td-skills

Use when the user asks to create, update, list, or manage work items, goals, notes, guides, or references in a Treasure Work 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 management. Also use when operating on files in goals/, items/, guides/, notes/, or references/ folders.

Manages CDP child segments using `tdx sg` commands with YAML rule configs. Covers Value/Behavior condition types, all operators (Equal, In, Between, TimeWithinPast, etc.), behavior aggregations with filters, and nested condition group restrictions. Use when creating audience segments with filtering rules, configuring behavior-based conditions, managing segment hierarchies, or exploring available fields with `tdx sg fields`.

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.

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.

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 on "check this image against brand", "review this ad image", "score this creative", "is this image on-brand", "fix brand violations on this image". For HTML/email/SMS content review, use the brand-compliance skill instead.

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

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.

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.

Executes tdx CLI commands for Treasure Data. Covers `tdx databases`, `tdx tables`, `tdx describe`, `tdx query`, `tdx auth setup`, context management with profiles/sessions, and output formats (JSON/TSV/table). Use when users need tdx command syntax, authentication setup, database/table exploration, schema inspection, or query execution.

Use when the user wants to create, configure, schedule, or run an agent in Treasure Work. Covers AGENTS.md authoring, the `agent_*` MCP tools, on-demand vs scheduled agents, lifecycle (draft → active → paused), and chat-based result inspection. Triggers on "create an agent", "set up an agent", "schedule a task", "set up a recurring job", "automate daily report", "cron job", "run X every weekday", etc.

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.

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 ephemeral-per-task session pattern (MCP tools, state via channels), subprocess for CLI tools, dynamic branching (next_task, next_iteration), HITL approval flows, and manifest.yml triggers and permissions.allow configuration. Also trigger on mentions of Graflow, agentic workflow, task graph, workflow.py, multi-step automation, CS health check, SDR sequence, or any request combining deterministic logic with AI decision points. For digdag/TD Workflow, see the digdag skill. For scheduled tasks with TASK.md, see the schedule-task skill.

Write .dig workflow files for Treasure Workflow. Covers creating new workflows (create_workflow MCP tool), importing existing workflows (register_workflow), digdag YAML syntax, td> operator, built-in variables, _parallel/_retry/_error directives, and TD platform constraints. Use when creating, editing, or deploying TD workflows. Also trigger on mentions of digdag, .dig files, td> operator, workflow scheduling, or any request to build a new data ETL pipeline on Treasure Data. For workflows with LLM processing or Slack/email notification, see the llm-workflow skill.

Use when the user wants to review, validate, or check an agent before activating it. Runs two parallel sub-agent checks — structural validation of `AGENTS.md` against the schema, and a quality assessment against the user's intent. Triggers on "review this agent", "check my agent", "validate agent", "is this agent ready", "review the agent before activating", etc.

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-original leaks. Trigger when the parent google-slides workflow reaches Step 9 / QA, or when the user asks "is this deck ready?" / "QA my deck" about a deck this agent itself just edited. Do NOT trigger for reviewing decks the agent did not create — without the Step 5 pre-fill snapshot the leak check silently degrades and the result is misleading.

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 Workspace context. Requires the Studio Google Slides + Google Drive MCP connectors. Do NOT use for PowerPoint (.pptx) creation (use the pptx skill), for editing without a template, or for authoring a new template (template authoring has its own skill).

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. Works by generating HTML/CSS slides (which LLMs excel at), rendering them in agent-browser for pixel-accurate DOM position extraction, and assembling the final PPTX with native PowerPoint charts, tables, and images via PptxGenJS. Includes bundled scripts for validation, DOM extraction, and PPTX assembly. Do NOT use this skill for editing existing PPTX files, converting other formats to PPTX, or extracting content from PPTX files.

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 ephemeral-per-task session pattern (MCP tools, state via channels), subprocess for CLI tools, dynamic branching (next_task, next_iteration), HITL approval flows, and manifest.yml triggers and permissions.allow configuration. Also trigger on mentions of Graflow, agentic workflow, task graph, workflow.py, multi-step automation, CS health check, SDR sequence, or any request combining deterministic logic with AI decision points. For digdag/TD Workflow, see the digdag skill. For scheduled tasks with TASK.md, see the schedule-task skill.

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

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.

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 task", "cron job", etc.

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 recommendations.

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. Required by seo-analysis and any skill that produces prioritized recommendations.

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 seo-analysis and any skill that produces visual data dashboards.

Use when building TD workflows that include LLM processing steps — data pipeline with LLM summarization, Slack/email notification, or any end-to-end automation. Covers patterns for query data, LLM analysis via TD LLM Proxy or TD Agent, and notification via Slack (Webhook/Bot API) or email. Also trigger on: LLM in workflow, workflow with Slack notification, automated report workflow, KPI summary pipeline, data-to-insight workflow.

Manages TD workflows using `tdx wf` commands. Covers project sync (pull/push/clone), running workflows, monitoring sessions/attempts, task timeline visualization, retry/kill operations, and secrets management. Use when users need to manage, monitor, or debug Treasure Workflow projects via tdx CLI.

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.

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

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

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: instagram ad image, generate ad image, image ad with text, ad visual, create instagram ad.

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.

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

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 one or more channels.

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 management. Also use when operating on files in goals/, items/, guides/, notes/, or references/ folders.

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.

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".

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.

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.

Manage Treasure Engage email templates and campaigns using `tdx engage` commands with YAML+HTML configs. Use when creating, editing, previewing, validating, or deploying email templates, email/push campaigns, managing workspaces, or any task involving Engage email content — even if the user only mentions "create an email" or "build an HTML email". Always write YAML definition files alongside HTML — never push raw HTML without a YAML wrapper.

Validation reference for CDP journey YAML. Lists all error codes, step type requirements, and flow control rules. Use alongside the **journey** skill when troubleshooting validation errors from `tdx journey validate` or `tdx journey push --dry-run`, checking step parameters, or understanding flow control constraints (merge, branching, convergence).