원클릭으로
marketing-agent
marketing-agent에는 gomarble-ai에서 수집한 skills 36개가 있으며, 저장소 수준 직업 범위와 사이트 내 skill 상세 페이지를 제공합니다.
이 저장소의 skills
Use when researching competitor ad creatives: find competitors, brand IDs, evergreen winners, breakout winners, pattern analysis.
Use when generating Word documents (.docx). Uses the marble_docx API.
Use when generating PDF documents. Uses the marble_pdf API.
Use when generating PowerPoint presentations (.pptx). Uses the marble_pptx API.
Use when generating Excel workbooks (.xlsx). Pandas + openpyxl patterns for multiple sheets, number formats, freeze panes, formulas.
Use for any GA4 query whose result will be reported back to the user. Covers conversions ≠ transactions distinction, channel-subset-sum trap with sessionDefaultChannelGroup, intraday partial-data discipline, Paid Social aggregation rules, API-vs-UI attribution mismatch.
Use when creating a Google Ads ad group. Loaded after the create master skill.
Use when creating a Google Ads ad (RSA, expanded text, etc.). Loaded after the create master skill.
Use when creating Google Ads assets (sitelinks, callouts, structured snippets, images). Loaded after the create master skill.
Use when adjusting Google Ads bid modifiers (device, location, audience). Loaded after the create master skill.
Use when creating a Google Ads campaign. Loaded after the create master skill.
Use when launching a Google Ads experiment. Loaded after the create master skill.
MUST load FIRST for any Google Ads create, update, or mutation task. Master workflow for create campaigns, ad groups, ads, assets, sitelinks, experiments, negative keyword lists, bid modifiers, pause/rename/update. Triggers: any Google Ads write intent.
Use when creating a Google Ads shared negative keyword list. Loaded after the create master skill.
Use for any Google Ads audit, performance review, optimization request, strategy question, or account restructuring. Covers 8 analytical dimensions: hierarchical drill-down, breakdowns, temporal trends, attribution rigor.
Guardrails for Google Ads recommendations and mutations. Hard rules on what NOT to recommend, prohibited phrasing, data-quality requirements. Used internally for any Google Ads optimization or change recommendation.
Use when planning Google Ads keywords: keyword discovery, evaluating intent/volume/bid, match-type selection.
Use when evaluating Google Ads Performance Max campaigns: maturity gate, PMax vs Search comparison, asset performance labels, device/location thresholds.
Use when scaling Google Ads Performance Max campaigns: budget scaling rules, pause triggers, location/audience/asset expansion. Loads PMax evaluation first.
Use when analyzing Google Ads Search campaigns: Q1–Q5 query classification, CPC inflation diagnosis, rank/budget pressure, decision matrix, scaling prerequisites.
Use when making changes to Google Ads Search campaigns: tool parameters for bid adjustments, budget changes, negation, query isolation.
Use when analyzing or optimizing Google Ads Shopping campaigns: feed health gate, item KILL/DOWNGRADE/PROMOTE rules, product groups, search-term negatives, SCALE/T/CAP.
Foundation tool reference for any Google Ads task — GAQL syntax, common entity relationships, default reporting windows. Used internally when working with Google Ads tools.
Use when proposing or executing Meta Ads changes: propose/execute workflow, campaign/adset/ad update rules, currency in cents.
Use when creating a Meta ad with its creative in one shot. Auto-detect landing page/CTA/UTM, creative analysis for copy, object_story_spec vs asset_feed_spec, text length guardrails, video thumbnail auto-gen. Loaded after the create master skill.
Use when creating a Meta ad set. Parent campaign verification, pixel detection, targeting patterns, attribution spec, bid amount rules, placement/optimization guardrails. Loaded after the create master skill.
Use when creating a Meta campaign. ABO/CBO detection, budget guardrails, special_ad_categories, structure defaults. Loaded after the create master skill.
MUST load FIRST for any Meta ad creation, launch, campaign setup, ad set creation, or creative push. Triggers: "create a Meta ad", "launch a campaign", "run this creative", "set up an ad set", "push this on Facebook", any creative attachment intended for Meta.
Use when analyzing Meta ad creatives: video hook/hold rates, 4 diagnostic scenarios, image/catalog rules, creative pattern recognition.
Use for any Meta Ads audit, performance review, optimization request, strategy question, or funnel analysis. Covers 8 analytical dimensions: hierarchical drill-down, breakdowns, temporal trends, attribution rigor.
Guardrails for Meta Ads recommendations and mutations. Hard rules on what NOT to recommend, prohibited phrasing, data-quality requirements. Used internally for any Meta optimization or change.
Use when analyzing Meta (Facebook/Instagram) ad performance: account type detection, Pareto analysis, baselines, performance thresholds, issue diagnosis.
Foundation tool reference for any Meta (Facebook/Instagram) Ads task — Marketing API quirks, common entity relationships, currency in cents. Used internally when working with Meta tools.
Foundation for any document generation skill (DOCX/PPTX/PDF/XLSX). Python-sandbox execution environment, available packages, file I/O conventions. Used internally by the document skills.
Use when analyzing Google Search Console data: organic search analysis, GSC data interpretation, opportunity scoring.
Use when querying Shopify orders or reconciling against a merchant dashboard. Default NO financial_status filter (dashboard parity), gross vs net revenue, created_at vs processed_at, refunds handling, multi-currency confirmation.