القائمة
Generates an HTML report summarizing dbt project work: decisions, SQL, queries, verifier results, and visual charts. Only load when explicitly requested.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Load when working with Xata Postgres branches: forking a branch, building or testing dbt models on a branch, wiring dbt to a branch's credentials, diffing two branches, or the pre-merge impact report. Covers create_xata_branch, delete_xata_branch, get_dbt_profile, xata_branch_diff, schema_diff_branches, and pgroll migrations.
Load at Step 1 before exploring the project. Covers output shape inference, incremental model handling, and what to trust in YML.
Use this skill before writing any SQL query. Covers: output shape inference (cardinality clues from the question), efficient schema exploration, iterative CTE-based query building, structured verification loop (row count, NULL audit, fan-out check, sample inspection), error recovery protocol, saving output to result.sql and result.csv, turn budget management, and common benchmark traps.
Populate the knowledge base from dbt project research. Proposes entries across all 6 categories at org, project, and connection scopes.
Load FIRST before any dbt project work. Covers the full 8-step dbt workflow: project scanning, skill loading, validation, macro discovery, research, technical spec, SQL writing, and verification. Also covers output shape inference, incremental model handling, and what to trust in YML.
Loaded at Step 2 for the full workflow. Covers column naming, type preservation, JOIN defaults, lookup joins, sibling models, materialization, packages, and filtering rules.
| name | write-report |
| description | Generates an HTML report summarizing dbt project work: decisions, SQL, queries, verifier results, and visual charts. Only load when explicitly requested. |
| disable-model-invocation | true |
Generate a single self-contained HTML file at <project_dir>/report.html that
gives the user complete confidence in what was built and why.
Load this skill ONLY after Step 8 verification is complete and all checks pass. This is the final step - it documents the work, it does not change any models.
Write the HTML file with these sections in order:
A colored status banner showing:
A table showing every major decision the agent made:
| # | Decision | Reasoning | Evidence |
|---|
Include decisions about:
Each row must cite the specific tool output, query result, or skill rule that informed the decision. No unsupported claims.
For each model created or edited:
<details> block)A collapsible section listing every query_database call the agent made:
Group by purpose: "Schema Discovery", "Data Profiling", "Verification".
Two subsections - Structure Verifier and Value Verifier:
Embed inline SVG or HTML/CSS charts (no external dependencies):
Row Count Waterfall: horizontal bar chart showing source rows → model rows, with JOIN multipliers/reductions annotated.
Column Coverage: a grid showing YML columns vs model SELECT columns (green = matched, red = missing, gray = extra).
NULL Heatmap: for each model column, show the % NULL as a colored cell (green = 0%, yellow = partial, red = 100%).
Use inline CSS and simple HTML elements (<div> with background-color,
width as percentage). Do NOT use JavaScript libraries - the report must
render in any browser with zero dependencies.
List the exact commands to rebuild from scratch:
dbt deps
dbt run --select <model1> <model2>
dbt test
.html file - all CSS inline in <style> blockfont-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif)#22c55e for PASS, #ef4444 for FAIL, #f59e0b for WARN, #6b7280 for SKIP<details><summary> HTML elementsborder-collapse: collapse with alternating row colorsquery_database.