme, excluded term) append it without a resourceName; to remove one, omit it. Keep id, accountId, campaignType, locations, languages, phone, and every existing asset and signal you are not removing. The same rule governs every update in Manage Campaign Lifecycle; field-level examples: Update Campaign.

curl -X PATCH 'https://www.wixapis.com/_serverless/pa-google/v1/campaigns/{campaignId}' \
  -H 'Authorization: <AUTH>' -H 'Content-Type: application/json' \
  -d '{ "campaign": { …the entire object returned by GET /v1/campaigns/{campaignId}…, "budget": { "amountMicros": "45000000" } } }'

The response is { "campaign": { … } } with the saved state; confirm the change from it.

Change Field (type) Rules
Daily budget budget.amountMicros (any) Source, in order: Google's budgetOptions; POST /v1/budget-recommendation (Performance Max) or POST /v1/budget-suggestions (Smart), bodies in Get AI Campaign Suggestions; last resort about 1.5× the current budget. Always within GET /v1/campaign/daily-budget-boundaries
Assets performanceMaxCampaign.assetGroups[0].assetGroupAssets.assets[] (Leads only; retail asset edits are ignored) Ask whether to generate images or use Media Manager URLs the user supplies. Generate with POST /v1/text-asset-suggestions and POST /v1/image-asset-suggestions (60 to 120 s; images are saved to the Media Manager). Per-asset shape and the count table (headlines 3–15, descriptions 2–5, images 1–20 per type, logos 1–5) are in Create and Launch a Performance Max Campaign; the update also accepts PORTRAIT_MARKETING_IMAGE (4:5) and LANDSCAPE_LOGO (4:1), 0–20 each; max 120 assets, no duplicates. Offer removing LOW-labelled assets as a separate optional item, keeping the minimums
Search themes assetGroups[0].assetGroupSignals.signals[].searchTheme.text (Leads) Max 25
Excluded search terms smartCampaign.excludedSearchTerms[] (Smart); performanceMaxCampaign.excludedKeywords[] (Leads) { "freeFormKeywordTheme": "…", "displayName": "…" } appended to the existing list
Keyword themes, ad copy, landing page smartCampaign.keywordThemes[] (max 10, same shape as excluded terms), smartCampaign.adGroups[0].ads[0].headlines (3, ≤30 chars) and .descriptions (2, ≤90), smartCampaign.url (Smart) Landing page must be a published page of the site. For a Leads campaign, changing performanceMaxCampaign.url resets learning and the guide: warn, and change it only if the user insists
Locations locations[] (any) geoTargetConstants/{id} from GET /v1/geo-options

Present the plan

  1. What I found: two to four lines with status, days running, and the 30-day numbers against the previous period when read.
  2. Do now: never more than three items, each tagged with its source (Google, Success guide, Performance) and ending in one concrete step. Every item traces to something a source raised in this run; no generic advice such as landing-page tips nobody flagged. Further items wait for the next batch.
  3. I can do this for you: one grouped offer of the changes you can perform after approval.
  4. Next actions: each destination once (Editor, Keywords Manager, Stores, Merchant Center), as an absolute link when known.
  5. One closing line when more items remain, inviting the next batch.
  6. End with a question as the last line: which of these should I apply? When the plan adds images, it also asks whether to generate them or use the user's own Media Manager images. State any assumption earlier, never in place of the question. (For a Smart campaign before the user has chosen, the question is whether to upgrade or keep the campaign.)

Plain Markdown, top to bottom; no tables or columns in the user-facing answer.

Errors

Error Response
ACCOUNT_NOT_FOUND, CAMPAIGN_NOT_FOUND, CAMPAIGN_DAILY_BUDGET_TOO_HIGH, MAXIMUM_NUMBER_OF_CAMPAIGNS_REACHED As in Manage Campaign Lifecycle; never probe other sites to recover. On the re-read of a pasted campaign, CAMPAIGN_NOT_FOUND means it is not on the current site: ask which site or campaign before applying anything
CAMPAIGN_TYPE_NOT_SUPPORTED, PLATFORM_NOT_SUPPORTED Guides exist only for Performance Max Leads with platformType: "GOOGLE"; use the recommendations path, or, when marking or reopening, skip that campaign
SUGGESTION_NOT_FOUND Retrieve the guide and use a type it contains
INVALID_REVISION (409) on a status update Another update to the site's guides landed first: retrieve the guide again and, once, update only if the item still lacks the requested status; on a second 409, tell the user the status was not saved and stop
INVALID_ASSET_GROUP_ASSETS, NOT_ENOUGH_ASSETS, DUPLICATE_ASSET, INVALID_IMAGE_FORMAT The resulting asset list breaks a count, size or uniqueness rule; fix and resend the full entity
quotaError (500, "Too many requests") from an analytics call Google's rate limit: wait a few seconds and retry that call once; never replace it with other calls
Timeout on the guide or asset generation; permission error Report the unknown outcome and retry later, never a second scan immediately; after a rejected call stop, do not try other base URLs or sites

References

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alerttoday4 checks · Risk SAFE
  • Gen Agent Trust Hub1d

    The skill is a comprehensive management tool for Wix sites. It contains potential security risks such as an indirect prompt injection surface from site scraping and the ability to define JavaScript-based automation logic, but it includes strong requirements for user confirmation before any site changes.

  • Sockettoday

    No alerts

  • Snyk1d

    Risk: CRITICAL · 3 issues

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at e2bc48e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 4 days ago
compatibility
Requires Wix REST API access (API key or OAuth).
  • wix
  • rest-api
  • ecommerce
  • bookings
  • cms
  • contacts
  • blog
  • domains
  • restaurants
  • site-configuration
  • api-integration

README badge

README badge for wix/skills/wix-manage

REST API operations for configuring Wix business solutions including stores, bookings, CMS, contacts, domains, and ecommerce. Routes to site setup, entity management (products, services, staff), bulk administrative operations, and server-to-server integrations across Wix's business app ecosystem.

Generated from the current SKILL.md.

Do I need API credentials to use these recipes?
Yes. The skill requires Wix REST API access via either an API key or OAuth token to execute any management operations.
Can I use these recipes to display data on my site frontend?
No. These recipes are for backend REST API operations only — site configuration, entity management, and administrative tasks. They do not cover frontend development or displaying data to users.
What business domains do these recipes cover?
The skill covers stores, bookings, payments, CMS, contacts, forms, media, apps, pricing plans, restaurants, rich content, sites, blogs, calendars, domains, and site properties.
Do these recipes handle OAuth authentication with external services like Google Calendar?
Yes. The external calendar integration recipe covers OAuth-based setup with Google Calendar, Microsoft Outlook, and Apple Calendar for bidirectional event sync.

Generated from the current SKILL.md. These answers refresh after source changes.