microsoft-ads

Create new items on Instagram, Facebook Pages, TikTok, YouTube, LinkedIn Pages, and Google Business Profile through Windsor.ai - publish image, video, carousel, and story posts and comment on posts on Instagram; publish text and photo posts on Facebook Pages; publish text and image posts on LinkedIn Pages; create posts, reply to reviews, and update photos, hours, and open status on Google Business Profile. Use when the user wants to create, publish, or post something new. Collect inputs, show the full draft, create only after confirmation.

Report, rank, compare, and trend web analytics performance across Google Analytics 4 and Google Search Console through Windsor.ai. Use when the user asks about sessions, users, engagement rate, conversions, and revenue from GA4; clicks, impressions, CTR, and average position from Search Console. Do not use to change anything, to connect an account, or to schedule exports - route those to the sibling skills.

Analyze TikTok account (organic) performance through Windsor.ai. Use when the user asks about their TikTok personal or business account's organic insights — video views, likes, comments, shares, followers, profile views, or audience breakdowns by country, age, gender, or active hour. Do not use for TikTok Ads (those live in the TikTok Ads connector), other platforms, or publishing videos.

Analyze and manage TikTok Ads through Windsor.ai. Use when the user asks about their TikTok Ads performance — pulling live campaign, ad group, or ad metrics (spend, impressions, clicks, conversions, CPA, ROAS), comparing date ranges, or finding top or underperforming campaigns — or when they want to pause or enable a campaign, ad group, or ad, or change a campaign or ad group budget. Do not use for TikTok organic (that's the TikTok Organic connector — no ad or cost data there), or other ad platforms (Meta/Facebook, Google, LinkedIn, Microsoft Ads).

Report, rank, compare, and trend social media performance across Instagram, Facebook Pages, TikTok, YouTube, LinkedIn Pages, and Google Business Profile through Windsor.ai. Use when the user asks about reach, impressions, engagement (likes, comments, shares, saves), follower growth, video views, and watch time. Do not use to change anything, to connect an account, or to schedule exports - route those to the sibling skills.

Analyze and manage LinkedIn Ads through Windsor.ai. Use when the user asks about their LinkedIn Ads performance — spend, impressions, clicks, CTR, CPC, conversions, or leads at campaign, campaign-group, or creative level, with member demographic breakdowns — or wants to pause/enable a campaign, campaign group, or creative, or change a campaign or campaign-group budget. Do not use for LinkedIn organic company-page data (that's the LinkedIn Organic connector), other ad platforms, or GA4/web analytics.

Analyze Klaviyo email and SMS performance and manage flows through Windsor.ai. Use when the user asks about their Klaviyo campaigns, flows, lists, or metrics — opens, clicks, conversions, revenue, unsubscribes — or wants to create a flow or change a flow's status (draft / manual / live). Do not use for other email platforms (Mailchimp, Brevo, …), ad campaigns, or writing email copy.

Connect, reconnect, or add accounts for any of the 350+ sources Windsor.ai supports - Google Ads, Meta Ads, TikTok Ads, LinkedIn Ads, Microsoft Ads, Amazon Ads, Instagram, Facebook Pages, LinkedIn Pages, YouTube, TikTok, Google Business Profile, GA4, Search Console, HubSpot, Salesforce, Pipedrive, GoHighLevel, Shopify, Amazon Seller Central, Klaviyo, Stripe, QuickBooks, Xero, BigQuery, Snowflake, Google Sheets, and more - and resolve which connected account a request means. Use when the user wants to connect or set up a source, asks what is connected or available, sees no data, or hits a permission or sign-in error. Do not use for analysis or changes.

Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall / FAR / PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include "RCA on my ChangeNet model", "why is my AOI model failing", "audit ChangeNet predictions", "investigate FAR regressions", "root cause analysis on visual-changenet".

Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module subsets based on each module's label eligibility. Use when the user asks to "route VCN gap samples", "split AOI gaps for k-NN mining and AnomalyGen", or prepare the immediate next step after DEFT gap analysis in a VCN AOI SDA iteration.

Kumo-Anomaly — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune Kumo-Anomaly", "run Kumo-Anomaly inference", "detect anomalies with diffusion", "time series anomaly detection", "finetune Kumo-Anomaly", "use perform_anomaly_analysis_with_diffusion", "automl Kumo-Anomaly", "hyperparameter search Kumo-Anomaly", "hyperparameter optimization" or mentions "curriculum_medium.yaml", "final_model.pth", "kumo-anomaly", "sdk/anomaly_analysis", or "TSDiffuser_Generic".

Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ gaps", "extract VLM false positives and false negatives", or identify failure cases from a predictions JSON for DEFT root-cause analysis on a binary-classification VLM workflow.

Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary cases.

Run TAO Data Services object-detection gap analysis from ground-truth and inference annotations. Use when an object detection workflow needs to identify weak images by comparing model predictions against ground truth using per-class recall, precision, and AP50 thresholds. Use when the user asks to "analyze OD gaps", "find weak OD images", or "run mAP gap analysis".

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.

NVIDIA CDF curation and retrieval. Cosmos Curator video and image pipelines (split, dedup, shard, annotate) with filtering, captioning, and embedding. Cosmos Dataset Search ingest, search, and capability qualification. TAO data mining embeddings and neighbor matching. Ships domain event catalogs, including workplace employee conduct monitoring, which requires legal review before use. Use when a request names Cosmos Curator, Cosmos Dataset Search, CDF, or their Make and CLI surfaces. Not for model training, orchestration, or unrelated dataset questions.