Skill catalog

The current skill library, grouped the same way the in-chat guide groups it (say "mixshift help" to see this map in a chat). Every skill runs by name in plain English or directly as /mixshift-ai:mx-[skill].

Skills marked needs brand setup read your brand context; run brand setup once per brand first. Everything else works with sign-in alone. Each skill links to a detail page with what it produces and how to run it.

Get set up and signed in

mx-welcome: first-run orientation, shows where you stand and what to do next.
mx-auth-login: browser sign-in, account switching, session refresh.
mx-auth-service-setup: service credential for unattended runs, via a one-time setup code.
mx-scheduled-task: builds a scheduled task end to end and verifies its first run.
mx-brand-context: brand setup; builds the context the analytical skills read. Also retires a brand your team no longer works on, and restores it.
mx-update: guided update plus "what's new" catch-up.

Explore data and pull reports

mx-data-explore: query, sample, and CSV-export your MixShift warehouse (Sponsored Ads, DSP, Seller and Vendor Central revenue, orders, inventory, catalog). Read-only.
mx-amazon-report: on-demand reports from Amazon for any window (orders, listings, FBA, Sales and Traffic, Brand Analytics, settlement, vendor). Read-only.
mx-amazon-retail: live retail lookups (catalog, inventory, FBA inbound shipments, orders, finances, pricing, Subscribe & Save, product reviews, seller promotions, listings). Read-only.

Daily and weekly account health

mx-portfolio-quick-scan: one green/yellow/red card per account; do I need to log in today? Needs brand setup.
mx-daily-health-check: daily exception-based review of spend and efficiency anomalies. Needs brand setup.
mx-runaway-spend-check: catches keywords spiking or spending with zero conversions. Needs brand setup.
mx-keyword-bid-health: weekly bid review; pullback candidates and scale opportunities. Needs brand setup.

Search terms, negatives, and harvesting

mx-search-term-negation: systematic irrelevance review and surgical negative keywords. Needs brand setup.
mx-search-term-harvest: promotes terms that convert efficiently under auto or broad match into explicit targeting. Needs brand setup.
mx-phrase-negative-discovery: finds phrase-level negative candidates from your search-term corpus; every candidate is validated before use. Needs brand setup.
mx-asin-target-negation: reviews ASIN targets matched through auto and category paths for product-page overlap. Needs brand setup.
mx-ppc-relevance-check: semantic relevance verdicts on search terms, separate from spend thresholds. Needs brand setup.
mx-search-term-data-pull: the data-extraction layer the other search-term skills build on. Needs brand setup.

Live Amazon surfaces

mx-amazon-ads: live Ads account reads (campaigns, bids, budgets, recommendations) and audited writes. Changes preview first and never reach Amazon without your confirmation.
mx-amazon-amc: Amazon Marketing Cloud clean-room analytics in plain English. Also builds audiences from a description, previewed before anything is created. See Run AMC queries from Claude. Queries are read-only; audience changes preview first.
mx-amazon-dsp: DSP report pulls (campaign, inventory, audience), plus DSP performance older than 90 days and a monthly history in one request, plus reads of how a DSP account is actually set up: campaigns, ad groups, creatives, which creative is attached to which line item, whether a placement is running, paused, or was rejected and why, which creatives Amazon considers eligible for a given line item, and discovering the account's DSP advertiser id. Straight from Amazon. Read-only.

Reporting and analysis

mx-monthly-report: the monthly performance report with month-over-month, year-over-year, efficiency analysis, and a looking-ahead section. Needs brand setup.
mx-monthly-report-max: the max tier, powered by MixShift Intelligence: a client-ready brief plus a private internal call-prep companion, with live featured-offer diagnosis and last call's commitments checked against the data, and, where the brand has a current forecast, the month compared with the number the forecasting app shows and with what was forecast before it closed. When no forecast is published it asks whether you want one run. Works on any account, including brand-new or empty ones. Needs brand setup.
mx-max-forecast: a forecast for any account, on request. Checks the account has the history first, then explains the forecast in plain language with its measured accuracy and what it stands on. Serves the forecast the forecasting app published, or one computed from your warehouse history and labelled as computed. Can save your sponsored ads budget (only after you confirm the months and amounts) and run the forecast again on it. Works with sign-in alone.

Help, feedback, and contributing

mx-help: the in-chat capability map and router when you are stuck.
mx-feedback: sends a bug report, feature request, or comment straight to the MixShift team.
mx-share-skill: submit a skill you built for review and possible inclusion in the shared library.