Data Exploration
dbt-labs/dbt-charts/src/dbt_charts/ai/skills/data-exploration
analysisOfficial
Official Provider SkillView repo
Explore available sources, schemas, tables, columns, relationships, and data shape before writing dashboard YAML or answering analyst questions. Use when the user asks what data exists, where to find a metric/dimension, how tables relate, or which columns are available. Do NOT use for dashboard design decisions (use {{ s_skill_name_design_board }}) or error diagnosis after a failed render (use {{ s_skill_name_troubleshooting }}).
Files1 files
SKILL.md97 lines
Loading editor…
Install
RecommendedOne command — your agent picks it up automatically.
Select an AI agent above to see the install command.
or
Manual Install
More stepsDownload the file and paste it into your agent's system prompt.
Skill details
Versionv1.0.0
Authordbt Labs
Categoryanalysis
Skill IDdbt-labs/dbt-charts/src/dbt_charts/ai/skills/data-exploration
Related skills
Analyst RunbookThe analyst process wrapped around anything you build: triage the request, reuse existing work, pick the response shape, verify the answer, then deliver it with a written read — observations plus where to look next. Use at the start of an analytical request ("show me…", "why did X change") and again when handing the work back. Not for chart-type or layout decisions (use {{ s_skill_name_design_board }}).Before After ComparisonPattern for placing two metric series on the same axis to compare baseline vs current, plan vs actual, or A vs B. Use when the question is "how does current compare to baseline?" for the same set of categories or time periods. Triggers on: 'compare', 'baseline vs current', 'plan vs actual', 'before after', 'A/B', 'target vs actual', 'layered bars'. Both series share the same x-axis encoding. Do NOT use for time-series trend (use time-series-trend). Do NOT use for more than 3 series (chart becomeBoard BuildBuild-test-iterate workflow for dbt charts boards and reports: edit board YAML, add charts, write parameterized queries, duplicate an existing board. Use for 'build a dashboard', 'add a chart', 'duplicate this dashboard'. Do NOT use for errors after something breaks ({{ s_skill_name_troubleshooting }}) or for chart-type and layout choices ({{ s_skill_name_design_board }}).Board DesignDesign principles for at-a-glance dbt charts boards: chart selection, information hierarchy, layout, color, dashboard vs report. Use for 'what chart type', 'how should I lay this out', 'dashboard design'. Do NOT use for narrative analyses ({{ s_skill_name_design_report }}) or the build-test-iterate cycle ({{ s_skill_name_build }}).Board Pack ScaffoldingExperimental internal workflow for evaluating multi-dashboard scaffolding: propose a folder structure, review with the user, then apply through the Python agent API. Use only when explicitly evaluating pack-level scaffolding for a data source or project. Do NOT use for a single-dashboard request (use {{ s_skill_name_build }}). Do NOT use for normal CLI guidance, chart edits, or bug fixes in one board file.Board ReplicateReproduce a dashboard the user supplies as a screenshot, image, or export — its structure and data, in dbt charts' own styling. Use for 'replicate', 'recreate', 'rebuild this in dbt charts', 'migrate from Looker', or when an image of a dashboard is attached. Do NOT use for building from scratch, or for copying a board already in this project ({{ s_skill_name_build }}).