sdk-skills

Plugin sdk-skills from marketplace td-skills in treasure-data/td-skills. Commands read from the repo's manifest — 8 days ago.

Skills (93)

• seo-analysis

  Runs SEO and AEO (Answer Engine Optimization) analysis on websites or specific pages. Use when the user mentions SEO, AEO, search rankings, search optimization, or wants to analyze how their pages perform in search engines and AI answers. Produces a data dashboard and action report with before/after

• aps-doc-core

  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.

• aps-doc-golden

  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.

• aps-doc-hist-union

  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.

• aps-doc-id-unification

  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.

• aps-doc-ingestion

  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.

• aps-doc-master-segment

  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.

• aps-doc-staging

  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.

• brand-compliance

  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 w

• brand-onboarding

  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 cre

• creative-brief-architect

  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 creat

• image-brand-compliance

  Review image files (PNG/JPEG) against brand guidelines — score visual compliance across 8 dimensions, identify violations with exact fixes, and apply corrections via Pillow or AI regeneration. Use when reviewing ad creatives, social media images, or AI-generated visuals for brand alignment. Triggers

• multi-channel-ad-ideation

  Orchestrates multi-channel ad ideation for email, SMS, and Instagram campaigns using a structured creative direction workflow. Use when brainstorming campaign concepts, generating ad copy variations, developing creative directions, exploring messaging strategies, or generating promotional ideas for

• email

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

• image-editor

  Interactive visual editor for Instagram ad images. Use when editing generated images, adjusting text overlays, repositioning logos, or modifying ad visual elements.

• image-gen

  Generate real Instagram image ads with AI-generated visuals and text overlays. Combines TD Creative Studio image generation with headline compositing via Pillow. Use when user wants to create Instagram ad images, generate ad visuals with text, or produce shareable ad PNGs. Trigger keywords: instagra

• instagram

  Generate Instagram image ad concepts with visual descriptions, copy constraints (125/40/30 chars), and HTML mockups. Visual-first, mobile-native single-image ads for Feed and Stories.

• sms

  Generate SMS advertising concepts with ultra-concise mobile messaging optimized for 160-character constraints. Includes personalization, CTA optimization, and timing recommendations.

• google-slides-review

  Use this skill at the end of a Google Slides deck-creation flow run by the same agent in the current session, before reporting the finished URL to the user. Catches the failure modes a creating agent reliably misses — surviving placeholder text, unswapped template imagery, layout overflow, hidden-or

• google-slides

  Use this skill any time the user wants to create a Google Slides deck from a template, mentions "Google Slides" with a template in mind, provides a Google Slides URL plus a content brief, or asks to "make slides", "build a deck", "generate a presentation", or "fill this template" in a Google Workspa

• pptx

  Use this skill any time the user wants to create a new PowerPoint presentation, slide deck, pitch deck, or .pptx file from scratch. Covers creating business presentations, quarterly reports, project proposals, product roadmaps, training materials, and any multi-slide document destined for PowerPoint

• email-campaign

  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 natu

• fde-classifier

  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, a

• fde-mta

  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,

• fde-nba-scores

  Sets up NBA (Next Best Action) engagement scores on Treasure Data: a workflow that unions customer activity and writes per-profile next best time, channel and campaign scores plus engagement flags for Parent Segment attributes, then builds the project's NBA agent and dashboard. Use it to start, set

• fde-nbp

  Sets up NBP (Next Best Product) recommendations on Treasure Data: a workflow that reads item-level purchase or interaction data, trains the AI Signals NBP model (ALS, similar-to-latest or popular) and writes the top products and categories per user for Parent Segment attributes, then builds the proj

• fde-prob-idu

  Sets up probabilistic ID unification on Treasure Data: finds duplicate people missed by deterministic IDU (typos, changed emails or inconsistent phone/address formats). Builds the input table, blocks likely matches with MinHash, clusters them with the AI Signals pidu solution, writes merged clusters

• fde-rfm

  Sets up RFM (Recency, Frequency, Monetary) customer segmentation on Treasure Data: a workflow that unions customer activity (pageviews, orders, email, sales), scores every profile with the AI Signals RFM model and assigns one of ten segments for Parent Segment attributes, then builds the project's R

• fde-ai-signals-shared

  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.

• fde-custom-audience-agent

  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 age

• fde-custom-dashboard-builder

  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

• field-agent-deployment

  Best practices for developing, testing, and deploying production-ready Field Agents including R&D workflows, version control, testing strategies, and release management

• field-agent-documentation

  Comprehensive template and guidelines for documenting Field Agents including technical specifications, system prompts, tool specifications, user interactions, and standardized documentation structure

• field-agent-visualization

  Professional Plotly visualization best practices for Field Agents including chart specifications, color palettes, formatting standards, and JSON structure requirements for executive-ready data visualizations

• activations

  Query activation logs to check for errors and view volume

• id-graph-canonical-id-size

  Query ID graph to analyze canonical ID group sizes. Use when debugging over-stitching by checking how many individual IDs are mapped to each canonical ID, or when canonical ID groups seem too large.

• id-graph-ids-to-canonical-id

  Query ID graph to find individual IDs appearing in multiple canonical ID groups. Use when debugging over-stitching by checking whether a single ID has been stitched to more than one canonical ID.

• identify-top-key-values

  Analyze RT event tables to identify the most common values for stitching keys. Use when inspecting what ID values are actually flowing into RT 2.0, debugging unexpected stitching behavior, or checking for data quality issues like nulls or empty stitching keys.

• identity

  Query identity change logs (id_changes, validation_failures) to explore profile creation, merging, evictions, and validation errors

• rt-config-attributes

  Configure RT 2.0 attributes - single, list, counter, and batch attributes for real-time profile enrichment

• rt-config-events

  Configure RT 2.0 event tables and key events - define which streaming events to track and filter for real-time processing

• rt-config-id-stitching

  Configure RT 2.0 ID stitching - merge real-time profiles across different identifiers using stitching keys and primary keys

• rt-config-setup

  Initial RT 2.0 setup - check enablement status, initialize configuration, and verify prerequisites for parent segments

• rt-config

  Configure RT 2.0 (Real-Time Personalization) for parent segments including event tables, key events, RT attributes, and ID stitching using tdx ps rt commands or API

• rt-journey-activations

  Configure RT journey activations - webhooks, Salesforce, email, and other integrations for real-time event-triggered actions

• rt-journey-create

  Create RT 2.0 Journeys (event-triggered) that activate when specific events occur, sending real-time data to external systems

• rt-journey-monitor

  Monitor RT journeys - track activation success, debug failures, query activation logs, and optimize performance

• rt-personalization-validation

  Validates RT Personalization Entity payloads before creation to prevent common API errors. MUST be invoked proactively during rt-setup-personalization workflow at Step 9c before making the entity creation API call. Also use when encountering "Attribute payload can't be blank" errors or when reviewin

• rt-personalization

  Create RT 2.0 Personalization services AND entities that return real-time personalized API responses. Creates both the service configuration (via tdx ps pz) and the actual Personalization entity (via API) with payload definition. Use after RT configuration is complete when user wants to "create RT p

• rt-setup-personalization

  Complete workflow to set up RT 2.0 personalization from scratch - validates parent segment RT status, discovers event tables and attributes, configures RT infrastructure (events, attributes, ID stitching), creates personalization service, and deploys the personalization entity with payload. Use when

• rt-setup-triggers

  Complete workflow to set up RT 2.0 triggers (RT journeys) from scratch - validates parent segment RT status, discovers event tables and attributes, configures RT infrastructure (events, attributes, ID stitching), creates RT journey with activations. Use when user wants to "create realtime triggers"

• rt-triggers

  Create RT 2.0 Journeys (Real-Time Triggers) that activate in real-time when specific events occur, triggering activations to external systems via API

• td-javascript-sdk

  Expert assistance for importing data to Treasure Data using the JavaScript SDK. Use this skill when users need help with browser-based event tracking, page analytics, client-side data collection, or implementing TD's JS SDK for web applications.

• pytd

  Expert assistance for using pytd (Python SDK) to query and import data with Treasure Data. Use this skill when users need help with Python-based data analysis, querying Presto/Hive, importing pandas DataFrames, bulk data uploads, or integrating TD with Python analytical workflows.

• data-dictionary

  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 w

• schema-auto-tagger

  Automated schema tagging and resource classification for Treasure Data. Detects new tables/columns, analyzes metadata patterns, and suggests appropriate policy tags with confidence scoring. Reduces manual tagging effort by 80% while maintaining compliance standards (GDPR, CCPA, HIPAA, SOX).

• hive

  TD Hive SQL with TD-specific functions and Hive-only features (lateral view, explode, MAPJOIN hint). Use when Trino memory errors occur or for Hive-specific syntax.

• time-filtering

  Advanced td_interval patterns including offset dates (-1d/2025-10-01, -7d/-1d, 0M/now), td_interval_range for debugging, td_time_string for display formatting, and partition pruning optimization.

• trino-optimizer

  TD Trino performance optimization including CTAS (5x faster), UDP bucketing for ID lookups, magic comments for join distribution, REGEXP_LIKE vs LIKE, and approx functions.

• trino-to-hive-migration

  Convert Trino queries to Hive when memory errors occur. Covers syntax differences (td_time_string→TD_TIME_FORMAT, REGEXP_LIKE→RLIKE, ARRAY_AGG→COLLECT_LIST) and engine selection.

• trino

  TD Trino SQL with TD-specific functions (td_interval, td_time_range, td_time_string, td_sessionize). Use for time-based filtering, partition pruning, and TD query patterns.

• action-report

  YAML format reference for action reports rendered via preview_action_report. MUST be read before writing any action report YAML — defines the report structure (title, summary, actions array) and action item fields (as_is, to_be, reason, priority, category, impact) with incremental build workflow. Re

• graflow

  Build agentic workflow pipelines using Graflow (Python). Use when the user asks to create, edit, or debug a Graflow workflow, agentic pipeline, or automated multi-step business process. Covers @task decorator, workflow composition (>> sequential, | parallel), Studio Agent integration with the epheme

• grid-dashboard

  YAML format reference for grid dashboards rendered via preview_grid_dashboard. MUST be read before writing any dashboard YAML — defines the page structure, 6 cell types (kpi, gauge, scores, table, chart, markdown), grid layout rules, cell merging syntax, and incremental build workflow. Required by s

• react-dashboard

  Build interactive React dashboards in Treasure Studio using render_react. Use when the user explicitly asks for an interactive dashboard or custom React component beyond what render_chart supports.

• schedule-review

  Use when the user wants to review, validate, or check a scheduled task before enabling it. Runs two parallel sub-agent checks — structural validation and quality assessment. Triggers on "review this task", "check my scheduled task", "validate task", "is this task ready", etc.

• schedule-task

  Use when the user wants to create, set up, or configure a scheduled task in Treasure Studio. Covers TASK.md authoring, schedule.yaml configuration, script creation, and direct file-based task setup. Triggers on "create a scheduled task", "set up a recurring job", "automate daily report", "schedule a

• skill-creator

  Use when the user asks to create, write, build, or define a new skill, or when they want to save reusable instructions for future chat sessions. Covers SKILL.md authoring, description optimization, and writing patterns.

• web-search

  Use when performing web searches, extracting content from URLs, or researching topics requiring up-to-date information. Triggers on: "search", "look up", "find out", "what's the latest", "extract from URL", "fetch this page", "research", "check online".

• work

  Use when the user asks to create, update, list, or manage work items, goals, notes, guides, or references in a Treasure Studio workspace. Triggers on "create a task", "add a work item", "move to done", "show my tasks", "goal progress", "create a note", "what's next", or any workspace document manage

• activation

  Configures CDP activations for exporting segment/journey audiences to external destinations. Covers connection discovery, activation YAML structure, schedule options (daily/weekly/monthly/cron), column selection with masking, multi-table behavior data export (join up to 4 behavior tables via `behavi

• ai-decision

  Answers structured questions about text, images, or query result rows with `tdx ai decision` (LLM Proxy Decisions API) — yes/no probabilities (predicate), one of a fixed set of options (choice), or a rating on a scale (score). Use when the user wants to classify, label, score, tag, or triage reviews

• cas

  Manages Composable Audience Studio (CAS) zero-copy audiences using `tdx cas` commands — audiences that query customer Cloud Data Warehouses (Snowflake, Databricks, BigQuery) directly instead of copying data into Treasure Data. Covers audience/attribute/behavior YAML, the composable segment rule DSL

• connector-config

  Writes connector_config for segment/journey activations using `tdx connection schema <type>` to discover available fields. Use when configuring activations - always run schema command first to see connector-specific fields.

• engage

  Manage Treasure Engage email templates, campaigns, workspaces, and DAM media using `tdx engage` commands with YAML+HTML configs. Use when creating, editing, previewing, validating, or deploying email templates, email/push campaigns, managing workspaces, or locating Engage media assets — even if the

• foundry-agent-prompt

  Write effective system prompts for Treasure AI Foundry agents. Covers role definition, constraint specification, output formatting, tool usage instructions, and prompt structure patterns.

• foundry-agent-test

  Run automated tests for Treasure AI Foundry agents using `tdx agent test`. Covers test.yml format with user_input/criteria, single and multi-round tests, evaluation by judge agent, and criteria development workflow.

• foundry-agent

  Build Treasure AI Foundry agents using `tdx agent pull/push` with YAML/Markdown config. Covers agent.yml structure, tools (knowledge_base, agent, web_search, image_gen), @ref syntax, and knowledge bases. Use for TD AI Foundry agent development workflow.

• journey

  Load when the client wants to create, edit, or manage a CDP customer journey. Use for building journey YAML with segments, activations, and stage steps, modifying journey stages or flow logic (decision points, condition waits, A/B tests), or pushing journey changes to Treasure Data. Also load when t

• parent-segment-analysis
• parent-segment
• segment
• tdx-basic
• validate-journey
• validate-segment
• workflow
• template-skill
• agent-review
• portal-guide
• work-agent
• dbt
• digdag
• llm-workflow