td-skills

Query activation logs to check for errors and view volume

Core documentation generation patterns and framework for Treasure Data pipeline layers. Provides shared templates, quality validation, testing framework, and Confluence integration used by all layer-specific documentation skills.

Expert documentation generation for golden layers. Detects SCD types, documents business rules, metric definitions, aggregation logic, and data quality scoring. Use when documenting golden layer tables.

Expert documentation generation for hist-union workflows. Documents historical and incremental table combination strategies, schema validation, time-based partitioning, and backfill processes. Use when documenting hist-union layers.

Expert documentation generation for ID unification layers. Documents identity resolution algorithms, merge strategies, match rules, entity graphs, and multi-workflow orchestration. Use when documenting ID unification processes.

Expert documentation generation for ingestion layers. Automatically detects connector types (REST API, Database, File, Streaming), documents authentication patterns, rate limiting strategies, and incremental load patterns. Use when documenting data source ingestion workflows.

Generate Confluence-ready technical documentation for CDP Parent Segments. Produces structured docs covering attribute schemas, behavior definitions, star schema relationships, and data lineage. Use when you need to write docs, create specs, or explain parent segment architecture.

Expert documentation generation for staging transformation layers. Auto-detects SQL engine (Presto/Trino vs Hive), documents transformation rules, PII handling, deduplication strategies, and data quality rules. Use when documenting staging transformations.

Review creative content for brand guideline compliance across visual identity, messaging, tone, legal requirements, and accessibility. Use when validating email/SMS/Instagram ads against brand standards. Analyzes content against user-provided guidelines and generates 8-dimension compliance scoring with visual dashboard.

Interactive wizard to create comprehensive brand guidelines for your company. Set up brand colors, fonts, voice, messaging, legal requirements, and accessibility standards. Use when setting up brand guidelines, creating brand standards, or configuring brand compliance. One-time setup enables all creative skills.

Conversational workflow to build a comprehensive creative brief. Guides users through brief intake, brand guidelines, trend-informed creative ideation, and asset requirements — then outputs a workspace note and visual grid dashboard. Use when asked to create a creative brief, plan a campaign's creative strategy, or build a brief for ad ideation.

Automate update and maintenance of data dictionaries in Treasure Data - generates 80-90% of column descriptions automatically, allowing users to review results, make changes, and fill in gaps. Orchestrates schema extraction, AI-powered description generation, human review, and write-back as single workflow.

Generate email advertising concepts with compelling subject lines, body copy, CTAs, and HTML previews. Produces multiple creative variations optimized for inbox engagement and conversions.

This skill should be used when the user asks to "create an email", "build an email campaign", "design an email template", "generate an email for a segment", "preview an email", or "push an email to Engage". Generates enterprise-grade HTML email templates with live preview in Treasure Studio and natural language editing, then pushes the final version to Treasure Engage.

Shared reference files (playbook, workflow, agent and docs patterns) read by the fde-rfm, fde-nbp, fde-mta, fde-nba-scores and fde-classifier setup skills. Not used directly — to set up a model, use one of those skills.

Sets up a binary classification (propensity scoring) model on Treasure Data for any yes/no outcome — lead scoring, churn, conversion, campaign response, upsell, renewal: a workflow that builds the project's feature table, trains the AI Signals classifier (XGBoost or CatBoost with tuning, threshold selection and SHAP) and writes scores for Parent Segment attributes, then builds the project's classifier agent and dashboard. Use it to start, set up, configure, change, re-run or resume a propensity project and to build or rebuild its agent. Trigger on: set up a propensity model, start a propensity project, predict which customers will churn, score leads by likelihood to convert, predict campaign response, build a churn model, build a lead scoring model, classifier setup, classification workflow, configure the classifier, rebuild the classifier agent, resume classifier setup, classifier runbook. Once the project's classifier agent is installed, questions about model performance, drivers and scores go to it.

Sets up AI Signals binary classification (propensity scoring) on Treasure Data for churn, lead scoring, conversion, campaign response, upsell or renewal. Builds leakage-safe stacked training snapshots, trains XGBoost/CatBoost with tuning, threshold selection and SHAP, writes Parent Segment scores, and builds the project agent and dashboard. Use to start, configure, change, re-run or resume a project or rebuild its agent. Trigger on: set up a propensity model, start a propensity project, ai signals propensity model, propensity model, propensity scoring, how does propensity model work, predict which customers will churn, score leads by likelihood to convert, predict campaign response, build a churn model, build a lead scoring model, classifier setup, classification workflow, configure the classifier, classifier data prep, training snapshots, classifier output tables, rebuild the classifier agent, resume classifier setup, classifier runbook. Project agents answer performance, drivers and scores questions.

Sets up a customer-specific audience agent on any Treasure AI CDP parent segment: explores attributes, behaviors and existing segments, drafts the business context (key terms, conversion events, product categories, lead definitions, compliance and exclusion rules) and data dictionary, builds the agent into the Work Folder's .claude/skills/, and evaluates it with ten customer-specific test prompts until it is production-ready. Use it to start, set up, update, rebuild or evaluate the audience agent. Trigger on: set up an audience agent, start an audience agent project, an AI analyst for our parent segment, help our marketers analyze customers and build segments, build an audience agent for [customer], custom audience agent setup, parent segment agent setup, update audience agent business context, rebuild the audience agent, run audience agent eval, test the audience agent. Once the project's audience agent is installed, audience and segment analysis questions go to it.

Builds a custom HTML dashboard on Treasure Data data — new, or converted from an existing dashboard (.dash export, HTML file, screenshot) — and turns it into the project's dashboard skill: discovers the data, recommends direct queries or a pre-aggregating workflow, builds a first draft and registers it in the Work Folder. Use it to start, build, convert, migrate or resume a dashboard project, or to change its workflow. Trigger on: build a dashboard, start a dashboard project, I need a dashboard for these metrics, turn this report into a dashboard, create a KPI dashboard, convert a dashboard to HTML, Treasure Insights / Sisense dashboard migration, .dash conversion, dashboard from a screenshot or mockup, dashboard from a table, dashboard workflow, resume dashboard project. Once the project's dashboard skill is installed, questions about its numbers go to it.

Sets up MTA (Multi-Touch Attribution) on Treasure Data: a workflow that builds customer journeys from marketing touchpoints and conversions, runs the standard attribution models and the AI Signals Markov and Shapley models, then builds the project's MTA agent and dashboard. Use it to start, set up, configure, change, re-run or resume an MTA project and to build or rebuild its agent. Trigger on: set up MTA, start an MTA project, new MTA setup, measure which channels drive conversions, marketing attribution setup, multi-touch attribution setup, attribution workflow, configure MTA, rebuild the MTA agent, resume MTA setup, MTA runbook, MTA output tables. Once the project's MTA agent is installed, questions about channel contribution and journeys go to it.