skills

Create, update, or apply a Holistics dashboard theme (library/themes/) from any input: a brand name, website, screenshot, brand guidelines, explicit colors, or a mood description. Use when the user wants to theme, brand, restyle, or change a dashboard's look and feel. Typical phrasings: build a theme, match our brand, use these colors, make it dark, make it warm/minimal/premium/editorial, glow up this dashboard. Do NOT trigger for building a dashboard, authoring block content, or adding controls.

Create or refine a Holistics custom chart (CustomChartDef in library/custom_charts/) for a chart type the built-in viz can't cover. Use when the user wants to create a custom chart, convert a Vega/Vega-Lite spec into Holistics AML, or scaffold or refine a chart template — or when a dashboard needs a chart form with no built-in equivalent (heatmap matrix, sankey, waterfall, box plot, ...). Typical phrasings: create a custom chart for X, turn this Vega-Lite spec into a Holistics chart, we need a sankey of X. Do NOT trigger for a standard built-in chart or a dynamic content block.

Create, update, or apply a Holistics dashboard theme (library/themes/) from any input: a brand name, website, screenshot, brand guidelines, explicit colors, or a mood description. Use when the user wants to theme, brand, restyle, or change a dashboard's look and feel. Typical phrasings: build a theme, match our brand, use these colors, make it dark, make it warm/minimal/premium/editorial, glow up this dashboard. Do NOT trigger for building a dashboard, authoring block content, or adding controls.

Review a past conversation between a Holistics data-analyst AI agent and a user, then produce insight report with three sections (`Summary`, `Recap`, and `Suggestions`). Use this whenever the user wants to assess, grade, debrief, or critique how the agent performed on a chat, including phrasings like " this conversation", "how did the agent do", "grade this chat", "what could the AI have done better", or "what context should I add to improve the agent", even if they don't say the word "review".

Use this whenever working in a (Holistics) AMQL project (i.e. with AML files). It guides you to set up and review the AMQL development environment and tooling so that the development can be done accurately and efficiently. Tooling includes CLI, MCP, code synchronization, etc.

Address suggestions in a past conversation's insight by performing each suggestion's actionable fix. Use when the user asks to implement, apply, address, or act on the suggestions from a conversation insight. Requires a conversation ID. Do NOT use this to generate a new insight.

Search Holistics documentation to answer questions about features, syntax, or concepts. Use this whenever the user asks how something works in Holistics, needs documentation references, or the answer requires looking up Holistics knowledge rather than relying on assumptions.

Write and edit AML/AQL code for Holistics models, datasets, dashboards, and metrics. Use this whenever the user wants to create or modify a model, dataset, dashboard page, AQL metric, or any file in an AMQL project.

Search Holistics documentation to answer questions about features, syntax, or concepts. Use this whenever the user asks how something works in Holistics, needs documentation references, or the answer requires looking up Holistics knowledge rather than relying on assumptions.

Convert an agent skill written for another runtime (Claude `SKILL.md`, OpenAI/Codex skill, raw system prompt) into a Holistics AML `Skill` block — or the reverse direction. Use whenever the user wants to migrate, port, or translate a skill across formats, including phrasings like "convert this Claude skill to AML", "port this OpenAI skill to Holistics", "turn this SKILL.md into an AML Skill", "translate this AML skill back to Claude", or "migrate this agent skill".

Author a Holistics skill. Use whenever the user wants to write, edit, or refine a skill that gives Holistics AI specific knowledge, workflows, or guardrails — including phrasings like "add a skill for X", "create a workspace glossary skill", "turn this prompt into a reusable skill", or "make this Holistics AI smarter about Y". For converting a skill written for another runtime (Claude, OpenAI/Codex) into AML, use `convert-agent-skill-to-holistics` instead.

Convert an agent skill written for another runtime (Claude `SKILL.md`, OpenAI/Codex skill, raw system prompt) into a Holistics AML `Skill` block — or the reverse direction. Use whenever the user wants to migrate, port, or translate a skill across formats, including phrasings like "convert this Claude skill to AML", "port this OpenAI skill to Holistics", "turn this SKILL.md into an AML Skill", "translate this AML skill back to Claude", or "migrate this agent skill".

Author a Holistics skill. Use whenever the user wants to write, edit, or refine a skill that gives Holistics AI specific knowledge, workflows, or guardrails — including phrasings like "add a skill for X", "create a workspace glossary skill", "turn this prompt into a reusable skill", or "make this Holistics AI smarter about Y". For converting a skill written for another runtime (Claude, OpenAI/Codex) into AML, use `convert-agent-skill-to-holistics` instead.

Migrate a Power BI semantic model (TMDL + DAX) and reports to Holistics AMQL assets (AML models, datasets, dashboards, AQL/SQL metrics). Use this when converting a .pbix/.pbip project, translating DAX measures, mapping TMDL tables and relationships to Holistics models, or rebuilding Power BI reports as Canvas Dashboards.

Use this skill to set up Holistics CLI and enable useful tools such as `holistics aml validate`, `holistics sync-code`, and `holistics mcp` tools such as `holistics mcp execute_aql`, `holistics mcp list_datasets`

Use this skill to set up or review Holistics MCP connection and enable useful tools such as `search_docs`, `execute_aql`, and `generate_viz`

Evaluate the results of an A/B test — lift on the primary metric, statistical significance, sample-ratio sanity check, and guardrail metrics. Use when the user asks whether an experiment moved a metric.

Compute customer lifetime value (LTV), realized or predicted, by cohort or segment, with optional gross-margin and discount-rate adjustments. Use when the user asks "what is a customer worth", wants to size a CAC budget, or compares channels by long-term value.

Compute the SaaS unit-economics quartet — CAC, LTV, LTV:CAC ratio, and CAC payback period — and assess whether the business acquires customers profitably. Use when evaluating growth health or comparing acquisition channels.

Split users, customers, orders, or other entities into meaningful subgroups (RFM, behavioral, value-based, lifecycle) and analyze each subgroup separately. Use when an aggregate metric likely hides important variation across cohorts.

Use this skill to set up Holistics MCP and enable useful tools such as `search_docs`, `execute_aql`, and `generate_viz`

Use Holistics analytics skills and tooling to work with Holistics analytics more efficiently and effectively. Tooling includes MCP tools such as `generate_viz` and `search_docs`. Use this whenever the user is trying to perform analytics using their Holistics platform.

Search and use visualizations that already exist in the project to provide fast and curated data answers.

Write and run AQL (Analytic Query Language) queries to answer data questions. Use this whenever the user asks for data, wants to query a dataset, needs to filter/aggregate/join data, or asks about metrics and dimensions in Holistics.

Search and use visualizations that already exist in the project to provide fast and curated data answers.

Write and run AQL (Analytic Query Language) queries to answer data questions. Use this whenever the user asks for data, wants to query a dataset, needs to filter/aggregate/join data, or asks about metrics and dimensions in Holistics.

Search and use visualizations that already exist in the project to provide fast and curated data answers.

Explain AQL queries and their results, and provide data insights. Use this whenever the user asks what a query does, wants to understand results, or needs to dig deeper into why a metric changed.

Create charts, tables, and visualizations from queries. Use this whenever the user wants to see data as a chart or formatted table, or asks for a visualization.

Explain AQL queries and their results, and provide data insights. Use this whenever the user asks what a query does, wants to understand results, or needs to dig deeper into why a metric changed.

Create charts, tables, and visualizations from queries. Use this whenever the user wants to see data as a chart or formatted table, or asks for a visualization.