Not in the top 1,000 by GitHub stars
Kemetra/Seshat-BI
Readiness system that lets AI agents build your BI pipeline but never approve it -- evidence-gated source profiling, medallion mappings, metric contracts, and Power BI delivery. Offline demo in 60 seconds: uvx --from seshat-bi seshat demo init
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
distribution/bundle-templates/shared/skills/bi-analyst-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/bi-bigdata-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/bi-dax-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/bi-python-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/bi-sql-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/dagster-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/dbt-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/pbi-mcp-doctor/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/powerbi-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/retail-kpi-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
distribution/bundle-templates/shared/skills/seshat-bi/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/knowledge/bi-analyst-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/knowledge/bi-bigdata-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/knowledge/bi-dax-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/knowledge/bi-python-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/knowledge/bi-sql-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/knowledge/retail-kpi-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/bi-analyst-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/bi-bigdata-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/bi-dax-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/bi-python-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/bi-sql-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/business-knowledge-interview/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/dagster-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/dbt-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/first-hour-compass/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/kpi-contract-builder/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/pbi-mcp-doctor/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/powerbi-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/retail-build-warehouse/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/retail-discover-portfolio/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/retail-govern/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/retail-kpi-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/retail-onboard-table/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/retail-orchestrate/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/retail-validate/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/seshat-bi/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/seshat-studio/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/claude-code/seshat-bi/skills/source-mapping/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/knowledge/bi-analyst-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/knowledge/bi-bigdata-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/knowledge/bi-dax-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/knowledge/bi-python-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/knowledge/bi-sql-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/knowledge/retail-kpi-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/bi-analyst-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/bi-bigdata-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/bi-dax-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/bi-python-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/bi-sql-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/business-knowledge-interview/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/dagster-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/dbt-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/first-hour-compass/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/kpi-contract-builder/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/pbi-mcp-doctor/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/powerbi-workflows/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/retail-build-warehouse/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/retail-discover-portfolio/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/retail-govern/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/retail-kpi-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/retail-onboard-table/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/retail-orchestrate/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/retail-validate/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/seshat-bi/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/seshat-studio/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
integrations/codex/seshat-bi/skills/source-mapping/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
skills/bi-analyst-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
skills/bi-bigdata-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
skills/bi-dax-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
skills/bi-python-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
skills/bi-sql-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
skills/retail-kpi-knowledge/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
tests/unit/fixtures/capability_inventory/good/.claude/skills/fake-skill/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
tests/unit/fixtures/capability_inventory/orphan/.claude/skills/bare-skill-no-frontmatter/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
tests/unit/fixtures/capability_inventory/orphan/.claude/skills/fake-skill/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
tests/unit/fixtures/capability_inventory/unlisted/.claude/skills/fake-skill/SKILL.md
Week of Oct 26, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6266e304556a → 6266e304556a
View on GitHubAdd to my skills
Verified commit 6266e304556a72b75d951b9433fd833481c61233
git clone --filter=blob:none --no-checkout https://github.com/Kemetra/Seshat-BI.git .hotskills/kemetra-seshat-bi && git -C .hotskills/kemetra-seshat-bi checkout --detach 6266e304556a72b75d951b9433fd833481c61233
# Copy each selected skill directory from .hotskills/kemetra-seshat-bi into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/Kemetra/Seshat-BI.git .hotskills/kemetra-seshat-bi && git -C .hotskills/kemetra-seshat-bi checkout --detach 6266e304556a72b75d951b9433fd833481c61233
# Copy each selected skill directory from .hotskills/kemetra-seshat-bi into .agents/skills/<skill-name>/2GitHub stars
0stars in 7 days
77skills in this repository
1commit in 30 days
Heat
1.2- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- bi-analyst-knowledge
distribution/bundle-templates/shared/skills/bi-analyst-knowledge - bi-bigdata-knowledge
distribution/bundle-templates/shared/skills/bi-bigdata-knowledge - bi-dax-knowledge
distribution/bundle-templates/shared/skills/bi-dax-knowledge - bi-python-knowledge
distribution/bundle-templates/shared/skills/bi-python-knowledge - bi-sql-knowledge
distribution/bundle-templates/shared/skills/bi-sql-knowledge - dagster-workflows
distribution/bundle-templates/shared/skills/dagster-workflows - dbt-workflows
distribution/bundle-templates/shared/skills/dbt-workflows - pbi-mcp-doctor
distribution/bundle-templates/shared/skills/pbi-mcp-doctor - powerbi-workflows
distribution/bundle-templates/shared/skills/powerbi-workflows - retail-kpi-knowledge
distribution/bundle-templates/shared/skills/retail-kpi-knowledge - seshat-bi
distribution/bundle-templates/shared/skills/seshat-bi - bi-analyst-knowledge
integrations/claude-code/seshat-bi/knowledge/bi-analyst-knowledge - bi-bigdata-knowledge
integrations/claude-code/seshat-bi/knowledge/bi-bigdata-knowledge - bi-dax-knowledge
integrations/claude-code/seshat-bi/knowledge/bi-dax-knowledge - bi-python-knowledge
integrations/claude-code/seshat-bi/knowledge/bi-python-knowledge - bi-sql-knowledge
integrations/claude-code/seshat-bi/knowledge/bi-sql-knowledge - retail-kpi-knowledge
integrations/claude-code/seshat-bi/knowledge/retail-kpi-knowledge - bi-analyst-knowledge
integrations/claude-code/seshat-bi/skills/bi-analyst-knowledge - bi-bigdata-knowledge
integrations/claude-code/seshat-bi/skills/bi-bigdata-knowledge - bi-dax-knowledge
integrations/claude-code/seshat-bi/skills/bi-dax-knowledge - bi-python-knowledge
integrations/claude-code/seshat-bi/skills/bi-python-knowledge - bi-sql-knowledge
integrations/claude-code/seshat-bi/skills/bi-sql-knowledge - business-knowledge-interview
integrations/claude-code/seshat-bi/skills/business-knowledge-interview - dagster-workflows
integrations/claude-code/seshat-bi/skills/dagster-workflows - dbt-workflows
integrations/claude-code/seshat-bi/skills/dbt-workflows - first-hour-compass
integrations/claude-code/seshat-bi/skills/first-hour-compass - kpi-contract-builder
integrations/claude-code/seshat-bi/skills/kpi-contract-builder - pbi-mcp-doctor
integrations/claude-code/seshat-bi/skills/pbi-mcp-doctor - powerbi-workflows
integrations/claude-code/seshat-bi/skills/powerbi-workflows - retail-build-warehouse
integrations/claude-code/seshat-bi/skills/retail-build-warehouse - retail-discover-portfolio
integrations/claude-code/seshat-bi/skills/retail-discover-portfolio - retail-govern
integrations/claude-code/seshat-bi/skills/retail-govern - retail-kpi-knowledge
integrations/claude-code/seshat-bi/skills/retail-kpi-knowledge - retail-onboard-table
integrations/claude-code/seshat-bi/skills/retail-onboard-table - retail-orchestrate
integrations/claude-code/seshat-bi/skills/retail-orchestrate - retail-validate
integrations/claude-code/seshat-bi/skills/retail-validate - seshat-bi
integrations/claude-code/seshat-bi/skills/seshat-bi - seshat-studio
integrations/claude-code/seshat-bi/skills/seshat-studio - source-mapping
integrations/claude-code/seshat-bi/skills/source-mapping - bi-analyst-knowledge
integrations/codex/seshat-bi/knowledge/bi-analyst-knowledge - bi-bigdata-knowledge
integrations/codex/seshat-bi/knowledge/bi-bigdata-knowledge - bi-dax-knowledge
integrations/codex/seshat-bi/knowledge/bi-dax-knowledge - bi-python-knowledge
integrations/codex/seshat-bi/knowledge/bi-python-knowledge - bi-sql-knowledge
integrations/codex/seshat-bi/knowledge/bi-sql-knowledge - retail-kpi-knowledge
integrations/codex/seshat-bi/knowledge/retail-kpi-knowledge - bi-analyst-knowledge
integrations/codex/seshat-bi/skills/bi-analyst-knowledge - bi-bigdata-knowledge
integrations/codex/seshat-bi/skills/bi-bigdata-knowledge - bi-dax-knowledge
integrations/codex/seshat-bi/skills/bi-dax-knowledge - bi-python-knowledge
integrations/codex/seshat-bi/skills/bi-python-knowledge - bi-sql-knowledge
integrations/codex/seshat-bi/skills/bi-sql-knowledge - business-knowledge-interview
integrations/codex/seshat-bi/skills/business-knowledge-interview - dagster-workflows
integrations/codex/seshat-bi/skills/dagster-workflows - dbt-workflows
integrations/codex/seshat-bi/skills/dbt-workflows - first-hour-compass
integrations/codex/seshat-bi/skills/first-hour-compass - kpi-contract-builder
integrations/codex/seshat-bi/skills/kpi-contract-builder - pbi-mcp-doctor
integrations/codex/seshat-bi/skills/pbi-mcp-doctor - powerbi-workflows
integrations/codex/seshat-bi/skills/powerbi-workflows - retail-build-warehouse
integrations/codex/seshat-bi/skills/retail-build-warehouse - retail-discover-portfolio
integrations/codex/seshat-bi/skills/retail-discover-portfolio - retail-govern
integrations/codex/seshat-bi/skills/retail-govern - retail-kpi-knowledge
integrations/codex/seshat-bi/skills/retail-kpi-knowledge - retail-onboard-table
integrations/codex/seshat-bi/skills/retail-onboard-table - retail-orchestrate
integrations/codex/seshat-bi/skills/retail-orchestrate - retail-validate
integrations/codex/seshat-bi/skills/retail-validate - seshat-bi
integrations/codex/seshat-bi/skills/seshat-bi - seshat-studio
integrations/codex/seshat-bi/skills/seshat-studio - source-mapping
integrations/codex/seshat-bi/skills/source-mapping - bi-analyst-knowledge
skills/bi-analyst-knowledge - bi-bigdata-knowledge
skills/bi-bigdata-knowledge - bi-dax-knowledge
skills/bi-dax-knowledge - bi-python-knowledge
skills/bi-python-knowledge - bi-sql-knowledge
skills/bi-sql-knowledge - retail-kpi-knowledge
skills/retail-kpi-knowledge - fake-skill
tests/unit/fixtures/capability_inventory/good/.claude/skills/fake-skill - bare-skill-no-frontmatter
tests/unit/fixtures/capability_inventory/orphan/.claude/skills/bare-skill-no-frontmatter - fake-skill
tests/unit/fixtures/capability_inventory/orphan/.claude/skills/fake-skill - fake-skill
tests/unit/fixtures/capability_inventory/unlisted/.claude/skills/fake-skill
How it works
bi-analyst-knowledge
When your agent uses it
Use Seshat's public analyst-judgment knowledge to derive decision-questions, choose an analytical framing, and order a story from approved metric contracts and a committed source-profile.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
109 tokensWhen the skill is activated
Reference documents
43,039 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../../../../.claude-plugin/marketplace.jsonasset508 bytes../../../../../.claude-plugin/marketplace.jsonasset508 bytes../../../claude/.claude-plugin/plugin.jsonasset417 bytes../../../claude/commands/auto.mddoc816 bytes../../../claude/commands/check.mddoc271 bytes../../../claude/commands/dagster-doctor.mddoc767 bytes../../../claude/commands/dagster-evidence.mddoc699 bytes../../../claude/commands/dagster-run.mddoc1,454 bytes../../../claude/commands/dagster-run.mddoc1,454 bytes../../../claude/commands/dbt-build.mddoc389 bytes../../../claude/commands/dbt-doctor.mddoc286 bytes../../../claude/commands/dbt-plan.mddoc388 bytes../../../claude/commands/dbt-review.mddoc443 bytes../../../claude/commands/doctor.mddoc447 bytes../../../claude/commands/help.mddoc2,724 bytes../../../claude/commands/init.mddoc371 bytes../../../claude/commands/next.mddoc281 bytes../../../claude/commands/powerbi-adopt.mddoc635 bytes../../../claude/commands/powerbi-design.mddoc835 bytes../../../claude/commands/powerbi-format.mddoc555 bytes../../../claude/commands/powerbi-review.mddoc846 bytes../../../claude/commands/powerbi-theme.mddoc735 bytes../../../claude/commands/review.mddoc225 bytes../../../claude/commands/seshat-check.mddoc396 bytes../../../claude/commands/seshat-init.mddoc492 bytes../../../claude/commands/seshat-next.mddoc411 bytes../../../claude/commands/seshat-review.mddoc352 bytes../../../claude/commands/status.mddoc473 bytesSKILL.mdcore477 bytes../../../../../integrations/claude-code/seshat-bi/.claude-plugin/plugin.jsonasset411 bytes../../../../../integrations/claude-code/seshat-bi/commands/auto.mddoc816 bytes../../../../../integrations/claude-code/seshat-bi/commands/check.mddoc271 bytes../../../../../integrations/claude-code/seshat-bi/commands/dagster-doctor.mddoc767 bytes../../../../../integrations/claude-code/seshat-bi/commands/dagster-evidence.mddoc699 bytes../../../../../integrations/claude-code/seshat-bi/commands/dagster-run.mddoc1,454 bytes../../../../../integrations/claude-code/seshat-bi/commands/dagster-run.mddoc1,454 bytes../../../../../integrations/claude-code/seshat-bi/commands/dbt-build.mddoc389 bytes../../../../../integrations/claude-code/seshat-bi/commands/dbt-doctor.mddoc286 bytes../../../../../integrations/claude-code/seshat-bi/commands/dbt-plan.mddoc388 bytes../../../../../integrations/claude-code/seshat-bi/commands/dbt-review.mddoc443 bytes../../../../../integrations/claude-code/seshat-bi/commands/doctor.mddoc447 bytes../../../../../integrations/claude-code/seshat-bi/commands/help.mddoc2,724 bytes../../../../../integrations/claude-code/seshat-bi/commands/init.mddoc371 bytes../../../../../integrations/claude-code/seshat-bi/commands/next.mddoc281 bytes../../../../../integrations/claude-code/seshat-bi/commands/powerbi-adopt.mddoc635 bytes../../../../../integrations/claude-code/seshat-bi/commands/powerbi-design.mddoc835 bytes../../../../../integrations/claude-code/seshat-bi/commands/powerbi-format.mddoc555 bytes../../../../../integrations/claude-code/seshat-bi/commands/powerbi-review.mddoc846 bytes../../../../../integrations/claude-code/seshat-bi/commands/powerbi-theme.mddoc735 bytes../../../../../integrations/claude-code/seshat-bi/commands/review.mddoc225 bytes../../../../../integrations/claude-code/seshat-bi/commands/seshat-check.mddoc396 bytes../../../../../integrations/claude-code/seshat-bi/commands/seshat-init.mddoc492 bytes../../../../../integrations/claude-code/seshat-bi/commands/seshat-next.mddoc411 bytes../../../../../integrations/claude-code/seshat-bi/commands/seshat-review.mddoc352 bytes../../../../../integrations/claude-code/seshat-bi/commands/status.mddoc473 bytes../../../../../integrations/claude-code/seshat-bi/mcp-servers.jsonasset106 bytes../../../../../integrations/claude-code/seshat-bi/skills/bi-analyst-knowledge/SKILL.mddoc477 bytes../../../../../integrations/claude-code/seshat-bi/skills/bi-bigdata-knowledge/SKILL.mddoc427 bytes../../../../../integrations/claude-code/seshat-bi/skills/bi-dax-knowledge/SKILL.mddoc378 bytes../../../../../integrations/claude-code/seshat-bi/skills/bi-python-knowledge/SKILL.mddoc419 bytes../../../../../integrations/claude-code/seshat-bi/skills/bi-sql-knowledge/SKILL.mddoc390 bytes../../../../../integrations/claude-code/seshat-bi/skills/business-knowledge-interview/SKILL.mddoc5,710 bytes../../../../../integrations/claude-code/seshat-bi/skills/dagster-workflows/SKILL.mddoc6,021 bytes../../../../../integrations/claude-code/seshat-bi/skills/dbt-workflows/SKILL.mddoc8,060 bytes../../../../../integrations/claude-code/seshat-bi/skills/first-hour-compass/SKILL.mddoc7,278 bytes../../../../../integrations/claude-code/seshat-bi/skills/kpi-contract-builder/SKILL.mddoc6,727 bytes../../../../../integrations/claude-code/seshat-bi/skills/kpi-contract-builder/walkthrough.mddoc3,103 bytes../../../../../integrations/claude-code/seshat-bi/skills/pbi-mcp-doctor/SKILL.mddoc6,168 bytes../../../../../integrations/claude-code/seshat-bi/skills/powerbi-workflows/SKILL.mddoc10,678 bytes../../../../../integrations/claude-code/seshat-bi/skills/retail-build-warehouse/SKILL.mddoc10,297 bytes../../../../../integrations/claude-code/seshat-bi/skills/retail-discover-portfolio/SKILL.mddoc6,543 bytes../../../../../integrations/claude-code/seshat-bi/skills/retail-govern/SKILL.mddoc16,927 bytes../../../../../integrations/claude-code/seshat-bi/skills/retail-kpi-knowledge/SKILL.mddoc476 bytes../../../../../integrations/claude-code/seshat-bi/skills/retail-onboard-table/SKILL.mddoc9,948 bytes../../../../../integrations/claude-code/seshat-bi/skills/retail-orchestrate/SKILL.mddoc10,848 bytes../../../../../integrations/claude-code/seshat-bi/skills/retail-validate/SKILL.mddoc4,871 bytes../../../../../integrations/claude-code/seshat-bi/skills/seshat-bi/SKILL.mddoc11,167 bytes../../../../../integrations/claude-code/seshat-bi/skills/seshat-studio/SKILL.mddoc7,442 bytes../../../../../integrations/claude-code/seshat-bi/skills/source-mapping/SKILL.mddoc10,729 bytes
Read SKILL.md
# BI Analyst knowledge
Open `../../knowledge/bi-analyst-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Never define metric meaning or invent a
number here; an unanswerable question is a `[GAP]`, not a guess.bi-bigdata-knowledge
When your agent uses it
Use Seshat's public big-data knowledge for distributed aggregation, partitioning, joins, skew, idempotency, reconciliation, performance, and cost reasoning.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
92 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore427 bytes
Read SKILL.md
# BI big-data knowledge
Open `../../knowledge/bi-bigdata-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Do not select a distributed engine unless
scale and operational evidence justify it.bi-dax-knowledge
When your agent uses it
Use Seshat's public DAX knowledge for metric contracts, evaluation context, measure review, performance reasoning, and semantic-model prerequisites.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
82 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore378 bytes
Read SKILL.md
# BI DAX knowledge
Open `../../knowledge/bi-dax-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Do not design visuals or invent business metric
meaning.bi-python-knowledge
When your agent uses it
Use Seshat's public Python knowledge for governed single-node source preparation, cleaning, grain, and aggregation reasoning.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
84 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore419 bytesSKILL.mdcore419 bytes
Read SKILL.md
# BI Python knowledge
Open `../../knowledge/bi-python-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Do not execute against live data without the user's
explicit in-scope request and required connection boundary.bi-sql-knowledge
When your agent uses it
Use Seshat's public SQL knowledge for source grain, joins, aggregation, validation, reconciliation, and transformation reasoning without executing a database.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
83 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore390 bytesSKILL.mdcore390 bytesSKILL.mdcore390 bytes
Read SKILL.md
# BI SQL knowledge
Open `../../knowledge/bi-sql-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Ground the row grain and never infer missing source
facts.dagster-workflows
When your agent uses it
Route Dagster intent to Seshat's governed medallion workflow or the official Dagster competence owner without bypassing readiness, approvals, or evidence.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,386 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intent ownership
- Fixed workflow
- Hard boundaries
- Exit meanings
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore6,021 bytes
Read SKILL.md
# Governed Dagster workflows
Read `../../portable-operating-contract.md` before acting. For a governed
Seshat medallion run, use only the installed `seshat dagster` helpers; never
invoke `dagster` directly against the orchestration project and never bypass
the gate readers, the closed-argv runner, or the redaction layer. Dagster RUNS
already-approved steps; the gate exit code and the named human decide whether
a stage passed.
## Intent ownership
| User intent | Seshat pre-gate | Execution owner | Seshat afterward |
|---|---|---|---|
| Decide whether orchestration fits the BI workflow | Readiness state and orchestration assessment | Seshat selection policy | State one truthful next action |dbt-workflows
When your agent uses it
Route dbt intent to Seshat's governed shadow workflow or the official dbt Labs competence and execution owner, without bypassing readiness or evidence.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,903 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intent ownership
- Fixed workflow
- The `meta.seshat` model contract
- Hard boundaries
- Exit meanings
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytes
Read SKILL.md
# Governed dbt workflows
Read `../../portable-operating-contract.md` before acting. For a governed
Seshat shadow workflow, use only the installed `seshat dbt` helpers; never
bypass their fixed selector, target, profile, lock, redaction, or artifact
checks with raw dbt commands.
## Intent ownership
| User intent | Seshat pre-gate | Execution owner | Seshat afterward |
|---|---|---|---|
| Decide whether dbt fits the current BI stage | Readiness and approved-mapping context | Seshat selection policy | State one truthful next action |
| Scaffold governed shadow models | Approved committed source map | Seshat source-map-derived scaffold | Validate citations and the `meta.seshat` contract |
| Governed compile, build, test, or parity | Mapping Ready, exact selector, shadow target, and accepted immutable plan | dbt Core through `seshat dbt` | Normalize artifacts into derived evidence, blockers, and parity findings |pbi-mcp-doctor
When your agent uses it
Use when a user asks whether or how to wire Microsoft's official Power BI MCP servers into a Seshat BI workspace: run the read-only environment doctor, map a task to the governed Power BI surface (including the official report-authoring skill), generate a safe read-only config template, or run the mocked read-only preflight.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,441 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Fixed workflow
- The recommendation matrix in plain language
- How to read the advisory records
- What this family will NEVER do
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore6,168 bytesSKILL.mdcore6,168 bytes
Read SKILL.md
# Power BI MCP doctor (read-only)
Read `../../portable-operating-contract.md` before acting. Use only the
installed `seshat pbi-mcp` verbs; never launch an MCP server directly, never
edit `.mcp.json` by hand when the generator can produce it, and never treat
any output of this family as an approval. F016 (the Power BI execution
adapter) is PARKED: no mutation path exists anywhere in this family.
## Fixed workflow
1. Map the user's task to the governed surface, read-only:
`seshat pbi-mcp doctor --repo . --intent <task> [--target <table>] [--harness <claude-code|codex>] [--json] [--write-advisory]`
powerbi-workflows
When your agent uses it
Route guarded Power BI work -- design, native report authoring, semantic-model operations, published queries, QA, bounded formatting, and PBIP adoption -- to the correct Seshat or official Microsoft surface under Seshat BI's gates.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,426 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- One front door, explicit execution owners
- Design (dashboards and pages)
- Review and QA
- Reopening Desktop after an external edit
- Theme and backgrounds
- Formatting and geometry
- Semantic measures (handoff)
- Existing PBIP adoption
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore10,678 bytes
Read SKILL.md
# Power BI workflows
Read `../../portable-operating-contract.md` before acting. These routes never
replace readiness gates: no invented metric, measure, KPI, or DAX meaning; no
numeric readiness/confidence score; no self-granted approval; no
dashboard-ready claim without committed evidence.
## One front door, explicit execution owners
This skill is the broad Power BI front door. It owns intent classification and
Seshat's pre/post gates; it does not reproduce Microsoft execution behavior.
For execution-shaped requests, use `seshat pbi-mcp doctor` as the canonical
machine-checkable selector even when the selected owner is an official skill
rather than an MCP server.retail-kpi-knowledge
When your agent uses it
Use Seshat's public retail KPI knowledge to define governed metric meaning, additivity, grain, required fields, ambiguity decisions, contracts, and handoffs before implementation.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
104 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore476 bytes
Read SKILL.md
# Retail KPI knowledge
Open `../../knowledge/retail-kpi-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Undefined VAT, returns, cost, same-store, or
snapshot policy is a named-human decision, never an agent default.seshat-bi
When your agent uses it
Route a BI project through Seshat BI's governed seven-stage readiness flow. Use when a user asks to inspect a retail source, initialize a Seshat project, find the truthful next action, validate readiness evidence, or stop at the correct human approval gate.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
2,702 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Discovering the surface (no name memorization needed)
- Agent-driven loop (programmatic automation)
- Existing PBIP projects
- Resetting / re-running a project
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytes
Read SKILL.md
# Seshat BI
Read `../../portable-operating-contract.md` before acting. Inspect the current
workspace and use installed `seshat` commands when available. If the workspace
has no `AGENTS.md`, this skill's portable operating contract still applies.
For subject reasoning, load only the relevant bundled skill:
- SQL and source grain: `bi-sql-knowledge`
- DAX and semantic measures: `bi-dax-knowledge`
- Python/dataframe preparation: `bi-python-knowledge`
- distributed data: `bi-bigdata-knowledge`
- retail KPI meaning and contracts: `retail-kpi-knowledge`
- decision-questions, framing, and story order from approved metrics:bi-analyst-knowledge
When your agent uses it
Analyst-judgment layer for Seshat BI Stage-6 design. Use when turning approved metric contracts + a committed source-profile into a decision-driven report: deriving ranked decision-questions, choosing an analytical framing (trend/anomaly, period variance, contribution & mix-shift, concentration/Pareto, rate decomposition, segment behavior, benchmark/threshold, signal-vs-noise statistical guardrails), and ordering pages into a story (overview, what changed, why/where, action), building grounded diagnostic question trees, reviewing narrative drift, and defining action/review-cadence handoffs BEFORE layout. It teaches HOW to frame approved numbers, never WHAT a metric means. A thinking layer, not a layout engine, chart renderer, metric definer, or owner assigner.
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
1,221 tokensWhen the skill is activated
Reference documents
14,193 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mandatory flow (do not skip a step)
- What this skill is for
- What this skill is NOT for
- Routing boundaries (pick the right skill first)
- Stop rules
Files
INDEX.mddoc6,458 bytesSKILL.mdcore5,282 bytesSKILL.mdcore5,282 bytesaction-and-review-cadence.mddoc1,818 byteschecklists/narrative-judgment-review-checklist.mddoc1,413 bytesderivation-route.mddoc10,810 bytesdiagnostic-question-tree.mddoc2,689 bytesexample-specialty-retail.mddoc9,900 bytesexample-weekly-business-review.mddoc3,189 bytesframing-benchmark-threshold.mddoc1,766 bytesframing-concentration.mddoc1,591 bytesframing-contribution-mix.mddoc1,710 bytesframing-period-variance.mddoc1,947 bytesframing-rate-decomposition.mddoc1,886 bytesframing-segment-behavior.mddoc1,742 bytesframing-signal-vs-noise.mddoc2,816 bytesframing-trend-anomaly.mddoc2,271 bytesnarrative-change-review.mddoc2,011 bytesstatistical-evidence-workflow.mddoc3,105 bytesstory-order.mddoc3,351 bytes
Read SKILL.md
# BI Analyst Knowledge (Seshat BI)
The judgment layer that turns a structurally-correct report into an ANALYSIS. It
sits between semantic-model readiness (F010) and dashboard layout (F011): given
approved contracts and a profiled source, it produces the decision-questions,
framings, and story order a good analyst would -- so a page answers a decision
instead of merely displaying a number.
This file is short by design. **It does not contain the knowledge base.** Do not
read every file. Follow the flow.
## Mandatory flow (do not skip a step)
```textbi-bigdata-knowledge
When your agent uses it
Big-data / distributed-compute reasoning and review layer for BI and data agents in the Seshat BI project. Use when data is too large for single-node pandas and the agent must reason about distributed or larger-than-memory processing — choosing an engine (Spark / Dask / Polars / DuckDB / warehouse), controlling partitioning and shuffle, avoiding skew and fan-out, aggregating at a declared grain at scale, choosing file formats (Parquet / Delta / Iceberg), incremental/idempotent processing, validating and reconciling at scale, diagnosing partial/retried output, reviewing backfills/partition evolution/compaction, and collecting performance/cost evidence. This is a reasoning layer, not an executor or Spark tutorial. It does not run jobs, define metrics, or own gating.
What it loads into context
Frontmatter
186 tokensAlways available to the agent
SKILL.md
1,238 tokensWhen the skill is activated
Reference documents
26,478 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to use this skill
- Use when
- Do not use when
- Boundaries
- Stop rules
- Conventions
Files
INDEX.mddoc6,670 bytesREADME.mddoc3,217 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 byteschecklists/aggregation-grain-checklist.mddoc1,915 byteschecklists/engine-selection-checklist.mddoc1,708 byteschecklists/join-skew-checklist.mddoc1,780 byteschecklists/operational-evidence-checklist.mddoc1,903 byteschecklists/partitioning-shuffle-checklist.mddoc1,741 byteschecklists/pipeline-review-checklist.mddoc3,021 byteschecklists/validation-reconciliation-checklist.mddoc2,243 bytesknowledge/aggregation-and-grain-at-scale.mddoc4,647 bytesknowledge/backfills-and-partition-evolution.mddoc3,473 bytesknowledge/bigdata-anti-patterns.mddoc4,749 bytesknowledge/bigdata-core-concepts-for-bi.mddoc5,636 bytesknowledge/bigdata-retail-examples.mddoc6,222 bytesknowledge/distributed-dataframe-model.mddoc4,851 bytesknowledge/engine-selection.mddoc4,442 bytesknowledge/file-formats-and-storage.mddoc3,651 bytesknowledge/incremental-and-idempotency.mddoc3,953 bytesknowledge/joins-and-skew.mddoc4,842 bytesknowledge/observability-and-partial-failures.mddoc4,051 bytesknowledge/partitioning-and-shuffle.mddoc4,690 bytesknowledge/performance-and-cost.mddoc4,958 bytesknowledge/validation-and-reconciliation-at-scale.mddoc4,520 bytespatterns/analyzer-rule-candidates.jsonasset4,093 bytespatterns/analyzer-rules.jsonasset9,979 bytespatterns/bigdata-patterns.jsonasset3,919 bytespatterns/validation-patterns.jsonasset4,434 bytesreferences/agent-training-set.jsonasset5,931 bytesreferences/agent-training-set.mddoc4,552 bytesreferences/copyright-and-sources.mddoc1,688 bytesreferences/cross-layer-map.mddoc3,915 bytesreferences/id-conventions.mddoc2,466 bytesreferences/research-notes.mddoc3,569 bytesreferences/retail-bigdata-schema.mddoc3,663 bytes
Read SKILL.md
# BI Big-Data Knowledge
A thin router into a distributed / large-scale data-processing reasoning layer for
BI/data agents. It helps an agent **think correctly** about big-data work and **hand off
cleanly** into the SQL, DAX, readiness, and dashboard layers. It does not execute jobs or
define business meaning.
This layer is the scale-out companion to `bi-python-knowledge`. The conceptual spine —
grain, fan-out, additivity, null semantics, reconciliation — is shared and **referenced,
not repeated** (see `references/cross-layer-map.md`). This layer owns only what changes
when compute becomes distributed or larger-than-memory.
## How to use this skill
bi-dax-knowledge
When your agent uses it
DAX knowledge base for teaching a BI agent to reason about, generate, review, and performance-tune DAX for Power BI / tabular models. Use when the task involves writing or auditing DAX measures, building time-intelligence / segmentation / ranking / customer / currency calculations, reviewing a semantic model, diagnosing physical or virtual filter propagation, calculation-group precedence, semi-additive totals, blank/zero semantics, or explaining DAX concepts and pitfalls. Covers core concepts, best practices, anti-patterns, performance notes, a curated pattern library, reusable metric contracts, and analyzer rules.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
1,692 tokensWhen the skill is activated
Reference documents
41,773 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- How to use it (recommended workflow)
- Phases the agent supports
- File map
- Cross-reference scheme
- Scope and boundaries
Files
INDEX.mddoc8,724 bytesREADME.mddoc4,559 bytesSKILL.mdcore7,172 byteschecklists/dax-diagnostic-checklist.mddoc1,566 byteschecklists/dax-measure-review-checklist.mddoc2,732 byteschecklists/dax-model-review-checklist.mddoc2,365 byteschecklists/metric-contract-checklist.mddoc2,378 bytesknowledge/dax-anti-patterns.mddoc5,564 bytesknowledge/dax-best-practices.mddoc5,754 bytesknowledge/dax-calculate-deep-dive.mddoc18,399 bytesknowledge/dax-calculation-groups-and-precedence.mddoc2,880 bytesknowledge/dax-core-concepts.mddoc9,520 bytesknowledge/dax-engine-internals.mddoc8,617 bytesknowledge/dax-evaluation-context-deep-dive.mddoc14,304 bytesknowledge/dax-function-semantics.mddoc15,647 bytesknowledge/dax-performance-diagnostics.mddoc10,014 bytesknowledge/dax-performance-notes.mddoc4,442 bytesknowledge/dax-relationships-and-virtual-filters.mddoc3,465 bytesknowledge/dax-retail-examples.mddoc13,781 bytesknowledge/dax-semi-additive-and-blank-semantics.mddoc3,288 bytespatterns/analyzer-rule-candidates.jsonasset16,240 bytespatterns/analyzer-rules.jsonasset16,155 bytespatterns/dax-patterns.jsonasset29,176 bytespatterns/metric-contract-patterns.jsonasset20,887 bytesreferences/agent-training-set.jsonasset19,080 bytesreferences/agent-training-set.mddoc14,612 bytesreferences/retail-schema.mddoc6,409 bytesreferences/source-map.mddoc7,541 bytes
Read SKILL.md
# BI DAX Knowledge
A teaching + reference layer for a Business Intelligence agent working with DAX. It separates
**explanation** (Markdown, for reasoning and teaching) from **structured rules** (JSON, for
precise generation and automated review).
## When to use this skill
Trigger for any of: writing a DAX measure or calculated column; reviewing/auditing existing
DAX; building time intelligence (YTD, YOY, rolling, running totals), segmentation, ABC, ranking,
new/returning customers, events-in-progress, what-if parameters, or currency conversion;
reviewing a semantic model for DAX prerequisites; or explaining a DAX concept/pitfall.
Also trigger for ambiguous relationship paths, `TREATAS`/virtual-filter defects, interacting
calculation groups, semi-additive snapshot totals, and blank-versus-zero behavior.bi-python-knowledge
When your agent uses it
Python/pandas reasoning and review layer for BI and data agents in the Seshat BI project. Use when an agent must reason about dataframe work — profiling a source, judging dtypes/schema, cleaning and standardizing, merging without fan-out, aggregating at a declared grain, parsing dates, validating/reconciling against SQL and readiness, diagnosing performance/memory, or reviewing a Python pipeline. This is a reasoning layer, not an executor and not a Python tutorial. It does not run pipelines, define metrics, or own gating. See INDEX.md for the live routes.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
826 tokensWhen the skill is activated
Reference documents
19,942 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Use this skill when
- Do not use this skill for
- Mandatory workflow
- What this layer owns
- What this layer does NOT own
- Global stop rules
- Conventions
Files
INDEX.mddoc9,473 bytesREADME.mddoc3,752 bytesSKILL.mdcore3,775 bytesSKILL.mdcore3,775 byteschecklists/aggregation-grain-checklist.mddoc1,732 byteschecklists/cleaning-review-checklist.mddoc3,452 byteschecklists/dataframe-review-checklist.mddoc1,616 byteschecklists/merge-fanout-checklist.mddoc1,111 byteschecklists/python-pipeline-review-checklist.mddoc1,410 byteschecklists/validation-reconciliation-checklist.mddoc1,419 bytesknowledge/cleaning-and-standardization.mddoc5,146 bytesknowledge/dataframe-mental-model.mddoc2,591 bytesknowledge/dates-times-and-calendars.mddoc2,313 bytesknowledge/file-source-grain.mddoc8,530 bytesknowledge/groupby-aggregation-and-grain.mddoc4,507 bytesknowledge/joins-merge-and-fanout.mddoc2,480 bytesknowledge/nulls-missing-values-and-blanks.mddoc2,190 bytesknowledge/pandas-dtypes-and-schema.mddoc2,450 bytesknowledge/performance-and-memory.mddoc2,593 bytesknowledge/profiling-and-source-inspection.mddoc2,511 bytesknowledge/python-anti-patterns.mddoc2,686 bytesknowledge/python-core-concepts-for-bi.mddoc2,294 bytesknowledge/python-retail-examples.mddoc2,674 bytesknowledge/validation-and-reconciliation.mddoc2,743 bytespatterns/analyzer-rule-candidates.jsonasset2,561 bytespatterns/analyzer-rules.jsonasset2,061 bytespatterns/python-patterns.jsonasset2,625 bytespatterns/validation-patterns.jsonasset3,326 bytesreferences/agent-training-set.jsonasset6,280 bytesreferences/agent-training-set.mddoc5,278 bytesreferences/copyright-safety.mddoc1,631 bytesreferences/id-conventions.mddoc2,885 bytesreferences/retail-dataframe-schema.mddoc3,619 bytesreferences/source-map.mddoc1,805 bytes
Read SKILL.md
# BI Python Knowledge Skill
A thin router into a Python/pandas reasoning layer for BI/data agents. It helps an
agent **think correctly** about dataframe work and **hand off cleanly** into the
SQL, DAX, readiness, and dashboard layers. It does not execute code or define
business meaning.
> **Status: core routes live.** Dataframe semantics, profiling, dtypes, missing
> values, cleaning, merge/fan-out, aggregation grain, dates/calendars, validation,
> performance, active-rule review, positive patterns, and pipeline review all resolve
> through `INDEX.md`.
## Use this skill when
bi-sql-knowledge
When your agent uses it
SQL reasoning, validation, reconciliation, transformation, diagnostics, and anti-pattern knowledge layer for Seshat BI agents. Use when a task involves reasoning about source SQL: source profiling, table grain, keys & uniqueness, joins & fan-out amplification, aggregation correctness, COUNT/NULL semantics, deduplication, validation queries, reconciliation queries, silver/gold transformation logic, window/date-time analytics, SQL anti-patterns, or basic SQL performance reasoning, or interpretation of a supplied sanitized PostgreSQL JSON execution plan. The SQL counterpart to bi-dax-knowledge. It is a thinking & validation layer, not a database executor, runtime validator, dbt/Dagster project, or automatic tuning service.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
1,369 tokensWhen the skill is activated
Reference documents
51,907 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mandatory flow (do not skip a step, do not lose the compass)
- What this skill is for
- What this skill is NOT for
- Routing boundaries (pick the right skill before working)
- Stop rules
- ID conventions (full detail in `references/id-conventions.md`)
- Boundaries
Files
INDEX.mddoc10,157 bytesREADME.mddoc4,156 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 byteschecklists/postgresql-plan-review-checklist.mddoc2,383 byteschecklists/sql-reconciliation-checklist.mddoc1,949 byteschecklists/sql-review-checklist.mddoc2,367 byteschecklists/sql-validation-checklist.mddoc2,089 bytesknowledge/postgresql-execution-plans.mddoc5,547 bytesknowledge/sql-aggregation-correctness.mddoc5,724 bytesknowledge/sql-anti-patterns.mddoc28,535 bytesknowledge/sql-cookbook-extension-notes.mddoc19,286 bytesknowledge/sql-core-concepts.mddoc11,163 bytesknowledge/sql-date-time-analysis.mddoc9,562 bytesknowledge/sql-diagnostics-playbook.mddoc15,230 bytesknowledge/sql-grain-and-joins.mddoc10,505 bytesknowledge/sql-logical-query-processing.mddoc3,255 bytesknowledge/sql-performance-notes.mddoc8,384 bytesknowledge/sql-reconciliation-playbook.mddoc11,455 bytesknowledge/sql-transformation-patterns.mddoc16,663 bytesknowledge/sql-window-functions.mddoc10,089 bytespatterns/postgresql-plan-patterns.jsonasset6,247 bytespatterns/sql-analyzer-rule-candidates.jsonasset39,042 bytespatterns/sql-analyzer-rules.jsonasset9,068 bytespatterns/sql-patterns.jsonasset11,876 bytespatterns/sql-validation-patterns.jsonasset7,396 bytesreferences/agent-training-set.jsonasset57,706 bytesreferences/copyright-safety.mddoc2,866 bytesreferences/id-conventions.mddoc4,068 bytesreferences/source-map.mddoc11,683 bytes
Read SKILL.md
# BI SQL Knowledge (Seshat BI)
A navigational interface to a SQL **reasoning and validation** knowledge base. It teaches an
agent to reason about SQL correctly -- with table **grain** and **aggregation correctness** as
its foundation, the way filter context is the foundation of `bi-dax-knowledge`.
This file is short by design. **It does not contain the knowledge base.** Do not read every
file in this skill. Follow the flow below.
## Mandatory flow (do not skip a step, do not lose the compass)
```text
Router -> this SKILL.md -> INDEX.md -> ONLY the relevant file(s) -> output contract / checklist
```retail-kpi-knowledge
When your agent uses it
Retail KPI / metric-contract reasoning layer for BI agents in the Seshat BI project. Use when an agent must reason about the BUSINESS MEANING of a retail KPI before any implementation — defining a KPI in business terms, classifying additivity (fully/semi/non-additive), identifying grain, listing required source fields, resolving ambiguity (gross vs net, VAT, returns, cost method, same-store), choosing an MVP KPI pack, reviewing a metric contract for completeness, or preparing a clean handoff to an implementation layer. Also use it to classify KPI sufficiency or prepare an owner policy decision packet. This is a meaning/definition + review layer, not an executor: it does not write DAX/SQL/Python, grant readiness, approve policy, or design dashboards. See INDEX.md for live/planned routes; registry.yaml is the authoritative machine-readable inventory.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
971 tokensWhen the skill is activated
Reference documents
53,115 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Use when
- Do not use when
- Mandatory workflow
- Boundaries
- Stop rules
Files
INDEX.mddoc9,369 bytesREADME.mddoc5,125 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 byteschecklists/kpi-extension-checklist.mddoc1,533 byteschecklists/kpi-pack-review-checklist.mddoc1,241 byteschecklists/kpi-policy-decision-checklist.mddoc1,239 byteschecklists/metric-ambiguity-checklist.mddoc1,436 byteschecklists/metric-contract-review-checklist.mddoc1,983 bytescontracts/average-basket-size-units.mddoc1,855 bytescontracts/average-transaction-value.mddoc2,665 bytescontracts/discount-amount.mddoc2,489 bytescontracts/discount-rate.mddoc1,960 bytescontracts/discounted-transaction-rate.mddoc2,071 bytescontracts/gross-margin-percent.mddoc1,935 bytescontracts/gross-margin.mddoc2,159 bytescontracts/gross-sales.mddoc2,766 bytescontracts/net-sales-growth.mddoc4,512 bytescontracts/net-sales.mddoc3,015 bytescontracts/quantity-sold.mddoc2,331 bytescontracts/returns-rate-value.mddoc2,852 bytescontracts/same-store-sales-growth.mddoc3,967 bytescontracts/transactions-count.mddoc2,249 bytescontracts/ytd.mddoc4,805 bytesdomains/basket-and-transactions.mddoc3,434 bytesdomains/branch-store-performance.mddoc4,443 bytesdomains/customer.mddoc6,000 bytesdomains/data-quality-control.mddoc3,882 bytesdomains/discounts-and-promotions.mddoc3,934 bytesdomains/inventory.mddoc3,989 bytesdomains/margin-profitability.mddoc3,546 bytesdomains/product-category-performance.mddoc3,796 bytesdomains/returns.mddoc3,770 bytesdomains/sales-and-revenue.mddoc4,006 bytesdomains/targets-and-budgets.mddoc3,304 bytesdomains/time-intelligence.mddoc2,303 bytesknowledge/kpi-additivity-and-grain.mddoc3,243 bytesknowledge/kpi-ambiguities.mddoc3,882 bytesknowledge/kpi-core-concepts.mddoc3,292 bytesknowledge/kpi-sufficiency-and-policy-decisions.mddoc3,150 bytesknowledge/metric-contracts.mddoc3,819 bytesknowledge/retail-kpi-domains.mddoc2,429 bytespacks/branch-performance-pack.mddoc1,720 bytespacks/data-quality-control-room-pack.mddoc1,497 bytespacks/inventory-control-pack.mddoc1,464 bytespacks/mvp-retail-kpi-pack.mddoc3,103 bytespacks/product-performance-pack.mddoc1,619 bytespacks/returns-exceptions-pack.mddoc1,379 bytespacks/sales-performance-pack.mddoc1,710 bytespatterns/metric-anti-patterns.jsonasset3,713 bytespatterns/metric-contract-candidates.jsonasset2,525 bytespatterns/metric-patterns.jsonasset2,244 bytesreferences/enterprise-kpi-knowledge-layer.mddoc73,153 bytesreferences/id-conventions.mddoc2,223 bytesreferences/implementation-handoff-template.mddoc1,367 bytesreferences/kpi-coverage-scorecard-template.mddoc4,986 bytesreferences/kpi-derivation-lineage.mddoc6,093 bytesreferences/metric-contract-template.mddoc2,647 bytesreferences/planned-kpi-backlog.mddoc987 bytesreferences/research-notes.mddoc2,237 bytesreferences/source-field-requirements.mddoc2,802 bytesreferences/source-map.mddoc1,335 bytesregistry.yamlasset13,806 bytes
Read SKILL.md
# Retail KPI Knowledge Skill
A Retail KPI and metric-contract reasoning layer for BI agents. It helps an agent
define, classify, review, and validate retail KPIs **before** any DAX measure, SQL
transformation, or dashboard page is built.
## Purpose
This layer owns the *business meaning* of retail KPIs and the *metric contract* that
must exist before implementation. It produces definitions, additivity and grain calls,
required-field lists, ambiguity flags, validation checks, and a clean handoff to the
DAX / semantic-model layer.
It does **not** produce runtime artifacts. It governs meaning; other layers govern code.bi-analyst-knowledge
When your agent uses it
Use Seshat's public analyst-judgment knowledge to derive decision-questions, choose an analytical framing, and order a story from approved metric contracts and a committed source-profile.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
109 tokensWhen the skill is activated
Reference documents
1,544 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-analyst-knowledge/INDEX.mddoc6,458 bytesSKILL.mdcore477 bytes
Read SKILL.md
# BI Analyst knowledge
Open `../../knowledge/bi-analyst-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Never define metric meaning or invent a
number here; an unanswerable question is a `[GAP]`, not a guess.bi-bigdata-knowledge
When your agent uses it
Use Seshat's public big-data knowledge for distributed aggregation, partitioning, joins, skew, idempotency, reconciliation, performance, and cost reasoning.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
92 tokensWhen the skill is activated
Reference documents
1,629 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-bigdata-knowledge/INDEX.mddoc6,670 bytesSKILL.mdcore427 bytes
Read SKILL.md
# BI big-data knowledge
Open `../../knowledge/bi-bigdata-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Do not select a distributed engine unless
scale and operational evidence justify it.bi-dax-knowledge
When your agent uses it
Use Seshat's public DAX knowledge for metric contracts, evaluation context, measure review, performance reasoning, and semantic-model prerequisites.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
82 tokensWhen the skill is activated
Reference documents
2,021 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-dax-knowledge/INDEX.mddoc8,724 bytesSKILL.mdcore378 bytes
Read SKILL.md
# BI DAX knowledge
Open `../../knowledge/bi-dax-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Do not design visuals or invent business metric
meaning.bi-python-knowledge
When your agent uses it
Use Seshat's public Python knowledge for governed single-node source preparation, cleaning, grain, and aggregation reasoning.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
84 tokensWhen the skill is activated
Reference documents
2,231 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-python-knowledge/INDEX.mddoc9,473 bytesSKILL.mdcore419 bytesSKILL.mdcore419 bytes
Read SKILL.md
# BI Python knowledge
Open `../../knowledge/bi-python-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Do not execute against live data without the user's
explicit in-scope request and required connection boundary.bi-sql-knowledge
When your agent uses it
Use Seshat's public SQL knowledge for source grain, joins, aggregation, validation, reconciliation, and transformation reasoning without executing a database.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
83 tokensWhen the skill is activated
Reference documents
2,673 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-sql-knowledge/INDEX.mddoc10,157 bytesSKILL.mdcore390 bytesSKILL.mdcore390 bytesSKILL.mdcore390 bytes
Read SKILL.md
# BI SQL knowledge
Open `../../knowledge/bi-sql-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Ground the row grain and never infer missing source
facts.business-knowledge-interview
When your agent uses it
After a database is discovered and profiled, interview the business owner to capture the meaning-critical decisions the rest of the Database-to-PBIP flow depends on -- KPI meaning, PII handling, table grain, primary keys, relationships, missing-value rules, and ambiguous financial/quantity/date columns -- and record every outcome in the project Decision Store. Use when someone asks to run the interview, capture business knowledge, or resolve the business questions behind a model in the Seshat BI repo. It asks obvious low-risk items as one batch and critical items individually with explicit named-human approval; it uses masked samples and never shows raw suspected PII by default; it records decisions and STOPS. It does NOT define metric contracts or DAX, does NOT self-grant any approval, and does NOT emit a confidence score.
What it loads into context
Frontmatter
196 tokensAlways available to the agent
SKILL.md
1,311 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Preconditions (stop if unmet)
- How it runs
- Exit
- Hard stops (never)
Files
SKILL.mdcore5,710 bytes
Read SKILL.md
# business-knowledge-interview
The interview is the front door of the Database-to-PBIP flow's decision layer
(spec 121). It converts a discovery profile into recorded, approvable business
decisions so that every downstream stage consumes governed answers instead of
unrecorded assumptions.
Behavior is governed by the `business-knowledge-interview` contract and its
recorded interview protocol. The
static rules DS1-DS5 (`seshat check`) verify the recorded outcome, not the
conversation.
## When to use
dagster-workflows
When your agent uses it
Route Dagster intent to Seshat's governed medallion workflow or the official Dagster competence owner without bypassing readiness, approvals, or evidence.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,386 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intent ownership
- Fixed workflow
- Hard boundaries
- Exit meanings
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore6,021 bytes
Read SKILL.md
# Governed Dagster workflows
Read `../../portable-operating-contract.md` before acting. For a governed
Seshat medallion run, use only the installed `seshat dagster` helpers; never
invoke `dagster` directly against the orchestration project and never bypass
the gate readers, the closed-argv runner, or the redaction layer. Dagster RUNS
already-approved steps; the gate exit code and the named human decide whether
a stage passed.
## Intent ownership
| User intent | Seshat pre-gate | Execution owner | Seshat afterward |
|---|---|---|---|
| Decide whether orchestration fits the BI workflow | Readiness state and orchestration assessment | Seshat selection policy | State one truthful next action |dbt-workflows
When your agent uses it
Route dbt intent to Seshat's governed shadow workflow or the official dbt Labs competence and execution owner, without bypassing readiness or evidence.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,903 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intent ownership
- Fixed workflow
- The `meta.seshat` model contract
- Hard boundaries
- Exit meanings
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytes
Read SKILL.md
# Governed dbt workflows
Read `../../portable-operating-contract.md` before acting. For a governed
Seshat shadow workflow, use only the installed `seshat dbt` helpers; never
bypass their fixed selector, target, profile, lock, redaction, or artifact
checks with raw dbt commands.
## Intent ownership
| User intent | Seshat pre-gate | Execution owner | Seshat afterward |
|---|---|---|---|
| Decide whether dbt fits the current BI stage | Readiness and approved-mapping context | Seshat selection policy | State one truthful next action |
| Scaffold governed shadow models | Approved committed source map | Seshat source-map-derived scaffold | Validate citations and the `meta.seshat` contract |
| Governed compile, build, test, or parity | Mapping Ready, exact selector, shadow target, and accepted immutable plan | dbt Core through `seshat dbt` | Normalize artifacts into derived evidence, blockers, and parity findings |first-hour-compass
When your agent uses it
Show a NEW-table author the stateful "you are here / next artifact / authoring skill" orientation card for ONE table in the Seshat BI repo. Use when someone asks "where is this table in the readiness journey", "what do I do next for <table>", or "orient me on a new table". READ-ONLY and invoke-and-present only: it parses that table's mappings/<table>/readiness-status.yaml and RENDERS a single-table orientation card (current stage, the next non-pass stage + the artifact it needs + the authoring skill that produces it, plus recorded STOP rows). It RENDERS recorded state (never recomputes a status, advances a stage, writes a pass, infers/back-fills an approval, or fabricates evidence), runs NO validator, opens NO DB connection, and emits NO numeric health/confidence/percent-ready/maturity score (hard rule #9). It is the STATEFUL single-table sibling of the F026 readiness-viewer (multi-table matrix) and the stateful form of the F006 static onboarding checklist.
What it loads into context
Frontmatter
256 tokensAlways available to the agent
SKILL.md
1,741 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What it does / does NOT do
- How it renders (renders, never re-derives)
- Honest-state rules
- First arrival: offer a worked example as the reference pattern
- The two-condition approval flag
- The four judgment seams (surfaced, never resolved -- Principle V)
- Deltas vs its parents
- Read-only proof
- See also
Files
SKILL.mdcore7,278 bytes
Read SKILL.md
# First-Hour Compass
The stateful single-table orientation card for a new-table author. F024 module class:
**Product Module / `read-only`**. It answers, for ONE table: *where am I, what is the next
artifact, which skill authors it, and what human STOP is recorded?*
## What it does / does NOT do
- **Creates no truth.** It copies recorded fields; it defines no meaning, sets no status.
- **Changes no state.** It edits no file and runs no git mutation (a run leaves `git status`
clean -- see the read-only proof below).
- **Infers no approval.** It never populates, back-fills, or synthesizes an approval; it only
reports whether the next stage's `<stage>-ready.md` names a required owner and whether an
`approvals[]` entry is recorded.kpi-contract-builder
When your agent uses it
Help a human turn a named-but-planned retail KPI into a governed, owner-ready project metric-contract by driving the shipped kpi_contracts engine (spec 124). On first contact, when no approved decisions exist yet, it assesses source answerability, lists the exact Decision Store decisions to get approved via business-knowledge-interview, and renders a preview with per-field provenance -- writing no YAML. Once the approved kpi_definition / policy_ruling decisions, a named eligible owner, and committed source evidence exist, it drives draft_project_metric_contract (a gold-blocked contract) and, after the gold binding is materialized, finalize_project_metric_contract. Use when someone asks to draft, author, or start a metric contract for a planned KPI in the Seshat BI repo. It never invents business meaning, DAX, SQL, gold columns, approvals, owners, a confidence score, or a registry entry; it never promotes a KPI to Seeded and never self-grants an approval.
What it loads into context
Frontmatter
234 tokensAlways available to the agent
SKILL.md
1,620 tokensWhen the skill is activated
Reference documents
751 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- The two-trip flow
- field_provenance (preview only; five-value origin vocabulary)
- Hard stops
Files
SKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 byteswalkthrough.mddoc3,103 bytes
Read SKILL.md
# kpi-contract-builder
This skill is the agent-facing front door to the shipped `kpi_contracts` stage.
It does NOT reimplement contract authoring: the shipped `kpi_contracts` engine and
its `kpi_answerability` scorecard already exist (spec 124). This skill DRIVES
them and adds the first-contact assessment the engine deliberately refuses to do.
## When to use
- Someone asks to draft / author / start a metric contract for a KPI that the
registry marks `planned` (no seeded contract yet), or for a user-supplied
custom KPI.
- You are at the `kpi_contracts` flow stage (downstream of
`business-knowledge-interview`, upstream of silver/gold model planning).pbi-mcp-doctor
When your agent uses it
Use when a user asks whether or how to wire Microsoft's official Power BI MCP servers into a Seshat BI workspace: run the read-only environment doctor, map a task to the governed Power BI surface (including the official report-authoring skill), generate a safe read-only config template, or run the mocked read-only preflight.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,441 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Fixed workflow
- The recommendation matrix in plain language
- How to read the advisory records
- What this family will NEVER do
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore6,168 bytesSKILL.mdcore6,168 bytes
Read SKILL.md
# Power BI MCP doctor (read-only)
Read `../../portable-operating-contract.md` before acting. Use only the
installed `seshat pbi-mcp` verbs; never launch an MCP server directly, never
edit `.mcp.json` by hand when the generator can produce it, and never treat
any output of this family as an approval. F016 (the Power BI execution
adapter) is PARKED: no mutation path exists anywhere in this family.
## Fixed workflow
1. Map the user's task to the governed surface, read-only:
`seshat pbi-mcp doctor --repo . --intent <task> [--target <table>] [--harness <claude-code|codex>] [--json] [--write-advisory]`
powerbi-workflows
When your agent uses it
Route guarded Power BI work -- design, native report authoring, semantic-model operations, published queries, QA, bounded formatting, and PBIP adoption -- to the correct Seshat or official Microsoft surface under Seshat BI's gates.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,426 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- One front door, explicit execution owners
- Design (dashboards and pages)
- Review and QA
- Reopening Desktop after an external edit
- Theme and backgrounds
- Formatting and geometry
- Semantic measures (handoff)
- Existing PBIP adoption
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore10,678 bytes
Read SKILL.md
# Power BI workflows
Read `../../portable-operating-contract.md` before acting. These routes never
replace readiness gates: no invented metric, measure, KPI, or DAX meaning; no
numeric readiness/confidence score; no self-granted approval; no
dashboard-ready claim without committed evidence.
## One front door, explicit execution owners
This skill is the broad Power BI front door. It owns intent classification and
Seshat's pre/post gates; it does not reproduce Microsoft execution behavior.
For execution-shaped requests, use `seshat pbi-mcp doctor` as the canonical
machine-checkable selector even when the selected owner is an official skill
rather than an MCP server.retail-build-warehouse
When your agent uses it
Author the silver + gold migration SQL for a mapped retail table from its APPROVED source-map, then STOP before executing. Use after a table's mapping gate is CLEARED in the Seshat BI repo and someone asks to build the silver/gold SQL, write the migration, or fill the retail-orchestrate build seam. Author-and-stop: it writes warehouse/migrations/*.sql FILES only, never connects to a database, never applies the SQL, and HARD-STOPS at any judgment call the map does not already answer.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
2,747 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Author vs execute (read first)
- Preconditions (STOP unless all hold)
- Silver: the load-bearing Phase-5 order (NUMBERED -- do NOT reorder)
- Gold: the Kimball star (Phase 6)
- Judgment stops (fail LOUD -- never satisfy with a silent default)
- After authoring (the handoff)
- Orchestration
- See also
Files
SKILL.mdcore10,297 bytes
Read SKILL.md
# retail-build-warehouse
Turns an APPROVED `mappings/<table>/source-map.yaml` into the two migration `.sql`
files -- `silver` (typed/cleaned flat table) then `gold` (Kimball star) -- in the
order the medallion playbook proves load-bearing. It fills the silver/gold
`[SEAM]` the `retail-orchestrate` conductor parks at.
The agent is the runtime: this is a procedure you follow, authoring SQL by adapting
the proven `warehouse/migrations/0003`/`0004` shape. There is NO codegen engine, NO
`.sql.tmpl` template, and NO `retail build` CLI -- by design (the source-map cannot
carry the transform logic; an engine would emit only boilerplate). That is a
recorded design decision, not an omission to be fixed.
## Author vs execute (read first)retail-discover-portfolio
When your agent uses it
Discover an unfamiliar retail data portfolio before per-table onboarding. Produces one metadata-only Layer-A survey across every reachable table, proposes non-critical domain and first-delivery scope decisions, delegates selected tables to retail-onboard-table for Layer-B profiling, and hands off to the existing business-knowledge-interview. Never samples source values, self-confirms a decision, or advances beyond the interview handoff.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,371 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Boundary
- 1. Produce the Layer-A survey
- 2. Propose a domain
- 3. Propose a bounded first-delivery scope
- 4. Hand off to the existing interview
- Resume and local-stop table
Files
SKILL.mdcore6,543 bytesSKILL.mdcore6,543 bytesSKILL.mdcore6,543 bytes
Read SKILL.md
# retail-discover-portfolio
Use this skill when the owner has an unfamiliar database schema or file folder and
needs a governed route from portfolio discovery to the business interview.
## Boundary
This is an agent-conducted flow, not a new state engine or CLI workflow:
portfolio discovery -> domain -> scope -> selected-table onboarding -> interview handoff -> STOP
- Layer A is the metadata-only portfolio survey in
templates/portfolio-survey.md.
- Layer B is the existing value-backed, per-table Source Ready profile owned byretail-govern
When your agent uses it
Run the Seshat BI governance checker and interpret its findings. Use when someone asks to check, validate, or gate Power BI / DAX / TMDL / PBIR / SQL work in the Seshat BI repo, when `seshat check` reports a rule violation, or when you need to know what a rule id (D8, C2, S2, G1, …) means and where to fix it. Invoke-and-interpret only: this skill does NOT build models, run pbi-cli, or auto-fix — it runs the checker and maps ids to fixes.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
4,420 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope boundary (read this first)
- Run the checker
- Read a finding
- Rule id → meaning → where to fix
- What to do after interpreting
- Orchestration
Scripts executed separately
../../../../../scripts/export_rule_fix_table.py
Files
SKILL.mdcore16,927 bytesSKILL.mdcore16,927 bytesSKILL.mdcore16,927 bytes../../../../../scripts/export_rule_fix_table.pyruns1,977 bytes
Read SKILL.md
# retail-govern
Seshat BI's conventions are enforced by a static checker, `seshat check`. This
skill teaches you to **run it, read its findings, and map each rule id to the file
and fix it points at**. The authoritative catalog is the glossary's "Static check
rules" section, which mirrors the checker's live rule registry; the rules manifest
is the machine-readable inventory. (An older 23-rule governance-layer design doc
is a historical record, NOT the current count -- do not cite it for the catalog.)
## Scope boundary (read this first)
This skill is **invoke-and-interpret only**. It does **not** orchestrate a Power BI
build, does **not** call `pbi-cli` or Power BI Desktop, and does **not** auto-fix or
self-heal violations. Those are deferred D-layer work (spec §9). Here you run theretail-kpi-knowledge
When your agent uses it
Use Seshat's public retail KPI knowledge to define governed metric meaning, additivity, grain, required fields, ambiguity decisions, contracts, and handoffs before implementation.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
104 tokensWhen the skill is activated
Reference documents
2,173 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/retail-kpi-knowledge/INDEX.mddoc9,369 bytesSKILL.mdcore476 bytes
Read SKILL.md
# Retail KPI knowledge
Open `../../knowledge/retail-kpi-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Undefined VAT, returns, cost, same-store, or
snapshot policy is a named-human decision, never an agent default.retail-onboard-table
When your agent uses it
Walk a NEW raw retail table across the FIRST readiness transition -- Source Ready (Stage 1) through Mapping Ready (Stage 2) -- and seed its per-table readiness-status, in the Seshat BI repo. Use when someone says "onboard <schema>.<table>", "take this new table from nothing to a reviewed map", or "start the readiness journey for a table". This is the stage-transition FRONT DOOR: it sequences profile -> map -> gate, writes the readiness-status record, and STOPS at Mapping Ready. It DELEGATES the five mapping artifacts to the `source-mapping` skill (it does not re-implement mapping); it NEVER writes `silver.*` SQL, NEVER self-grants the gate approval, and NEVER answers a Principle-V judgment call (grain, PII, business rollup, product identity).
What it loads into context
Frontmatter
201 tokensAlways available to the agent
SKILL.md
2,452 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope boundary (read first)
- Run-state: read mappings/<table>/ FIRST (no new state file)
- Stage 1 -- Source Ready (profile + PROPOSE semantics)
- Stage 2 -- Mapping Ready (delegate to source-mapping)
- Readiness-status bookkeeping
- Human seams -- HARD-STOP (Principle V; the wizard proposes, a human decides)
- Terminal: Mapping Ready -- STOP
- Deferred-boundary mode (no DSN or no `db` extra)
- Generic, not C086
- See also
- Orchestration
Files
SKILL.mdcore9,948 bytes
Read SKILL.md
# retail-onboard-table
The onboarding front door for ONE table's first two readiness stages. The kit
already ships the verb that authors the mapping artifacts (`source-mapping`) and the
conductor that sequences every verb end-to-end (`retail-orchestrate`). This skill is
the stage-scoped composition between them: "I have a new raw table -- walk me from
nothing to a reviewed map." It advances **Source Ready -> Mapping Ready**, seeds the
per-table `readiness-status.yaml`, and STOPS. It is a procedure the agent performs
(agent-first, Principle I); `seshat check` and the read-only profile are gates it
CALLS, not a CLI subcommand.
## Scope boundary (read first)
- **Agent-first, no CLI.** This is a SKILL the agent runs; it adds no `retail`retail-orchestrate
When your agent uses it
Drive a retail table through the medallion sequence (profile -> map -> gate -> build -> validate -> Power BI) by composing the existing verb-skills, and self-heal against the governance gate's exit code. Use when someone asks to take a table end-to-end, "orchestrate", "run the whole pipeline", or drive the medallion playbook in the Seshat BI repo. The AGENT is the runtime: this skill sequences and instructs; it never spawns a loop runtime, never self-grants the mapping approval, and HARD-STOPS at human judgment calls.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
2,824 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope + non-negotiables (read first)
- Run-state: read mappings/<table>/ FIRST (no new state file)
- Fixed sequence (delegate to the existing verbs)
- The self-heal loop (a contract you follow; not a runtime)
- Per-rule classification: auto-fixable vs HARD-STOP
- Seams (deferred by design -- report and park, never fake)
- What "done for this slice" looks like
- See also
Files
SKILL.mdcore10,848 bytesSKILL.mdcore10,848 bytes
Read SKILL.md
# retail-orchestrate
The conductor for Layer D. The kit's architecture makes the agent the primary
surface: "an agent runs the playbook conversationally ... and self-heals against
the gate." This skill is how the agent does that -- it **sequences the four
existing verb-skills** across the medallion phases and runs the **self-heal loop**
whose only success signal is a literal gate exit 0.
You (the agent reading this) ARE the runtime. This skill is procedure, not an
engine: there is no daemon, no scheduler, no persisted counter, and no
fix-applying subagent.
## Scope + non-negotiables (read first)
retail-validate
When your agent uses it
Run the LIVE data checks against a materialized retail table and interpret the findings. Use after silver + gold exist for a mapped table in the Seshat BI repo, when someone asks to validate or reconcile a table, or when a V-RC2 / V-RC15 / V-RC16 finding appears. Invoke-and-interpret only: this skill runs `retail validate` against a live Postgres DB and maps each finding id to its fix. It does NOT build models, write SQL, or auto-fix.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,272 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope boundary (read first)
- Prerequisites
- Run it
- Read a finding
- Finding id -> meaning -> where to fix
- Deferred/live-boundary mode (no DSN or no `db` extra)
- What to do after interpreting
- See also
- Orchestration
Files
SKILL.mdcore4,871 bytes
Read SKILL.md
# retail-validate
`seshat check` proves everything provable from committed text. `retail validate`
proves the four things only a running database can show, on the MATERIALIZED rows
(constitution Principle VIII). This skill runs it and
maps each finding to the one place to fix it -- the live sibling of
`retail-govern`.
## Scope boundary (read first)
Invoke-and-interpret only. This skill runs the live checks and explains findings;
it does NOT write or fix silver/gold SQL, does NOT call pbi-cli, and does NOT
auto-loop. The live run needs a DB and is the user's call; you report and stop.
seshat-bi
When your agent uses it
Route a BI project through Seshat BI's governed seven-stage readiness flow. Use when a user asks to inspect a retail source, initialize a Seshat project, find the truthful next action, validate readiness evidence, or stop at the correct human approval gate.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
2,702 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Discovering the surface (no name memorization needed)
- Agent-driven loop (programmatic automation)
- Existing PBIP projects
- Resetting / re-running a project
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytes
Read SKILL.md
# Seshat BI
Read `../../portable-operating-contract.md` before acting. Inspect the current
workspace and use installed `seshat` commands when available. If the workspace
has no `AGENTS.md`, this skill's portable operating contract still applies.
For subject reasoning, load only the relevant bundled skill:
- SQL and source grain: `bi-sql-knowledge`
- DAX and semantic measures: `bi-dax-knowledge`
- Python/dataframe preparation: `bi-python-knowledge`
- distributed data: `bi-bigdata-knowledge`
- retail KPI meaning and contracts: `retail-kpi-knowledge`
- decision-questions, framing, and story order from approved metrics:seshat-studio
When your agent uses it
Open Seshat Studio, the local analyst console for ONE Seshat workspace, when someone asks to "open Studio", "show me the workspace", "launch the console", or wants to see readiness, tables, and approvals in a browser instead of a terminal. Studio serves a single pinned workspace on loopback only, reads recorded state, and stops at the same human approval gates as every other Seshat verb. It NEVER grants an approval, advances a stage, writes a pass, invents evidence, or emits a numeric readiness/health/confidence score. It needs the optional `studio` extra; without it the launch is a named refusal with an install remedy, never a traceback. NOT a hosted or shared service, NOT a replacement for the readiness verbs, and NOT a Power BI authoring surface.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
1,672 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Launch it by asking
- What it shows, and what it refuses
- Local only, by construction
- Which agent answers a turn
- Relationship to the readiness verbs
- Troubleshooting
- See also
Files
SKILL.mdcore7,442 bytes
Read SKILL.md
# Seshat Studio
The local analyst console for one Seshat workspace. It presents what the
workspace already records -- readiness by stage, tables, turns, and the
approvals a human still owes -- in a browser, on loopback, for one workspace per
process.
## Launch it by asking
Natural language is the way in. When the user says any of these, launch Studio:
- "open Studio" / "open the Studio console"
- "show me this workspace in the browser"
- "launch the analyst console"source-mapping
When your agent uses it
Drive a raw retail source table through the source-mapping gate before any silver SQL exists. Use when someone asks to map, model, profile, or onboard a new bronze table toward Power BI in the Seshat BI repo -- profile the source, decide grain/PK, fill the five mapping artifacts into mappings/<table>/, and stop at the gate. This skill ENFORCES the rule that no silver.* SQL is written until the map is reviewed and approved. It profiles and authors and stops; it does NOT write silver/gold SQL and does NOT build the Power BI model.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,762 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope boundary (read first)
- The five artifacts (write the blanks with `seshat scaffold-source <table>`)
- Cleaning chain (canonical order -- the HYBRID walk)
- Procedure
- Deferred/live-boundary mode (no DSN or no `db` extra)
- See also
- Orchestration
Files
SKILL.mdcore10,729 bytesSKILL.mdcore10,729 bytesSKILL.mdcore10,729 bytesSKILL.mdcore10,729 bytesSKILL.mdcore10,729 bytes
Read SKILL.md
# source-mapping
The source-mapping gate is the kit's one load-bearing rule (constitution
Principle IV): **before any `silver.*` SQL is written, the source MUST be
profiled and mapped into committed, reviewed artifacts.** This skill runs that
gate: profile -> author the five artifacts -> stop at judgment calls -> hard-stop
before silver. It formalizes Phases 1-4 of the medallion playbook; the
playbook stays authoritative on HOW to decide, the templates on WHAT to record.
## Scope boundary (read first)
This skill profiles a source and authors the mapping artifacts, then STOPS. It
does NOT write `silver.*` or `gold.*` SQL, does NOT call pbi-cli or Power BI
Desktop, and does NOT decide the judgment calls Principle V reserves for a human.bi-analyst-knowledge
When your agent uses it
Analyst-judgment layer for Seshat BI Stage-6 design. Use when turning approved metric contracts + a committed source-profile into a decision-driven report: deriving ranked decision-questions, choosing an analytical framing (trend/anomaly, period variance, contribution & mix-shift, concentration/Pareto, rate decomposition, segment behavior, benchmark/threshold, signal-vs-noise statistical guardrails), and ordering pages into a story (overview, what changed, why/where, action), building grounded diagnostic question trees, reviewing narrative drift, and defining action/review-cadence handoffs BEFORE layout. It teaches HOW to frame approved numbers, never WHAT a metric means. A thinking layer, not a layout engine, chart renderer, metric definer, or owner assigner.
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
1,221 tokensWhen the skill is activated
Reference documents
14,193 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mandatory flow (do not skip a step)
- What this skill is for
- What this skill is NOT for
- Routing boundaries (pick the right skill first)
- Stop rules
Files
INDEX.mddoc6,458 bytesSKILL.mdcore5,282 bytesSKILL.mdcore5,282 bytesaction-and-review-cadence.mddoc1,818 byteschecklists/narrative-judgment-review-checklist.mddoc1,413 bytesderivation-route.mddoc10,810 bytesdiagnostic-question-tree.mddoc2,689 bytesexample-specialty-retail.mddoc9,900 bytesexample-weekly-business-review.mddoc3,189 bytesframing-benchmark-threshold.mddoc1,766 bytesframing-concentration.mddoc1,591 bytesframing-contribution-mix.mddoc1,710 bytesframing-period-variance.mddoc1,947 bytesframing-rate-decomposition.mddoc1,886 bytesframing-segment-behavior.mddoc1,742 bytesframing-signal-vs-noise.mddoc2,816 bytesframing-trend-anomaly.mddoc2,271 bytesnarrative-change-review.mddoc2,011 bytesstatistical-evidence-workflow.mddoc3,105 bytesstory-order.mddoc3,351 bytes
Read SKILL.md
# BI Analyst Knowledge (Seshat BI)
The judgment layer that turns a structurally-correct report into an ANALYSIS. It
sits between semantic-model readiness (F010) and dashboard layout (F011): given
approved contracts and a profiled source, it produces the decision-questions,
framings, and story order a good analyst would -- so a page answers a decision
instead of merely displaying a number.
This file is short by design. **It does not contain the knowledge base.** Do not
read every file. Follow the flow.
## Mandatory flow (do not skip a step)
```textbi-bigdata-knowledge
When your agent uses it
Big-data / distributed-compute reasoning and review layer for BI and data agents in the Seshat BI project. Use when data is too large for single-node pandas and the agent must reason about distributed or larger-than-memory processing — choosing an engine (Spark / Dask / Polars / DuckDB / warehouse), controlling partitioning and shuffle, avoiding skew and fan-out, aggregating at a declared grain at scale, choosing file formats (Parquet / Delta / Iceberg), incremental/idempotent processing, validating and reconciling at scale, diagnosing partial/retried output, reviewing backfills/partition evolution/compaction, and collecting performance/cost evidence. This is a reasoning layer, not an executor or Spark tutorial. It does not run jobs, define metrics, or own gating.
What it loads into context
Frontmatter
186 tokensAlways available to the agent
SKILL.md
1,238 tokensWhen the skill is activated
Reference documents
26,478 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to use this skill
- Use when
- Do not use when
- Boundaries
- Stop rules
- Conventions
Files
INDEX.mddoc6,670 bytesREADME.mddoc3,217 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 byteschecklists/aggregation-grain-checklist.mddoc1,915 byteschecklists/engine-selection-checklist.mddoc1,708 byteschecklists/join-skew-checklist.mddoc1,780 byteschecklists/operational-evidence-checklist.mddoc1,903 byteschecklists/partitioning-shuffle-checklist.mddoc1,741 byteschecklists/pipeline-review-checklist.mddoc3,021 byteschecklists/validation-reconciliation-checklist.mddoc2,243 bytesknowledge/aggregation-and-grain-at-scale.mddoc4,647 bytesknowledge/backfills-and-partition-evolution.mddoc3,473 bytesknowledge/bigdata-anti-patterns.mddoc4,749 bytesknowledge/bigdata-core-concepts-for-bi.mddoc5,636 bytesknowledge/bigdata-retail-examples.mddoc6,222 bytesknowledge/distributed-dataframe-model.mddoc4,851 bytesknowledge/engine-selection.mddoc4,442 bytesknowledge/file-formats-and-storage.mddoc3,651 bytesknowledge/incremental-and-idempotency.mddoc3,953 bytesknowledge/joins-and-skew.mddoc4,842 bytesknowledge/observability-and-partial-failures.mddoc4,051 bytesknowledge/partitioning-and-shuffle.mddoc4,690 bytesknowledge/performance-and-cost.mddoc4,958 bytesknowledge/validation-and-reconciliation-at-scale.mddoc4,520 bytespatterns/analyzer-rule-candidates.jsonasset4,093 bytespatterns/analyzer-rules.jsonasset9,979 bytespatterns/bigdata-patterns.jsonasset3,919 bytespatterns/validation-patterns.jsonasset4,434 bytesreferences/agent-training-set.jsonasset5,931 bytesreferences/agent-training-set.mddoc4,552 bytesreferences/copyright-and-sources.mddoc1,688 bytesreferences/cross-layer-map.mddoc3,915 bytesreferences/id-conventions.mddoc2,466 bytesreferences/research-notes.mddoc3,569 bytesreferences/retail-bigdata-schema.mddoc3,663 bytes
Read SKILL.md
# BI Big-Data Knowledge
A thin router into a distributed / large-scale data-processing reasoning layer for
BI/data agents. It helps an agent **think correctly** about big-data work and **hand off
cleanly** into the SQL, DAX, readiness, and dashboard layers. It does not execute jobs or
define business meaning.
This layer is the scale-out companion to `bi-python-knowledge`. The conceptual spine —
grain, fan-out, additivity, null semantics, reconciliation — is shared and **referenced,
not repeated** (see `references/cross-layer-map.md`). This layer owns only what changes
when compute becomes distributed or larger-than-memory.
## How to use this skill
bi-dax-knowledge
When your agent uses it
DAX knowledge base for teaching a BI agent to reason about, generate, review, and performance-tune DAX for Power BI / tabular models. Use when the task involves writing or auditing DAX measures, building time-intelligence / segmentation / ranking / customer / currency calculations, reviewing a semantic model, diagnosing physical or virtual filter propagation, calculation-group precedence, semi-additive totals, blank/zero semantics, or explaining DAX concepts and pitfalls. Covers core concepts, best practices, anti-patterns, performance notes, a curated pattern library, reusable metric contracts, and analyzer rules.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
1,692 tokensWhen the skill is activated
Reference documents
41,773 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- How to use it (recommended workflow)
- Phases the agent supports
- File map
- Cross-reference scheme
- Scope and boundaries
Files
INDEX.mddoc8,724 bytesREADME.mddoc4,559 bytesSKILL.mdcore7,172 byteschecklists/dax-diagnostic-checklist.mddoc1,566 byteschecklists/dax-measure-review-checklist.mddoc2,732 byteschecklists/dax-model-review-checklist.mddoc2,365 byteschecklists/metric-contract-checklist.mddoc2,378 bytesknowledge/dax-anti-patterns.mddoc5,564 bytesknowledge/dax-best-practices.mddoc5,754 bytesknowledge/dax-calculate-deep-dive.mddoc18,399 bytesknowledge/dax-calculation-groups-and-precedence.mddoc2,880 bytesknowledge/dax-core-concepts.mddoc9,520 bytesknowledge/dax-engine-internals.mddoc8,617 bytesknowledge/dax-evaluation-context-deep-dive.mddoc14,304 bytesknowledge/dax-function-semantics.mddoc15,647 bytesknowledge/dax-performance-diagnostics.mddoc10,014 bytesknowledge/dax-performance-notes.mddoc4,442 bytesknowledge/dax-relationships-and-virtual-filters.mddoc3,465 bytesknowledge/dax-retail-examples.mddoc13,781 bytesknowledge/dax-semi-additive-and-blank-semantics.mddoc3,288 bytespatterns/analyzer-rule-candidates.jsonasset16,240 bytespatterns/analyzer-rules.jsonasset16,155 bytespatterns/dax-patterns.jsonasset29,176 bytespatterns/metric-contract-patterns.jsonasset20,887 bytesreferences/agent-training-set.jsonasset19,080 bytesreferences/agent-training-set.mddoc14,612 bytesreferences/retail-schema.mddoc6,409 bytesreferences/source-map.mddoc7,541 bytes
Read SKILL.md
# BI DAX Knowledge
A teaching + reference layer for a Business Intelligence agent working with DAX. It separates
**explanation** (Markdown, for reasoning and teaching) from **structured rules** (JSON, for
precise generation and automated review).
## When to use this skill
Trigger for any of: writing a DAX measure or calculated column; reviewing/auditing existing
DAX; building time intelligence (YTD, YOY, rolling, running totals), segmentation, ABC, ranking,
new/returning customers, events-in-progress, what-if parameters, or currency conversion;
reviewing a semantic model for DAX prerequisites; or explaining a DAX concept/pitfall.
Also trigger for ambiguous relationship paths, `TREATAS`/virtual-filter defects, interacting
calculation groups, semi-additive snapshot totals, and blank-versus-zero behavior.bi-python-knowledge
When your agent uses it
Python/pandas reasoning and review layer for BI and data agents in the Seshat BI project. Use when an agent must reason about dataframe work — profiling a source, judging dtypes/schema, cleaning and standardizing, merging without fan-out, aggregating at a declared grain, parsing dates, validating/reconciling against SQL and readiness, diagnosing performance/memory, or reviewing a Python pipeline. This is a reasoning layer, not an executor and not a Python tutorial. It does not run pipelines, define metrics, or own gating. See INDEX.md for the live routes.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
826 tokensWhen the skill is activated
Reference documents
19,942 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Use this skill when
- Do not use this skill for
- Mandatory workflow
- What this layer owns
- What this layer does NOT own
- Global stop rules
- Conventions
Files
INDEX.mddoc9,473 bytesREADME.mddoc3,752 bytesSKILL.mdcore3,775 bytesSKILL.mdcore3,775 byteschecklists/aggregation-grain-checklist.mddoc1,732 byteschecklists/cleaning-review-checklist.mddoc3,452 byteschecklists/dataframe-review-checklist.mddoc1,616 byteschecklists/merge-fanout-checklist.mddoc1,111 byteschecklists/python-pipeline-review-checklist.mddoc1,410 byteschecklists/validation-reconciliation-checklist.mddoc1,419 bytesknowledge/cleaning-and-standardization.mddoc5,146 bytesknowledge/dataframe-mental-model.mddoc2,591 bytesknowledge/dates-times-and-calendars.mddoc2,313 bytesknowledge/file-source-grain.mddoc8,530 bytesknowledge/groupby-aggregation-and-grain.mddoc4,507 bytesknowledge/joins-merge-and-fanout.mddoc2,480 bytesknowledge/nulls-missing-values-and-blanks.mddoc2,190 bytesknowledge/pandas-dtypes-and-schema.mddoc2,450 bytesknowledge/performance-and-memory.mddoc2,593 bytesknowledge/profiling-and-source-inspection.mddoc2,511 bytesknowledge/python-anti-patterns.mddoc2,686 bytesknowledge/python-core-concepts-for-bi.mddoc2,294 bytesknowledge/python-retail-examples.mddoc2,674 bytesknowledge/validation-and-reconciliation.mddoc2,743 bytespatterns/analyzer-rule-candidates.jsonasset2,561 bytespatterns/analyzer-rules.jsonasset2,061 bytespatterns/python-patterns.jsonasset2,625 bytespatterns/validation-patterns.jsonasset3,326 bytesreferences/agent-training-set.jsonasset6,280 bytesreferences/agent-training-set.mddoc5,278 bytesreferences/copyright-safety.mddoc1,631 bytesreferences/id-conventions.mddoc2,885 bytesreferences/retail-dataframe-schema.mddoc3,619 bytesreferences/source-map.mddoc1,805 bytes
Read SKILL.md
# BI Python Knowledge Skill
A thin router into a Python/pandas reasoning layer for BI/data agents. It helps an
agent **think correctly** about dataframe work and **hand off cleanly** into the
SQL, DAX, readiness, and dashboard layers. It does not execute code or define
business meaning.
> **Status: core routes live.** Dataframe semantics, profiling, dtypes, missing
> values, cleaning, merge/fan-out, aggregation grain, dates/calendars, validation,
> performance, active-rule review, positive patterns, and pipeline review all resolve
> through `INDEX.md`.
## Use this skill when
bi-sql-knowledge
When your agent uses it
SQL reasoning, validation, reconciliation, transformation, diagnostics, and anti-pattern knowledge layer for Seshat BI agents. Use when a task involves reasoning about source SQL: source profiling, table grain, keys & uniqueness, joins & fan-out amplification, aggregation correctness, COUNT/NULL semantics, deduplication, validation queries, reconciliation queries, silver/gold transformation logic, window/date-time analytics, SQL anti-patterns, or basic SQL performance reasoning, or interpretation of a supplied sanitized PostgreSQL JSON execution plan. The SQL counterpart to bi-dax-knowledge. It is a thinking & validation layer, not a database executor, runtime validator, dbt/Dagster project, or automatic tuning service.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
1,369 tokensWhen the skill is activated
Reference documents
51,907 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mandatory flow (do not skip a step, do not lose the compass)
- What this skill is for
- What this skill is NOT for
- Routing boundaries (pick the right skill before working)
- Stop rules
- ID conventions (full detail in `references/id-conventions.md`)
- Boundaries
Files
INDEX.mddoc10,157 bytesREADME.mddoc4,156 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 byteschecklists/postgresql-plan-review-checklist.mddoc2,383 byteschecklists/sql-reconciliation-checklist.mddoc1,949 byteschecklists/sql-review-checklist.mddoc2,367 byteschecklists/sql-validation-checklist.mddoc2,089 bytesknowledge/postgresql-execution-plans.mddoc5,547 bytesknowledge/sql-aggregation-correctness.mddoc5,724 bytesknowledge/sql-anti-patterns.mddoc28,535 bytesknowledge/sql-cookbook-extension-notes.mddoc19,286 bytesknowledge/sql-core-concepts.mddoc11,163 bytesknowledge/sql-date-time-analysis.mddoc9,562 bytesknowledge/sql-diagnostics-playbook.mddoc15,230 bytesknowledge/sql-grain-and-joins.mddoc10,505 bytesknowledge/sql-logical-query-processing.mddoc3,255 bytesknowledge/sql-performance-notes.mddoc8,384 bytesknowledge/sql-reconciliation-playbook.mddoc11,455 bytesknowledge/sql-transformation-patterns.mddoc16,663 bytesknowledge/sql-window-functions.mddoc10,089 bytespatterns/postgresql-plan-patterns.jsonasset6,247 bytespatterns/sql-analyzer-rule-candidates.jsonasset39,042 bytespatterns/sql-analyzer-rules.jsonasset9,068 bytespatterns/sql-patterns.jsonasset11,876 bytespatterns/sql-validation-patterns.jsonasset7,396 bytesreferences/agent-training-set.jsonasset57,706 bytesreferences/copyright-safety.mddoc2,866 bytesreferences/id-conventions.mddoc4,068 bytesreferences/source-map.mddoc11,683 bytes
Read SKILL.md
# BI SQL Knowledge (Seshat BI)
A navigational interface to a SQL **reasoning and validation** knowledge base. It teaches an
agent to reason about SQL correctly -- with table **grain** and **aggregation correctness** as
its foundation, the way filter context is the foundation of `bi-dax-knowledge`.
This file is short by design. **It does not contain the knowledge base.** Do not read every
file in this skill. Follow the flow below.
## Mandatory flow (do not skip a step, do not lose the compass)
```text
Router -> this SKILL.md -> INDEX.md -> ONLY the relevant file(s) -> output contract / checklist
```retail-kpi-knowledge
When your agent uses it
Retail KPI / metric-contract reasoning layer for BI agents in the Seshat BI project. Use when an agent must reason about the BUSINESS MEANING of a retail KPI before any implementation — defining a KPI in business terms, classifying additivity (fully/semi/non-additive), identifying grain, listing required source fields, resolving ambiguity (gross vs net, VAT, returns, cost method, same-store), choosing an MVP KPI pack, reviewing a metric contract for completeness, or preparing a clean handoff to an implementation layer. Also use it to classify KPI sufficiency or prepare an owner policy decision packet. This is a meaning/definition + review layer, not an executor: it does not write DAX/SQL/Python, grant readiness, approve policy, or design dashboards. See INDEX.md for live/planned routes; registry.yaml is the authoritative machine-readable inventory.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
971 tokensWhen the skill is activated
Reference documents
53,115 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Use when
- Do not use when
- Mandatory workflow
- Boundaries
- Stop rules
Files
INDEX.mddoc9,369 bytesREADME.mddoc5,125 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 byteschecklists/kpi-extension-checklist.mddoc1,533 byteschecklists/kpi-pack-review-checklist.mddoc1,241 byteschecklists/kpi-policy-decision-checklist.mddoc1,239 byteschecklists/metric-ambiguity-checklist.mddoc1,436 byteschecklists/metric-contract-review-checklist.mddoc1,983 bytescontracts/average-basket-size-units.mddoc1,855 bytescontracts/average-transaction-value.mddoc2,665 bytescontracts/discount-amount.mddoc2,489 bytescontracts/discount-rate.mddoc1,960 bytescontracts/discounted-transaction-rate.mddoc2,071 bytescontracts/gross-margin-percent.mddoc1,935 bytescontracts/gross-margin.mddoc2,159 bytescontracts/gross-sales.mddoc2,766 bytescontracts/net-sales-growth.mddoc4,512 bytescontracts/net-sales.mddoc3,015 bytescontracts/quantity-sold.mddoc2,331 bytescontracts/returns-rate-value.mddoc2,852 bytescontracts/same-store-sales-growth.mddoc3,967 bytescontracts/transactions-count.mddoc2,249 bytescontracts/ytd.mddoc4,805 bytesdomains/basket-and-transactions.mddoc3,434 bytesdomains/branch-store-performance.mddoc4,443 bytesdomains/customer.mddoc6,000 bytesdomains/data-quality-control.mddoc3,882 bytesdomains/discounts-and-promotions.mddoc3,934 bytesdomains/inventory.mddoc3,989 bytesdomains/margin-profitability.mddoc3,546 bytesdomains/product-category-performance.mddoc3,796 bytesdomains/returns.mddoc3,770 bytesdomains/sales-and-revenue.mddoc4,006 bytesdomains/targets-and-budgets.mddoc3,304 bytesdomains/time-intelligence.mddoc2,303 bytesknowledge/kpi-additivity-and-grain.mddoc3,243 bytesknowledge/kpi-ambiguities.mddoc3,882 bytesknowledge/kpi-core-concepts.mddoc3,292 bytesknowledge/kpi-sufficiency-and-policy-decisions.mddoc3,150 bytesknowledge/metric-contracts.mddoc3,819 bytesknowledge/retail-kpi-domains.mddoc2,429 bytespacks/branch-performance-pack.mddoc1,720 bytespacks/data-quality-control-room-pack.mddoc1,497 bytespacks/inventory-control-pack.mddoc1,464 bytespacks/mvp-retail-kpi-pack.mddoc3,103 bytespacks/product-performance-pack.mddoc1,619 bytespacks/returns-exceptions-pack.mddoc1,379 bytespacks/sales-performance-pack.mddoc1,710 bytespatterns/metric-anti-patterns.jsonasset3,713 bytespatterns/metric-contract-candidates.jsonasset2,525 bytespatterns/metric-patterns.jsonasset2,244 bytesreferences/enterprise-kpi-knowledge-layer.mddoc73,153 bytesreferences/id-conventions.mddoc2,223 bytesreferences/implementation-handoff-template.mddoc1,367 bytesreferences/kpi-coverage-scorecard-template.mddoc4,986 bytesreferences/kpi-derivation-lineage.mddoc6,093 bytesreferences/metric-contract-template.mddoc2,647 bytesreferences/planned-kpi-backlog.mddoc987 bytesreferences/research-notes.mddoc2,237 bytesreferences/source-field-requirements.mddoc2,802 bytesreferences/source-map.mddoc1,335 bytesregistry.yamlasset13,806 bytes
Read SKILL.md
# Retail KPI Knowledge Skill
A Retail KPI and metric-contract reasoning layer for BI agents. It helps an agent
define, classify, review, and validate retail KPIs **before** any DAX measure, SQL
transformation, or dashboard page is built.
## Purpose
This layer owns the *business meaning* of retail KPIs and the *metric contract* that
must exist before implementation. It produces definitions, additivity and grain calls,
required-field lists, ambiguity flags, validation checks, and a clean handoff to the
DAX / semantic-model layer.
It does **not** produce runtime artifacts. It governs meaning; other layers govern code.bi-analyst-knowledge
When your agent uses it
Use Seshat's public analyst-judgment knowledge to derive decision-questions, choose an analytical framing, and order a story from approved metric contracts and a committed source-profile.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
109 tokensWhen the skill is activated
Reference documents
1,544 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-analyst-knowledge/INDEX.mddoc6,458 bytesSKILL.mdcore477 bytes
Read SKILL.md
# BI Analyst knowledge
Open `../../knowledge/bi-analyst-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Never define metric meaning or invent a
number here; an unanswerable question is a `[GAP]`, not a guess.bi-bigdata-knowledge
When your agent uses it
Use Seshat's public big-data knowledge for distributed aggregation, partitioning, joins, skew, idempotency, reconciliation, performance, and cost reasoning.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
92 tokensWhen the skill is activated
Reference documents
1,629 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-bigdata-knowledge/INDEX.mddoc6,670 bytesSKILL.mdcore427 bytes
Read SKILL.md
# BI big-data knowledge
Open `../../knowledge/bi-bigdata-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Do not select a distributed engine unless
scale and operational evidence justify it.bi-dax-knowledge
When your agent uses it
Use Seshat's public DAX knowledge for metric contracts, evaluation context, measure review, performance reasoning, and semantic-model prerequisites.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
82 tokensWhen the skill is activated
Reference documents
2,021 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-dax-knowledge/INDEX.mddoc8,724 bytesSKILL.mdcore378 bytes
Read SKILL.md
# BI DAX knowledge
Open `../../knowledge/bi-dax-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Do not design visuals or invent business metric
meaning.bi-python-knowledge
When your agent uses it
Use Seshat's public Python knowledge for governed single-node source preparation, cleaning, grain, and aggregation reasoning.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
84 tokensWhen the skill is activated
Reference documents
2,231 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-python-knowledge/INDEX.mddoc9,473 bytesSKILL.mdcore419 bytesSKILL.mdcore419 bytes
Read SKILL.md
# BI Python knowledge
Open `../../knowledge/bi-python-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Do not execute against live data without the user's
explicit in-scope request and required connection boundary.bi-sql-knowledge
When your agent uses it
Use Seshat's public SQL knowledge for source grain, joins, aggregation, validation, reconciliation, and transformation reasoning without executing a database.
What it loads into context
Frontmatter
38 tokensAlways available to the agent
SKILL.md
83 tokensWhen the skill is activated
Reference documents
2,673 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/bi-sql-knowledge/INDEX.mddoc10,157 bytesSKILL.mdcore390 bytesSKILL.mdcore390 bytesSKILL.mdcore390 bytes
Read SKILL.md
# BI SQL knowledge
Open `../../knowledge/bi-sql-knowledge/INDEX.md`, select only the route needed,
and follow its stop rules. Ground the row grain and never infer missing source
facts.business-knowledge-interview
When your agent uses it
After a database is discovered and profiled, interview the business owner to capture the meaning-critical decisions the rest of the Database-to-PBIP flow depends on -- KPI meaning, PII handling, table grain, primary keys, relationships, missing-value rules, and ambiguous financial/quantity/date columns -- and record every outcome in the project Decision Store. Use when someone asks to run the interview, capture business knowledge, or resolve the business questions behind a model in the Seshat BI repo. It asks obvious low-risk items as one batch and critical items individually with explicit named-human approval; it uses masked samples and never shows raw suspected PII by default; it records decisions and STOPS. It does NOT define metric contracts or DAX, does NOT self-grant any approval, and does NOT emit a confidence score.
What it loads into context
Frontmatter
196 tokensAlways available to the agent
SKILL.md
1,311 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Preconditions (stop if unmet)
- How it runs
- Exit
- Hard stops (never)
Files
SKILL.mdcore5,710 bytes
Read SKILL.md
# business-knowledge-interview
The interview is the front door of the Database-to-PBIP flow's decision layer
(spec 121). It converts a discovery profile into recorded, approvable business
decisions so that every downstream stage consumes governed answers instead of
unrecorded assumptions.
Behavior is governed by the `business-knowledge-interview` contract and its
recorded interview protocol. The
static rules DS1-DS5 (`seshat check`) verify the recorded outcome, not the
conversation.
## When to use
dagster-workflows
When your agent uses it
Route Dagster intent to Seshat's governed medallion workflow or the official Dagster competence owner without bypassing readiness, approvals, or evidence.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,386 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intent ownership
- Fixed workflow
- Hard boundaries
- Exit meanings
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore6,021 bytes
Read SKILL.md
# Governed Dagster workflows
Read `../../portable-operating-contract.md` before acting. For a governed
Seshat medallion run, use only the installed `seshat dagster` helpers; never
invoke `dagster` directly against the orchestration project and never bypass
the gate readers, the closed-argv runner, or the redaction layer. Dagster RUNS
already-approved steps; the gate exit code and the named human decide whether
a stage passed.
## Intent ownership
| User intent | Seshat pre-gate | Execution owner | Seshat afterward |
|---|---|---|---|
| Decide whether orchestration fits the BI workflow | Readiness state and orchestration assessment | Seshat selection policy | State one truthful next action |dbt-workflows
When your agent uses it
Route dbt intent to Seshat's governed shadow workflow or the official dbt Labs competence and execution owner, without bypassing readiness or evidence.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,903 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Intent ownership
- Fixed workflow
- The `meta.seshat` model contract
- Hard boundaries
- Exit meanings
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytesSKILL.mdcore8,060 bytes
Read SKILL.md
# Governed dbt workflows
Read `../../portable-operating-contract.md` before acting. For a governed
Seshat shadow workflow, use only the installed `seshat dbt` helpers; never
bypass their fixed selector, target, profile, lock, redaction, or artifact
checks with raw dbt commands.
## Intent ownership
| User intent | Seshat pre-gate | Execution owner | Seshat afterward |
|---|---|---|---|
| Decide whether dbt fits the current BI stage | Readiness and approved-mapping context | Seshat selection policy | State one truthful next action |
| Scaffold governed shadow models | Approved committed source map | Seshat source-map-derived scaffold | Validate citations and the `meta.seshat` contract |
| Governed compile, build, test, or parity | Mapping Ready, exact selector, shadow target, and accepted immutable plan | dbt Core through `seshat dbt` | Normalize artifacts into derived evidence, blockers, and parity findings |first-hour-compass
When your agent uses it
Show a NEW-table author the stateful "you are here / next artifact / authoring skill" orientation card for ONE table in the Seshat BI repo. Use when someone asks "where is this table in the readiness journey", "what do I do next for <table>", or "orient me on a new table". READ-ONLY and invoke-and-present only: it parses that table's mappings/<table>/readiness-status.yaml and RENDERS a single-table orientation card (current stage, the next non-pass stage + the artifact it needs + the authoring skill that produces it, plus recorded STOP rows). It RENDERS recorded state (never recomputes a status, advances a stage, writes a pass, infers/back-fills an approval, or fabricates evidence), runs NO validator, opens NO DB connection, and emits NO numeric health/confidence/percent-ready/maturity score (hard rule #9). It is the STATEFUL single-table sibling of the F026 readiness-viewer (multi-table matrix) and the stateful form of the F006 static onboarding checklist.
What it loads into context
Frontmatter
256 tokensAlways available to the agent
SKILL.md
1,741 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What it does / does NOT do
- How it renders (renders, never re-derives)
- Honest-state rules
- First arrival: offer a worked example as the reference pattern
- The two-condition approval flag
- The four judgment seams (surfaced, never resolved -- Principle V)
- Deltas vs its parents
- Read-only proof
- See also
Files
SKILL.mdcore7,278 bytes
Read SKILL.md
# First-Hour Compass
The stateful single-table orientation card for a new-table author. F024 module class:
**Product Module / `read-only`**. It answers, for ONE table: *where am I, what is the next
artifact, which skill authors it, and what human STOP is recorded?*
## What it does / does NOT do
- **Creates no truth.** It copies recorded fields; it defines no meaning, sets no status.
- **Changes no state.** It edits no file and runs no git mutation (a run leaves `git status`
clean -- see the read-only proof below).
- **Infers no approval.** It never populates, back-fills, or synthesizes an approval; it only
reports whether the next stage's `<stage>-ready.md` names a required owner and whether an
`approvals[]` entry is recorded.kpi-contract-builder
When your agent uses it
Help a human turn a named-but-planned retail KPI into a governed, owner-ready project metric-contract by driving the shipped kpi_contracts engine (spec 124). On first contact, when no approved decisions exist yet, it assesses source answerability, lists the exact Decision Store decisions to get approved via business-knowledge-interview, and renders a preview with per-field provenance -- writing no YAML. Once the approved kpi_definition / policy_ruling decisions, a named eligible owner, and committed source evidence exist, it drives draft_project_metric_contract (a gold-blocked contract) and, after the gold binding is materialized, finalize_project_metric_contract. Use when someone asks to draft, author, or start a metric contract for a planned KPI in the Seshat BI repo. It never invents business meaning, DAX, SQL, gold columns, approvals, owners, a confidence score, or a registry entry; it never promotes a KPI to Seeded and never self-grants an approval.
What it loads into context
Frontmatter
234 tokensAlways available to the agent
SKILL.md
1,620 tokensWhen the skill is activated
Reference documents
751 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- The two-trip flow
- field_provenance (preview only; five-value origin vocabulary)
- Hard stops
Files
SKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 bytesSKILL.mdcore6,727 byteswalkthrough.mddoc3,103 bytes
Read SKILL.md
# kpi-contract-builder
This skill is the agent-facing front door to the shipped `kpi_contracts` stage.
It does NOT reimplement contract authoring: the shipped `kpi_contracts` engine and
its `kpi_answerability` scorecard already exist (spec 124). This skill DRIVES
them and adds the first-contact assessment the engine deliberately refuses to do.
## When to use
- Someone asks to draft / author / start a metric contract for a KPI that the
registry marks `planned` (no seeded contract yet), or for a user-supplied
custom KPI.
- You are at the `kpi_contracts` flow stage (downstream of
`business-knowledge-interview`, upstream of silver/gold model planning).pbi-mcp-doctor
When your agent uses it
Use when a user asks whether or how to wire Microsoft's official Power BI MCP servers into a Seshat BI workspace: run the read-only environment doctor, map a task to the governed Power BI surface (including the official report-authoring skill), generate a safe read-only config template, or run the mocked read-only preflight.
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,441 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Fixed workflow
- The recommendation matrix in plain language
- How to read the advisory records
- What this family will NEVER do
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore6,168 bytesSKILL.mdcore6,168 bytes
Read SKILL.md
# Power BI MCP doctor (read-only)
Read `../../portable-operating-contract.md` before acting. Use only the
installed `seshat pbi-mcp` verbs; never launch an MCP server directly, never
edit `.mcp.json` by hand when the generator can produce it, and never treat
any output of this family as an approval. F016 (the Power BI execution
adapter) is PARKED: no mutation path exists anywhere in this family.
## Fixed workflow
1. Map the user's task to the governed surface, read-only:
`seshat pbi-mcp doctor --repo . --intent <task> [--target <table>] [--harness <claude-code|codex>] [--json] [--write-advisory]`
powerbi-workflows
When your agent uses it
Route guarded Power BI work -- design, native report authoring, semantic-model operations, published queries, QA, bounded formatting, and PBIP adoption -- to the correct Seshat or official Microsoft surface under Seshat BI's gates.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
2,426 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- One front door, explicit execution owners
- Design (dashboards and pages)
- Review and QA
- Reopening Desktop after an external edit
- Theme and backgrounds
- Formatting and geometry
- Semantic measures (handoff)
- Existing PBIP adoption
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore10,678 bytes
Read SKILL.md
# Power BI workflows
Read `../../portable-operating-contract.md` before acting. These routes never
replace readiness gates: no invented metric, measure, KPI, or DAX meaning; no
numeric readiness/confidence score; no self-granted approval; no
dashboard-ready claim without committed evidence.
## One front door, explicit execution owners
This skill is the broad Power BI front door. It owns intent classification and
Seshat's pre/post gates; it does not reproduce Microsoft execution behavior.
For execution-shaped requests, use `seshat pbi-mcp doctor` as the canonical
machine-checkable selector even when the selected owner is an official skill
rather than an MCP server.retail-build-warehouse
When your agent uses it
Author the silver + gold migration SQL for a mapped retail table from its APPROVED source-map, then STOP before executing. Use after a table's mapping gate is CLEARED in the Seshat BI repo and someone asks to build the silver/gold SQL, write the migration, or fill the retail-orchestrate build seam. Author-and-stop: it writes warehouse/migrations/*.sql FILES only, never connects to a database, never applies the SQL, and HARD-STOPS at any judgment call the map does not already answer.
What it loads into context
Frontmatter
130 tokensAlways available to the agent
SKILL.md
2,747 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Author vs execute (read first)
- Preconditions (STOP unless all hold)
- Silver: the load-bearing Phase-5 order (NUMBERED -- do NOT reorder)
- Gold: the Kimball star (Phase 6)
- Judgment stops (fail LOUD -- never satisfy with a silent default)
- After authoring (the handoff)
- Orchestration
- See also
Files
SKILL.mdcore10,297 bytes
Read SKILL.md
# retail-build-warehouse
Turns an APPROVED `mappings/<table>/source-map.yaml` into the two migration `.sql`
files -- `silver` (typed/cleaned flat table) then `gold` (Kimball star) -- in the
order the medallion playbook proves load-bearing. It fills the silver/gold
`[SEAM]` the `retail-orchestrate` conductor parks at.
The agent is the runtime: this is a procedure you follow, authoring SQL by adapting
the proven `warehouse/migrations/0003`/`0004` shape. There is NO codegen engine, NO
`.sql.tmpl` template, and NO `retail build` CLI -- by design (the source-map cannot
carry the transform logic; an engine would emit only boilerplate). That is a
recorded design decision, not an omission to be fixed.
## Author vs execute (read first)retail-discover-portfolio
When your agent uses it
Discover an unfamiliar retail data portfolio before per-table onboarding. Produces one metadata-only Layer-A survey across every reachable table, proposes non-critical domain and first-delivery scope decisions, delegates selected tables to retail-onboard-table for Layer-B profiling, and hands off to the existing business-knowledge-interview. Never samples source values, self-confirms a decision, or advances beyond the interview handoff.
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
1,371 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Boundary
- 1. Produce the Layer-A survey
- 2. Propose a domain
- 3. Propose a bounded first-delivery scope
- 4. Hand off to the existing interview
- Resume and local-stop table
Files
SKILL.mdcore6,543 bytesSKILL.mdcore6,543 bytesSKILL.mdcore6,543 bytes
Read SKILL.md
# retail-discover-portfolio
Use this skill when the owner has an unfamiliar database schema or file folder and
needs a governed route from portfolio discovery to the business interview.
## Boundary
This is an agent-conducted flow, not a new state engine or CLI workflow:
portfolio discovery -> domain -> scope -> selected-table onboarding -> interview handoff -> STOP
- Layer A is the metadata-only portfolio survey in
templates/portfolio-survey.md.
- Layer B is the existing value-backed, per-table Source Ready profile owned byretail-govern
When your agent uses it
Run the Seshat BI governance checker and interpret its findings. Use when someone asks to check, validate, or gate Power BI / DAX / TMDL / PBIR / SQL work in the Seshat BI repo, when `seshat check` reports a rule violation, or when you need to know what a rule id (D8, C2, S2, G1, …) means and where to fix it. Invoke-and-interpret only: this skill does NOT build models, run pbi-cli, or auto-fix — it runs the checker and maps ids to fixes.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
4,420 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope boundary (read this first)
- Run the checker
- Read a finding
- Rule id → meaning → where to fix
- What to do after interpreting
- Orchestration
Scripts executed separately
../../../../../scripts/export_rule_fix_table.py
Files
SKILL.mdcore16,927 bytesSKILL.mdcore16,927 bytesSKILL.mdcore16,927 bytes../../../../../scripts/export_rule_fix_table.pyruns1,977 bytes
Read SKILL.md
# retail-govern
Seshat BI's conventions are enforced by a static checker, `seshat check`. This
skill teaches you to **run it, read its findings, and map each rule id to the file
and fix it points at**. The authoritative catalog is the glossary's "Static check
rules" section, which mirrors the checker's live rule registry; the rules manifest
is the machine-readable inventory. (An older 23-rule governance-layer design doc
is a historical record, NOT the current count -- do not cite it for the catalog.)
## Scope boundary (read this first)
This skill is **invoke-and-interpret only**. It does **not** orchestrate a Power BI
build, does **not** call `pbi-cli` or Power BI Desktop, and does **not** auto-fix or
self-heal violations. Those are deferred D-layer work (spec §9). Here you run theretail-kpi-knowledge
When your agent uses it
Use Seshat's public retail KPI knowledge to define governed metric meaning, additivity, grain, required fields, ambiguity decisions, contracts, and handoffs before implementation.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
104 tokensWhen the skill is activated
Reference documents
2,173 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
../../knowledge/retail-kpi-knowledge/INDEX.mddoc9,369 bytesSKILL.mdcore476 bytes
Read SKILL.md
# Retail KPI knowledge
Open `../../knowledge/retail-kpi-knowledge/INDEX.md`, select only the route
needed, and follow its stop rules. Undefined VAT, returns, cost, same-store, or
snapshot policy is a named-human decision, never an agent default.retail-onboard-table
When your agent uses it
Walk a NEW raw retail table across the FIRST readiness transition -- Source Ready (Stage 1) through Mapping Ready (Stage 2) -- and seed its per-table readiness-status, in the Seshat BI repo. Use when someone says "onboard <schema>.<table>", "take this new table from nothing to a reviewed map", or "start the readiness journey for a table". This is the stage-transition FRONT DOOR: it sequences profile -> map -> gate, writes the readiness-status record, and STOPS at Mapping Ready. It DELEGATES the five mapping artifacts to the `source-mapping` skill (it does not re-implement mapping); it NEVER writes `silver.*` SQL, NEVER self-grants the gate approval, and NEVER answers a Principle-V judgment call (grain, PII, business rollup, product identity).
What it loads into context
Frontmatter
201 tokensAlways available to the agent
SKILL.md
2,452 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope boundary (read first)
- Run-state: read mappings/<table>/ FIRST (no new state file)
- Stage 1 -- Source Ready (profile + PROPOSE semantics)
- Stage 2 -- Mapping Ready (delegate to source-mapping)
- Readiness-status bookkeeping
- Human seams -- HARD-STOP (Principle V; the wizard proposes, a human decides)
- Terminal: Mapping Ready -- STOP
- Deferred-boundary mode (no DSN or no `db` extra)
- Generic, not C086
- See also
- Orchestration
Files
SKILL.mdcore9,948 bytes
Read SKILL.md
# retail-onboard-table
The onboarding front door for ONE table's first two readiness stages. The kit
already ships the verb that authors the mapping artifacts (`source-mapping`) and the
conductor that sequences every verb end-to-end (`retail-orchestrate`). This skill is
the stage-scoped composition between them: "I have a new raw table -- walk me from
nothing to a reviewed map." It advances **Source Ready -> Mapping Ready**, seeds the
per-table `readiness-status.yaml`, and STOPS. It is a procedure the agent performs
(agent-first, Principle I); `seshat check` and the read-only profile are gates it
CALLS, not a CLI subcommand.
## Scope boundary (read first)
- **Agent-first, no CLI.** This is a SKILL the agent runs; it adds no `retail`retail-orchestrate
When your agent uses it
Drive a retail table through the medallion sequence (profile -> map -> gate -> build -> validate -> Power BI) by composing the existing verb-skills, and self-heal against the governance gate's exit code. Use when someone asks to take a table end-to-end, "orchestrate", "run the whole pipeline", or drive the medallion playbook in the Seshat BI repo. The AGENT is the runtime: this skill sequences and instructs; it never spawns a loop runtime, never self-grants the mapping approval, and HARD-STOPS at human judgment calls.
What it loads into context
Frontmatter
144 tokensAlways available to the agent
SKILL.md
2,824 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope + non-negotiables (read first)
- Run-state: read mappings/<table>/ FIRST (no new state file)
- Fixed sequence (delegate to the existing verbs)
- The self-heal loop (a contract you follow; not a runtime)
- Per-rule classification: auto-fixable vs HARD-STOP
- Seams (deferred by design -- report and park, never fake)
- What "done for this slice" looks like
- See also
Files
SKILL.mdcore10,848 bytesSKILL.mdcore10,848 bytes
Read SKILL.md
# retail-orchestrate
The conductor for Layer D. The kit's architecture makes the agent the primary
surface: "an agent runs the playbook conversationally ... and self-heals against
the gate." This skill is how the agent does that -- it **sequences the four
existing verb-skills** across the medallion phases and runs the **self-heal loop**
whose only success signal is a literal gate exit 0.
You (the agent reading this) ARE the runtime. This skill is procedure, not an
engine: there is no daemon, no scheduler, no persisted counter, and no
fix-applying subagent.
## Scope + non-negotiables (read first)
retail-validate
When your agent uses it
Run the LIVE data checks against a materialized retail table and interpret the findings. Use after silver + gold exist for a mapped table in the Seshat BI repo, when someone asks to validate or reconcile a table, or when a V-RC2 / V-RC15 / V-RC16 finding appears. Invoke-and-interpret only: this skill runs `retail validate` against a live Postgres DB and maps each finding id to its fix. It does NOT build models, write SQL, or auto-fix.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,272 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope boundary (read first)
- Prerequisites
- Run it
- Read a finding
- Finding id -> meaning -> where to fix
- Deferred/live-boundary mode (no DSN or no `db` extra)
- What to do after interpreting
- See also
- Orchestration
Files
SKILL.mdcore4,871 bytes
Read SKILL.md
# retail-validate
`seshat check` proves everything provable from committed text. `retail validate`
proves the four things only a running database can show, on the MATERIALIZED rows
(constitution Principle VIII). This skill runs it and
maps each finding to the one place to fix it -- the live sibling of
`retail-govern`.
## Scope boundary (read first)
Invoke-and-interpret only. This skill runs the live checks and explains findings;
it does NOT write or fix silver/gold SQL, does NOT call pbi-cli, and does NOT
auto-loop. The live run needs a DB and is the user's call; you report and stop.
seshat-bi
When your agent uses it
Route a BI project through Seshat BI's governed seven-stage readiness flow. Use when a user asks to inspect a retail source, initialize a Seshat project, find the truthful next action, validate readiness evidence, or stop at the correct human approval gate.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
2,702 tokensWhen the skill is activated
Reference documents
450 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Discovering the surface (no name memorization needed)
- Agent-driven loop (programmatic automation)
- Existing PBIP projects
- Resetting / re-running a project
Files
../../portable-operating-contract.mddoc1,968 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytesSKILL.mdcore11,167 bytes
Read SKILL.md
# Seshat BI
Read `../../portable-operating-contract.md` before acting. Inspect the current
workspace and use installed `seshat` commands when available. If the workspace
has no `AGENTS.md`, this skill's portable operating contract still applies.
For subject reasoning, load only the relevant bundled skill:
- SQL and source grain: `bi-sql-knowledge`
- DAX and semantic measures: `bi-dax-knowledge`
- Python/dataframe preparation: `bi-python-knowledge`
- distributed data: `bi-bigdata-knowledge`
- retail KPI meaning and contracts: `retail-kpi-knowledge`
- decision-questions, framing, and story order from approved metrics:seshat-studio
When your agent uses it
Open Seshat Studio, the local analyst console for ONE Seshat workspace, when someone asks to "open Studio", "show me the workspace", "launch the console", or wants to see readiness, tables, and approvals in a browser instead of a terminal. Studio serves a single pinned workspace on loopback only, reads recorded state, and stops at the same human approval gates as every other Seshat verb. It NEVER grants an approval, advances a stage, writes a pass, invents evidence, or emits a numeric readiness/health/confidence score. It needs the optional `studio` extra; without it the launch is a named refusal with an install remedy, never a traceback. NOT a hosted or shared service, NOT a replacement for the readiness verbs, and NOT a Power BI authoring surface.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
1,672 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Launch it by asking
- What it shows, and what it refuses
- Local only, by construction
- Which agent answers a turn
- Relationship to the readiness verbs
- Troubleshooting
- See also
Files
SKILL.mdcore7,442 bytes
Read SKILL.md
# Seshat Studio
The local analyst console for one Seshat workspace. It presents what the
workspace already records -- readiness by stage, tables, turns, and the
approvals a human still owes -- in a browser, on loopback, for one workspace per
process.
## Launch it by asking
Natural language is the way in. When the user says any of these, launch Studio:
- "open Studio" / "open the Studio console"
- "show me this workspace in the browser"
- "launch the analyst console"source-mapping
When your agent uses it
Drive a raw retail source table through the source-mapping gate before any silver SQL exists. Use when someone asks to map, model, profile, or onboard a new bronze table toward Power BI in the Seshat BI repo -- profile the source, decide grain/PK, fill the five mapping artifacts into mappings/<table>/, and stop at the gate. This skill ENFORCES the rule that no silver.* SQL is written until the map is reviewed and approved. It profiles and authors and stops; it does NOT write silver/gold SQL and does NOT build the Power BI model.
What it loads into context
Frontmatter
143 tokensAlways available to the agent
SKILL.md
2,762 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Scope boundary (read first)
- The five artifacts (write the blanks with `seshat scaffold-source <table>`)
- Cleaning chain (canonical order -- the HYBRID walk)
- Procedure
- Deferred/live-boundary mode (no DSN or no `db` extra)
- See also
- Orchestration
Files
SKILL.mdcore10,729 bytesSKILL.mdcore10,729 bytesSKILL.mdcore10,729 bytesSKILL.mdcore10,729 bytesSKILL.mdcore10,729 bytes
Read SKILL.md
# source-mapping
The source-mapping gate is the kit's one load-bearing rule (constitution
Principle IV): **before any `silver.*` SQL is written, the source MUST be
profiled and mapped into committed, reviewed artifacts.** This skill runs that
gate: profile -> author the five artifacts -> stop at judgment calls -> hard-stop
before silver. It formalizes Phases 1-4 of the medallion playbook; the
playbook stays authoritative on HOW to decide, the templates on WHAT to record.
## Scope boundary (read first)
This skill profiles a source and authors the mapping artifacts, then STOPS. It
does NOT write `silver.*` or `gold.*` SQL, does NOT call pbi-cli or Power BI
Desktop, and does NOT decide the judgment calls Principle V reserves for a human.bi-analyst-knowledge
When your agent uses it
Analyst-judgment layer for Seshat BI Stage-6 design. Use when turning approved metric contracts + a committed source-profile into a decision-driven report: deriving ranked decision-questions, choosing an analytical framing (trend/anomaly, period variance, contribution & mix-shift, concentration/Pareto, rate decomposition, segment behavior, benchmark/threshold, signal-vs-noise statistical guardrails), and ordering pages into a story (overview, what changed, why/where, action), building grounded diagnostic question trees, reviewing narrative drift, and defining action/review-cadence handoffs BEFORE layout. It teaches HOW to frame approved numbers, never WHAT a metric means. A thinking layer, not a layout engine, chart renderer, metric definer, or owner assigner.
What it loads into context
Frontmatter
184 tokensAlways available to the agent
SKILL.md
1,221 tokensWhen the skill is activated
Reference documents
14,193 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mandatory flow (do not skip a step)
- What this skill is for
- What this skill is NOT for
- Routing boundaries (pick the right skill first)
- Stop rules
Files
INDEX.mddoc6,458 bytesSKILL.mdcore5,282 bytesSKILL.mdcore5,282 bytesaction-and-review-cadence.mddoc1,818 byteschecklists/narrative-judgment-review-checklist.mddoc1,413 bytesderivation-route.mddoc10,810 bytesdiagnostic-question-tree.mddoc2,689 bytesexample-specialty-retail.mddoc9,900 bytesexample-weekly-business-review.mddoc3,189 bytesframing-benchmark-threshold.mddoc1,766 bytesframing-concentration.mddoc1,591 bytesframing-contribution-mix.mddoc1,710 bytesframing-period-variance.mddoc1,947 bytesframing-rate-decomposition.mddoc1,886 bytesframing-segment-behavior.mddoc1,742 bytesframing-signal-vs-noise.mddoc2,816 bytesframing-trend-anomaly.mddoc2,271 bytesnarrative-change-review.mddoc2,011 bytesstatistical-evidence-workflow.mddoc3,105 bytesstory-order.mddoc3,351 bytes
Read SKILL.md
# BI Analyst Knowledge (Seshat BI)
The judgment layer that turns a structurally-correct report into an ANALYSIS. It
sits between semantic-model readiness (F010) and dashboard layout (F011): given
approved contracts and a profiled source, it produces the decision-questions,
framings, and story order a good analyst would -- so a page answers a decision
instead of merely displaying a number.
This file is short by design. **It does not contain the knowledge base.** Do not
read every file. Follow the flow.
## Mandatory flow (do not skip a step)
```textbi-bigdata-knowledge
When your agent uses it
Big-data / distributed-compute reasoning and review layer for BI and data agents in the Seshat BI project. Use when data is too large for single-node pandas and the agent must reason about distributed or larger-than-memory processing — choosing an engine (Spark / Dask / Polars / DuckDB / warehouse), controlling partitioning and shuffle, avoiding skew and fan-out, aggregating at a declared grain at scale, choosing file formats (Parquet / Delta / Iceberg), incremental/idempotent processing, validating and reconciling at scale, diagnosing partial/retried output, reviewing backfills/partition evolution/compaction, and collecting performance/cost evidence. This is a reasoning layer, not an executor or Spark tutorial. It does not run jobs, define metrics, or own gating.
What it loads into context
Frontmatter
186 tokensAlways available to the agent
SKILL.md
1,238 tokensWhen the skill is activated
Reference documents
26,478 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to use this skill
- Use when
- Do not use when
- Boundaries
- Stop rules
- Conventions
Files
INDEX.mddoc6,670 bytesREADME.mddoc3,217 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 bytesSKILL.mdcore5,641 byteschecklists/aggregation-grain-checklist.mddoc1,915 byteschecklists/engine-selection-checklist.mddoc1,708 byteschecklists/join-skew-checklist.mddoc1,780 byteschecklists/operational-evidence-checklist.mddoc1,903 byteschecklists/partitioning-shuffle-checklist.mddoc1,741 byteschecklists/pipeline-review-checklist.mddoc3,021 byteschecklists/validation-reconciliation-checklist.mddoc2,243 bytesknowledge/aggregation-and-grain-at-scale.mddoc4,647 bytesknowledge/backfills-and-partition-evolution.mddoc3,473 bytesknowledge/bigdata-anti-patterns.mddoc4,749 bytesknowledge/bigdata-core-concepts-for-bi.mddoc5,636 bytesknowledge/bigdata-retail-examples.mddoc6,222 bytesknowledge/distributed-dataframe-model.mddoc4,851 bytesknowledge/engine-selection.mddoc4,442 bytesknowledge/file-formats-and-storage.mddoc3,651 bytesknowledge/incremental-and-idempotency.mddoc3,953 bytesknowledge/joins-and-skew.mddoc4,842 bytesknowledge/observability-and-partial-failures.mddoc4,051 bytesknowledge/partitioning-and-shuffle.mddoc4,690 bytesknowledge/performance-and-cost.mddoc4,958 bytesknowledge/validation-and-reconciliation-at-scale.mddoc4,520 bytespatterns/analyzer-rule-candidates.jsonasset4,093 bytespatterns/analyzer-rules.jsonasset9,979 bytespatterns/bigdata-patterns.jsonasset3,919 bytespatterns/validation-patterns.jsonasset4,434 bytesreferences/agent-training-set.jsonasset5,931 bytesreferences/agent-training-set.mddoc4,552 bytesreferences/copyright-and-sources.mddoc1,688 bytesreferences/cross-layer-map.mddoc3,915 bytesreferences/id-conventions.mddoc2,466 bytesreferences/research-notes.mddoc3,569 bytesreferences/retail-bigdata-schema.mddoc3,663 bytes
Read SKILL.md
# BI Big-Data Knowledge
A thin router into a distributed / large-scale data-processing reasoning layer for
BI/data agents. It helps an agent **think correctly** about big-data work and **hand off
cleanly** into the SQL, DAX, readiness, and dashboard layers. It does not execute jobs or
define business meaning.
This layer is the scale-out companion to `bi-python-knowledge`. The conceptual spine —
grain, fan-out, additivity, null semantics, reconciliation — is shared and **referenced,
not repeated** (see `references/cross-layer-map.md`). This layer owns only what changes
when compute becomes distributed or larger-than-memory.
## How to use this skill
bi-dax-knowledge
When your agent uses it
DAX knowledge base for teaching a BI agent to reason about, generate, review, and performance-tune DAX for Power BI / tabular models. Use when the task involves writing or auditing DAX measures, building time-intelligence / segmentation / ranking / customer / currency calculations, reviewing a semantic model, diagnosing physical or virtual filter propagation, calculation-group precedence, semi-additive totals, blank/zero semantics, or explaining DAX concepts and pitfalls. Covers core concepts, best practices, anti-patterns, performance notes, a curated pattern library, reusable metric contracts, and analyzer rules.
What it loads into context
Frontmatter
142 tokensAlways available to the agent
SKILL.md
1,692 tokensWhen the skill is activated
Reference documents
41,773 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use this skill
- How to use it (recommended workflow)
- Phases the agent supports
- File map
- Cross-reference scheme
- Scope and boundaries
Files
INDEX.mddoc8,724 bytesREADME.mddoc4,559 bytesSKILL.mdcore7,172 byteschecklists/dax-diagnostic-checklist.mddoc1,566 byteschecklists/dax-measure-review-checklist.mddoc2,732 byteschecklists/dax-model-review-checklist.mddoc2,365 byteschecklists/metric-contract-checklist.mddoc2,378 bytesknowledge/dax-anti-patterns.mddoc5,564 bytesknowledge/dax-best-practices.mddoc5,754 bytesknowledge/dax-calculate-deep-dive.mddoc18,399 bytesknowledge/dax-calculation-groups-and-precedence.mddoc2,880 bytesknowledge/dax-core-concepts.mddoc9,520 bytesknowledge/dax-engine-internals.mddoc8,617 bytesknowledge/dax-evaluation-context-deep-dive.mddoc14,304 bytesknowledge/dax-function-semantics.mddoc15,647 bytesknowledge/dax-performance-diagnostics.mddoc10,014 bytesknowledge/dax-performance-notes.mddoc4,442 bytesknowledge/dax-relationships-and-virtual-filters.mddoc3,465 bytesknowledge/dax-retail-examples.mddoc13,781 bytesknowledge/dax-semi-additive-and-blank-semantics.mddoc3,288 bytespatterns/analyzer-rule-candidates.jsonasset16,240 bytespatterns/analyzer-rules.jsonasset16,154 bytespatterns/dax-patterns.jsonasset29,175 bytespatterns/metric-contract-patterns.jsonasset20,886 bytesreferences/agent-training-set.jsonasset19,079 bytesreferences/agent-training-set.mddoc14,612 bytesreferences/retail-schema.mddoc6,409 bytesreferences/source-map.mddoc7,541 bytes
Read SKILL.md
# BI DAX Knowledge
A teaching + reference layer for a Business Intelligence agent working with DAX. It separates
**explanation** (Markdown, for reasoning and teaching) from **structured rules** (JSON, for
precise generation and automated review).
## When to use this skill
Trigger for any of: writing a DAX measure or calculated column; reviewing/auditing existing
DAX; building time intelligence (YTD, YOY, rolling, running totals), segmentation, ABC, ranking,
new/returning customers, events-in-progress, what-if parameters, or currency conversion;
reviewing a semantic model for DAX prerequisites; or explaining a DAX concept/pitfall.
Also trigger for ambiguous relationship paths, `TREATAS`/virtual-filter defects, interacting
calculation groups, semi-additive snapshot totals, and blank-versus-zero behavior.bi-python-knowledge
When your agent uses it
Python/pandas reasoning and review layer for BI and data agents in the Seshat BI project. Use when an agent must reason about dataframe work — profiling a source, judging dtypes/schema, cleaning and standardizing, merging without fan-out, aggregating at a declared grain, parsing dates, validating/reconciling against SQL and readiness, diagnosing performance/memory, or reviewing a Python pipeline. This is a reasoning layer, not an executor and not a Python tutorial. It does not run pipelines, define metrics, or own gating. See INDEX.md for the live routes.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
826 tokensWhen the skill is activated
Reference documents
19,942 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Use this skill when
- Do not use this skill for
- Mandatory workflow
- What this layer owns
- What this layer does NOT own
- Global stop rules
- Conventions
Files
INDEX.mddoc9,473 bytesREADME.mddoc3,752 bytesSKILL.mdcore3,775 bytesSKILL.mdcore3,775 byteschecklists/aggregation-grain-checklist.mddoc1,732 byteschecklists/cleaning-review-checklist.mddoc3,452 byteschecklists/dataframe-review-checklist.mddoc1,616 byteschecklists/merge-fanout-checklist.mddoc1,111 byteschecklists/python-pipeline-review-checklist.mddoc1,410 byteschecklists/validation-reconciliation-checklist.mddoc1,419 bytesknowledge/cleaning-and-standardization.mddoc5,146 bytesknowledge/dataframe-mental-model.mddoc2,591 bytesknowledge/dates-times-and-calendars.mddoc2,313 bytesknowledge/file-source-grain.mddoc8,530 bytesknowledge/groupby-aggregation-and-grain.mddoc4,507 bytesknowledge/joins-merge-and-fanout.mddoc2,480 bytesknowledge/nulls-missing-values-and-blanks.mddoc2,190 bytesknowledge/pandas-dtypes-and-schema.mddoc2,450 bytesknowledge/performance-and-memory.mddoc2,593 bytesknowledge/profiling-and-source-inspection.mddoc2,511 bytesknowledge/python-anti-patterns.mddoc2,686 bytesknowledge/python-core-concepts-for-bi.mddoc2,294 bytesknowledge/python-retail-examples.mddoc2,674 bytesknowledge/validation-and-reconciliation.mddoc2,743 bytespatterns/analyzer-rule-candidates.jsonasset2,561 bytespatterns/analyzer-rules.jsonasset2,061 bytespatterns/python-patterns.jsonasset2,625 bytespatterns/validation-patterns.jsonasset3,326 bytesreferences/agent-training-set.jsonasset6,280 bytesreferences/agent-training-set.mddoc5,278 bytesreferences/copyright-safety.mddoc1,631 bytesreferences/id-conventions.mddoc2,885 bytesreferences/retail-dataframe-schema.mddoc3,619 bytesreferences/source-map.mddoc1,805 bytes
Read SKILL.md
# BI Python Knowledge Skill
A thin router into a Python/pandas reasoning layer for BI/data agents. It helps an
agent **think correctly** about dataframe work and **hand off cleanly** into the
SQL, DAX, readiness, and dashboard layers. It does not execute code or define
business meaning.
> **Status: core routes live.** Dataframe semantics, profiling, dtypes, missing
> values, cleaning, merge/fan-out, aggregation grain, dates/calendars, validation,
> performance, active-rule review, positive patterns, and pipeline review all resolve
> through `INDEX.md`.
## Use this skill when
bi-sql-knowledge
When your agent uses it
SQL reasoning, validation, reconciliation, transformation, diagnostics, and anti-pattern knowledge layer for Seshat BI agents. Use when a task involves reasoning about source SQL: source profiling, table grain, keys & uniqueness, joins & fan-out amplification, aggregation correctness, COUNT/NULL semantics, deduplication, validation queries, reconciliation queries, silver/gold transformation logic, window/date-time analytics, SQL anti-patterns, or basic SQL performance reasoning, or interpretation of a supplied sanitized PostgreSQL JSON execution plan. The SQL counterpart to bi-dax-knowledge. It is a thinking & validation layer, not a database executor, runtime validator, dbt/Dagster project, or automatic tuning service.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
1,369 tokensWhen the skill is activated
Reference documents
51,907 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Mandatory flow (do not skip a step, do not lose the compass)
- What this skill is for
- What this skill is NOT for
- Routing boundaries (pick the right skill before working)
- Stop rules
- ID conventions (full detail in `references/id-conventions.md`)
- Boundaries
Files
INDEX.mddoc10,157 bytesREADME.mddoc4,156 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 bytesSKILL.mdcore5,897 byteschecklists/postgresql-plan-review-checklist.mddoc2,383 byteschecklists/sql-reconciliation-checklist.mddoc1,949 byteschecklists/sql-review-checklist.mddoc2,367 byteschecklists/sql-validation-checklist.mddoc2,089 bytesknowledge/postgresql-execution-plans.mddoc5,547 bytesknowledge/sql-aggregation-correctness.mddoc5,724 bytesknowledge/sql-anti-patterns.mddoc28,535 bytesknowledge/sql-cookbook-extension-notes.mddoc19,286 bytesknowledge/sql-core-concepts.mddoc11,163 bytesknowledge/sql-date-time-analysis.mddoc9,562 bytesknowledge/sql-diagnostics-playbook.mddoc15,230 bytesknowledge/sql-grain-and-joins.mddoc10,505 bytesknowledge/sql-logical-query-processing.mddoc3,255 bytesknowledge/sql-performance-notes.mddoc8,384 bytesknowledge/sql-reconciliation-playbook.mddoc11,455 bytesknowledge/sql-transformation-patterns.mddoc16,663 bytesknowledge/sql-window-functions.mddoc10,089 bytespatterns/postgresql-plan-patterns.jsonasset6,247 bytespatterns/sql-analyzer-rule-candidates.jsonasset39,042 bytespatterns/sql-analyzer-rules.jsonasset9,068 bytespatterns/sql-patterns.jsonasset11,876 bytespatterns/sql-validation-patterns.jsonasset7,396 bytesreferences/agent-training-set.jsonasset57,706 bytesreferences/copyright-safety.mddoc2,866 bytesreferences/id-conventions.mddoc4,068 bytesreferences/source-map.mddoc11,683 bytes
Read SKILL.md
# BI SQL Knowledge (Seshat BI)
A navigational interface to a SQL **reasoning and validation** knowledge base. It teaches an
agent to reason about SQL correctly -- with table **grain** and **aggregation correctness** as
its foundation, the way filter context is the foundation of `bi-dax-knowledge`.
This file is short by design. **It does not contain the knowledge base.** Do not read every
file in this skill. Follow the flow below.
## Mandatory flow (do not skip a step, do not lose the compass)
```text
Router -> this SKILL.md -> INDEX.md -> ONLY the relevant file(s) -> output contract / checklist
```retail-kpi-knowledge
When your agent uses it
Retail KPI / metric-contract reasoning layer for BI agents in the Seshat BI project. Use when an agent must reason about the BUSINESS MEANING of a retail KPI before any implementation — defining a KPI in business terms, classifying additivity (fully/semi/non-additive), identifying grain, listing required source fields, resolving ambiguity (gross vs net, VAT, returns, cost method, same-store), choosing an MVP KPI pack, reviewing a metric contract for completeness, or preparing a clean handoff to an implementation layer. Also use it to classify KPI sufficiency or prepare an owner policy decision packet. This is a meaning/definition + review layer, not an executor: it does not write DAX/SQL/Python, grant readiness, approve policy, or design dashboards. See INDEX.md for live/planned routes; registry.yaml is the authoritative machine-readable inventory.
What it loads into context
Frontmatter
205 tokensAlways available to the agent
SKILL.md
971 tokensWhen the skill is activated
Reference documents
53,115 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Purpose
- Use when
- Do not use when
- Mandatory workflow
- Boundaries
- Stop rules
Files
INDEX.mddoc9,369 bytesREADME.mddoc5,125 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 bytesSKILL.mdcore4,390 byteschecklists/kpi-extension-checklist.mddoc1,533 byteschecklists/kpi-pack-review-checklist.mddoc1,241 byteschecklists/kpi-policy-decision-checklist.mddoc1,239 byteschecklists/metric-ambiguity-checklist.mddoc1,436 byteschecklists/metric-contract-review-checklist.mddoc1,983 bytescontracts/average-basket-size-units.mddoc1,855 bytescontracts/average-transaction-value.mddoc2,665 bytescontracts/discount-amount.mddoc2,489 bytescontracts/discount-rate.mddoc1,960 bytescontracts/discounted-transaction-rate.mddoc2,071 bytescontracts/gross-margin-percent.mddoc1,935 bytescontracts/gross-margin.mddoc2,159 bytescontracts/gross-sales.mddoc2,766 bytescontracts/net-sales-growth.mddoc4,512 bytescontracts/net-sales.mddoc3,015 bytescontracts/quantity-sold.mddoc2,331 bytescontracts/returns-rate-value.mddoc2,852 bytescontracts/same-store-sales-growth.mddoc3,967 bytescontracts/transactions-count.mddoc2,249 bytescontracts/ytd.mddoc4,805 bytesdomains/basket-and-transactions.mddoc3,434 bytesdomains/branch-store-performance.mddoc4,443 bytesdomains/customer.mddoc6,000 bytesdomains/data-quality-control.mddoc3,882 bytesdomains/discounts-and-promotions.mddoc3,934 bytesdomains/inventory.mddoc3,989 bytesdomains/margin-profitability.mddoc3,546 bytesdomains/product-category-performance.mddoc3,796 bytesdomains/returns.mddoc3,770 bytesdomains/sales-and-revenue.mddoc4,006 bytesdomains/targets-and-budgets.mddoc3,304 bytesdomains/time-intelligence.mddoc2,303 bytesknowledge/kpi-additivity-and-grain.mddoc3,243 bytesknowledge/kpi-ambiguities.mddoc3,882 bytesknowledge/kpi-core-concepts.mddoc3,292 bytesknowledge/kpi-sufficiency-and-policy-decisions.mddoc3,150 bytesknowledge/metric-contracts.mddoc3,819 bytesknowledge/retail-kpi-domains.mddoc2,429 bytespacks/branch-performance-pack.mddoc1,720 bytespacks/data-quality-control-room-pack.mddoc1,497 bytespacks/inventory-control-pack.mddoc1,464 bytespacks/mvp-retail-kpi-pack.mddoc3,103 bytespacks/product-performance-pack.mddoc1,619 bytespacks/returns-exceptions-pack.mddoc1,379 bytespacks/sales-performance-pack.mddoc1,710 bytespatterns/metric-anti-patterns.jsonasset3,713 bytespatterns/metric-contract-candidates.jsonasset2,525 bytespatterns/metric-patterns.jsonasset2,244 bytesreferences/enterprise-kpi-knowledge-layer.mddoc73,153 bytesreferences/id-conventions.mddoc2,223 bytesreferences/implementation-handoff-template.mddoc1,367 bytesreferences/kpi-coverage-scorecard-template.mddoc4,986 bytesreferences/kpi-derivation-lineage.mddoc6,093 bytesreferences/metric-contract-template.mddoc2,647 bytesreferences/planned-kpi-backlog.mddoc987 bytesreferences/research-notes.mddoc2,237 bytesreferences/source-field-requirements.mddoc2,802 bytesreferences/source-map.mddoc1,335 bytesregistry.yamlasset13,806 bytes
Read SKILL.md
# Retail KPI Knowledge Skill
A Retail KPI and metric-contract reasoning layer for BI agents. It helps an agent
define, classify, review, and validate retail KPIs **before** any DAX measure, SQL
transformation, or dashboard page is built.
## Purpose
This layer owns the *business meaning* of retail KPIs and the *metric contract* that
must exist before implementation. It produces definitions, additivity and grain calls,
required-field lists, ambiguity flags, validation checks, and a clean handoff to the
DAX / semantic-model layer.
It does **not** produce runtime artifacts. It governs meaning; other layers govern code.fake-skill
When your agent uses it
A fixture skill with declaring frontmatter, used as positive shipped evidence.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
33 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore149 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
28 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore139 bytes
Read SKILL.md
This file has no YAML frontmatter fence, so it declares nothing about itself.
It must NOT count as evidence of a shipped skill capability.fake-skill
When your agent uses it
A fixture skill with declaring frontmatter, used as positive shipped evidence.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
33 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore149 bytes
fake-skill
When your agent uses it
A fixture skill with declaring frontmatter, used as positive shipped evidence.
What it loads into context
Frontmatter
22 tokensAlways available to the agent
SKILL.md
33 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore149 bytes
Skills included
- bi-analyst-knowledge
- bi-bigdata-knowledge
- bi-dax-knowledge
- bi-python-knowledge
- bi-sql-knowledge
- dagster-workflows
- dbt-workflows
- pbi-mcp-doctor
- powerbi-workflows
- retail-kpi-knowledge
- seshat-bi
- bi-analyst-knowledge
- bi-bigdata-knowledge
- bi-dax-knowledge
- bi-python-knowledge
- bi-sql-knowledge
- retail-kpi-knowledge
- bi-analyst-knowledge
- bi-bigdata-knowledge
- bi-dax-knowledge
- bi-python-knowledge
- bi-sql-knowledge
- business-knowledge-interview
- dagster-workflows
- dbt-workflows
- first-hour-compass
- kpi-contract-builder
- pbi-mcp-doctor
- powerbi-workflows
- retail-build-warehouse
- retail-discover-portfolio
- retail-govern
- retail-kpi-knowledge
- retail-onboard-table
- retail-orchestrate
- retail-validate
- seshat-bi
- seshat-studio
- source-mapping
- bi-analyst-knowledge
- bi-bigdata-knowledge
- bi-dax-knowledge
- bi-python-knowledge
- bi-sql-knowledge
- retail-kpi-knowledge
- bi-analyst-knowledge
- bi-bigdata-knowledge
- bi-dax-knowledge
- bi-python-knowledge
- bi-sql-knowledge
- business-knowledge-interview
- dagster-workflows
- dbt-workflows
- first-hour-compass
- kpi-contract-builder
- pbi-mcp-doctor
- powerbi-workflows
- retail-build-warehouse
- retail-discover-portfolio
- retail-govern
- retail-kpi-knowledge
- retail-onboard-table
- retail-orchestrate
- retail-validate
- seshat-bi
- seshat-studio
- source-mapping
- bi-analyst-knowledge
- bi-bigdata-knowledge
- bi-dax-knowledge
- bi-python-knowledge
- bi-sql-knowledge
- retail-kpi-knowledge
- fake-skill
- fake-skill
- fake-skill
Repository facts
- License
- Apache-2.0
- Created
- Jun 22, 2026
- Last pushed
- Nov 4, 2026
- Forks
- 0
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 156 notes
.claude-plugin/marketplace.json:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/claude/commands/dagster-run.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedintegrations/claude-code/seshat-bi/commands/dagster-run.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notesdistribution/bundle-templates/shared/skills/bi-python-knowledge/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/bi-sql-knowledge/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/bi-sql-knowledge/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notesdistribution/bundle-templates/shared/skills/dbt-workflows/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/dbt-workflows/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/dbt-workflows/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/pbi-mcp-doctor/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notes.claude-plugin/marketplace.json:1Plugin-wide analysis incomplete; see repository notesdistribution/bundle-templates/shared/skills/seshat-bi/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/seshat-bi/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/seshat-bi/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/seshat-bi/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzeddistribution/bundle-templates/shared/skills/seshat-bi/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 155 network referencesin 14 files: bi-bigdata-knowledge/references/research-notes.md:10 bi-bigdata-knowledge/references/research-notes.md:10 bi-bigdata-knowledge/references/research-notes.md:10 and 11 more
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 1 file: scripts/export_rule_fix_table.py:1
- No access to secrets
- No requests to vote in Hot
Show all 157 signals by file
distribution/bundle-templates/claude/.claude-plugin/plugin.json
- Network accessline 4
"description": "Guarded Seshat BI readiness workflow and public knowledge for Claude Code.", "author": {"name": "Ahmed Shaaban"}, "homepage": "https://github.com/Kemetra/Seshat-BI", - Network accessline 5
"author": {"name": "Ahmed Shaaban"}, "homepage": "https://github.com/Kemetra/Seshat-BI", "repository": "https://github.com/Kemetra/Seshat-BI", - Network accessline 6
"homepage": "https://github.com/Kemetra/Seshat-BI", - Network accessline 7
"repository": "https://github.com/Kemetra/Seshat-BI",
integrations/claude-code/seshat-bi/.claude-plugin/plugin.json
- Network accessline 4
"description": "Guarded Seshat BI readiness workflow and public knowledge for Claude Code.", "author": {"name": "Ahmed Shaaban"}, "homepage": "https://github.com/Kemetra/Seshat-BI", - Network accessline 5
"author": {"name": "Ahmed Shaaban"}, "homepage": "https://github.com/Kemetra/Seshat-BI", "repository": "https://github.com/Kemetra/Seshat-BI", - Network accessline 6
"homepage": "https://github.com/Kemetra/Seshat-BI", - Network accessline 7
"repository": "https://github.com/Kemetra/Seshat-BI",
integrations/claude-code/seshat-bi/knowledge/bi-bigdata-knowledge/references/research-notes.md
- Network accessline 10
### Spark performance, shuffle, partition tuning, AQE - Apache Spark — Performance Tuning (official docs): https://spark.apache.org/docs/latest/sql-performance-tuning.html - Network accessline 11
- Apache Spark — Performance Tuning (official docs): https://spark.apache.org/docs/latest/sql-performance-tuning.html - Network accessline 12
- Databricks — Adaptive Query Execution: https://www.databricks.com/blog/2020/05/29/adaptive-query-execution-speeding-up-spark-sql-at-runtime.html - Network accessline 13
- Spark partition tuning (luminousmen): https://luminousmen.com/post/spark-tips-partition-tuning/ - Network accessline 14
- AWS Glue — Optimize shuffles: https://docs.aws.amazon.com/prescriptive-guidance/latest/tuning-aws-glue-for-apache-spark/optimize-shuffles.html - Network accessline 16
### Data skew, salting, broadcast vs shuffle joins - Mitigating data skew in Spark (canadiandataguy): https://www.canadiandataguy.com/p/a-deep-dive-into-skewed-joins-groupby - Network accessline 17
- Mitigating data skew in Spark (canadiandataguy): https://www.canadiandataguy.com/p/a-deep-dive-into-skewed-joins-groupby - Network accessline 18
- Spark joins / broadcast / skew (DataCamp): https://www.datacamp.com/tutorial/pyspark-joins - Network accessline 19
- Accelerating Spark joins (dev.to): https://dev.to/sandeepk27/day-8-accelerating-spark-joins-broadcast-shuffle-optimization-skew-handling-13gd - Network accessline 21
### Anti-patterns: collect()/driver memory, small files, coalesce(1), UDFs - Bringing too much data back to the driver (Spark flowchart): https://holdenk.github.io/spark-flowchart/details/best-pratice-collect/ - Network accessline 22
- Bringing too much data back to the driver (Spark flowchart): https://holdenk.github.io/spark-flowchart/details/best-pratice-collect/ - Network accessline 23
- Top Spark code mistakes (Databricks community): https://community.databricks.com/t5/technical-blog/top-10-code-mistakes-that-degrade-your-spark-performance/ba-p/118468 - Network accessline 24
- Anti-patterns in a PySpark ETL pipeline (Medium): https://medium.com/@ChillData/breaking-the-bottlenecks-lessons-from-anti-patterns-in-our-pyspark-etl-pipeline-660fc297b25e - Network accessline 26
### Single-node engines vs Spark (Polars, DuckDB) - DuckDB vs Polars on large Parquet (codecentric): https://www.codecentric.de/en/knowledge-hub/blog/duckdb-vs-polars-performance-and-memory-with-massive-parquet-data - Network accessline 27
- DuckDB vs Polars on large Parquet (codecentric): https://www.codecentric.de/en/knowledge-hub/blog/duckdb-vs-polars-performance-and-memory-with-massive-parquet-data - Network accessline 28
- 650GB Delta Lake — Polars vs DuckDB vs Spark (data engineering central): https://dataengineeringcentral.substack.com/p/650gb-of-data-delta-lake-on-s3-polars - Network accessline 29
- DuckDB/Polars won't replace Spark (Medium / israeli-tech-radar): https://medium.com/israeli-tech-radar/will-duckdb-replace-spark-maybe-polars-will-9728f6d86c8d - Network accessline 31
### Data quality / reconciliation at scale - Great Expectations — data quality volume: https://greatexpectations.io/blog/exploring-data-quality-volume/ - Network accessline 32
- Great Expectations — data quality volume: https://greatexpectations.io/blog/exploring-data-quality-volume/ - Network accessline 33
- Data quality with PySpark + Great Expectations (Databricks community): https://community.databricks.com/t5/community-articles/data-quality-with-pyspark-and-great-expectations-on-databricks/td-p/128912 - Network accessline 34
- Data quality & reconciliation concepts (Medium / Geeks Data): https://medium.com/geeks-data/data-quality-and-data-reconciliation-in-data-engineering-concepts-and-processes-5672c081d2fa - Network accessline 36
### File / table formats, incremental, idempotency (Parquet, Delta, Iceberg) - Iceberg vs Delta Lake — schema & partition evolution (Flexera): https://www.flexera.com/blog/finops/iceberg-vs-delta-lake-schema-partition/ - Network accessline 37
- Iceberg vs Delta Lake — schema & partition evolution (Flexera): https://www.flexera.com/blog/finops/iceberg-vs-delta-lake-schema-partition/ - Network accessline 38
- Delta / Parquet / Iceberg update guide (Medium): https://medium.com/@shreerajgujar/delta-lake-parquet-or-iceberg-a-guide-to-efficient-data-updates-in-data-lakes-7a5ae8fc80d7 - Network accessline 39
- Iceberg vs Delta Lake (DataCamp): https://www.datacamp.com/blog/iceberg-vs-delta-lake
integrations/claude-code/seshat-bi/knowledge/bi-dax-knowledge/knowledge/dax-function-semantics.md
- Network accessline 8
> file is the per-function reference layer. Examples use the reference retail schema. Original > teaching material — no book text or examples reproduced. For an exhaustive per-function > reference (every argument, every version), defer to h - Network accessline 10
> reference (every argument, every version), defer to https://dax.guide.
integrations/claude-code/seshat-bi/knowledge/bi-dax-knowledge/references/source-map.md
- Network accessline 5
- **DAX Patterns, 2nd edition** — Marco Russo & Alberto Ferrari, SQLBI Corp., 2020. ISBN 978-1-7353652-0-6. Companion site: https://www.daxpatterns.com - Network accessline 6
ISBN 978-1-7353652-0-6. Companion site: https://www.daxpatterns.com - Network accessline 114
- DAX Patterns (book + daxpatterns.com) — full pattern library with all variations. - The Definitive Guide to DAX — deep theory (contexts, engines, optimization). - DAX Guide (https://dax.guide) — per-function reference and return types. - Network accessline 116
- DAX Guide (https://dax.guide) — per-function reference and return types.
integrations/claude-code/seshat-bi/knowledge/retail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md
- Network accessline 942
- [Seshat BI repository](https://github.com/Kemetra/Seshat-BI) - Network accessline 943
- [Retail KPI knowledge router](https://github.com/Kemetra/Seshat-BI/blob/main/skills/retail-kpi-knowledge/INDEX.md) - Network accessline 944
- [Retail KPI registry](https://github.com/Kemetra/Seshat-BI/blob/main/skills/retail-kpi-knowledge/registry.yaml) - Network accessline 945
- [Metric contract template](https://github.com/Kemetra/Seshat-BI/blob/main/templates/metric-contract.yaml) - Network accessline 946
- [KPI pack template](https://github.com/Kemetra/Seshat-BI/blob/main/templates/kpi-pack.yaml) - Network accessline 953
- [ISO 22400-1: manufacturing KPI concepts and terminology](https://www.iso.org/standard/56847.html) - Network accessline 954
- [ASQ quality glossary: OEE definition](https://asq.org/quality-resources/quality-glossary) - Network accessline 955
- [PMI: earned value management](https://www.pmi.org/learning/library/2019/04/07/15/04/earned-value-gauge-components-method-extensions-2512) - Network accessline 956
- [ASCM SCOR Digital Standard introduction](https://www.ascm.org/globalassets/ascm_website_assets/docs/intro-and-front-matter-scor-digital-standard2.pdf) - Network accessline 957
- [APQC: selecting process measures and benchmarks](https://www.apqc.org/resource-library/resource-listing/picking-process-measures-and-benchmarking-how-apply-pcf) - Network accessline 958
- [SEC: guide to financial statements](https://www.sec.gov/about/reports-publications/investorpubsbegfinstmtguide) - Network accessline 959
- [IFRS 18 key terms and management-defined performance measures](https://www.ifrs.org/supporting-implementation/supporting-materials-by-ifrs-standards/ifrs-18/key-terms/) - Network accessline 960
- [Bain: Net Promoter System calculation](https://www.bain.com/contentassets/a0e49354bbe74390831ae2b899be35d1/loyalty_insights_1_introducing_the_net_promoter_system_update.pdf) - Network accessline 961
- [Google Analytics: GA4 engagement and bounce rates](https://support.google.com/analytics/answer/12195621?hl=en) - Network accessline 962
- [ISO 30414:2025 human capital reporting and disclosure](https://www.iso.org/standard/30414) - Network accessline 963
- [GHG Protocol: Corporate Standard FAQ and emissions scopes](https://ghgprotocol.org/corporate-standard-frequently-asked-questions) - Network accessline 964
- [GRI Standards](https://www.globalreporting.org/standards/) - Network accessline 965
- [Klout shutdown record](https://arstechnica.com/information-technology/2018/05/klout-is-out-social-media-mojo-ranking-service-to-shutter/)
integrations/codex/seshat-bi/knowledge/bi-bigdata-knowledge/references/research-notes.md
- Network accessline 10
### Spark performance, shuffle, partition tuning, AQE - Apache Spark — Performance Tuning (official docs): https://spark.apache.org/docs/latest/sql-performance-tuning.html - Network accessline 11
- Apache Spark — Performance Tuning (official docs): https://spark.apache.org/docs/latest/sql-performance-tuning.html - Network accessline 12
- Databricks — Adaptive Query Execution: https://www.databricks.com/blog/2020/05/29/adaptive-query-execution-speeding-up-spark-sql-at-runtime.html - Network accessline 13
- Spark partition tuning (luminousmen): https://luminousmen.com/post/spark-tips-partition-tuning/ - Network accessline 14
- AWS Glue — Optimize shuffles: https://docs.aws.amazon.com/prescriptive-guidance/latest/tuning-aws-glue-for-apache-spark/optimize-shuffles.html - Network accessline 16
### Data skew, salting, broadcast vs shuffle joins - Mitigating data skew in Spark (canadiandataguy): https://www.canadiandataguy.com/p/a-deep-dive-into-skewed-joins-groupby - Network accessline 17
- Mitigating data skew in Spark (canadiandataguy): https://www.canadiandataguy.com/p/a-deep-dive-into-skewed-joins-groupby - Network accessline 18
- Spark joins / broadcast / skew (DataCamp): https://www.datacamp.com/tutorial/pyspark-joins - Network accessline 19
- Accelerating Spark joins (dev.to): https://dev.to/sandeepk27/day-8-accelerating-spark-joins-broadcast-shuffle-optimization-skew-handling-13gd - Network accessline 21
### Anti-patterns: collect()/driver memory, small files, coalesce(1), UDFs - Bringing too much data back to the driver (Spark flowchart): https://holdenk.github.io/spark-flowchart/details/best-pratice-collect/ - Network accessline 22
- Bringing too much data back to the driver (Spark flowchart): https://holdenk.github.io/spark-flowchart/details/best-pratice-collect/ - Network accessline 23
- Top Spark code mistakes (Databricks community): https://community.databricks.com/t5/technical-blog/top-10-code-mistakes-that-degrade-your-spark-performance/ba-p/118468 - Network accessline 24
- Anti-patterns in a PySpark ETL pipeline (Medium): https://medium.com/@ChillData/breaking-the-bottlenecks-lessons-from-anti-patterns-in-our-pyspark-etl-pipeline-660fc297b25e - Network accessline 26
### Single-node engines vs Spark (Polars, DuckDB) - DuckDB vs Polars on large Parquet (codecentric): https://www.codecentric.de/en/knowledge-hub/blog/duckdb-vs-polars-performance-and-memory-with-massive-parquet-data - Network accessline 27
- DuckDB vs Polars on large Parquet (codecentric): https://www.codecentric.de/en/knowledge-hub/blog/duckdb-vs-polars-performance-and-memory-with-massive-parquet-data - Network accessline 28
- 650GB Delta Lake — Polars vs DuckDB vs Spark (data engineering central): https://dataengineeringcentral.substack.com/p/650gb-of-data-delta-lake-on-s3-polars - Network accessline 29
- DuckDB/Polars won't replace Spark (Medium / israeli-tech-radar): https://medium.com/israeli-tech-radar/will-duckdb-replace-spark-maybe-polars-will-9728f6d86c8d - Network accessline 31
### Data quality / reconciliation at scale - Great Expectations — data quality volume: https://greatexpectations.io/blog/exploring-data-quality-volume/ - Network accessline 32
- Great Expectations — data quality volume: https://greatexpectations.io/blog/exploring-data-quality-volume/ - Network accessline 33
- Data quality with PySpark + Great Expectations (Databricks community): https://community.databricks.com/t5/community-articles/data-quality-with-pyspark-and-great-expectations-on-databricks/td-p/128912 - Network accessline 34
- Data quality & reconciliation concepts (Medium / Geeks Data): https://medium.com/geeks-data/data-quality-and-data-reconciliation-in-data-engineering-concepts-and-processes-5672c081d2fa - Network accessline 36
### File / table formats, incremental, idempotency (Parquet, Delta, Iceberg) - Iceberg vs Delta Lake — schema & partition evolution (Flexera): https://www.flexera.com/blog/finops/iceberg-vs-delta-lake-schema-partition/ - Network accessline 37
- Iceberg vs Delta Lake — schema & partition evolution (Flexera): https://www.flexera.com/blog/finops/iceberg-vs-delta-lake-schema-partition/ - Network accessline 38
- Delta / Parquet / Iceberg update guide (Medium): https://medium.com/@shreerajgujar/delta-lake-parquet-or-iceberg-a-guide-to-efficient-data-updates-in-data-lakes-7a5ae8fc80d7 - Network accessline 39
- Iceberg vs Delta Lake (DataCamp): https://www.datacamp.com/blog/iceberg-vs-delta-lake
integrations/codex/seshat-bi/knowledge/bi-dax-knowledge/knowledge/dax-function-semantics.md
- Network accessline 8
> file is the per-function reference layer. Examples use the reference retail schema. Original > teaching material — no book text or examples reproduced. For an exhaustive per-function > reference (every argument, every version), defer to h - Network accessline 10
> reference (every argument, every version), defer to https://dax.guide.
integrations/codex/seshat-bi/knowledge/bi-dax-knowledge/references/source-map.md
- Network accessline 5
- **DAX Patterns, 2nd edition** — Marco Russo & Alberto Ferrari, SQLBI Corp., 2020. ISBN 978-1-7353652-0-6. Companion site: https://www.daxpatterns.com - Network accessline 6
ISBN 978-1-7353652-0-6. Companion site: https://www.daxpatterns.com - Network accessline 114
- DAX Patterns (book + daxpatterns.com) — full pattern library with all variations. - The Definitive Guide to DAX — deep theory (contexts, engines, optimization). - DAX Guide (https://dax.guide) — per-function reference and return types. - Network accessline 116
- DAX Guide (https://dax.guide) — per-function reference and return types.
integrations/codex/seshat-bi/knowledge/retail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md
- Network accessline 942
- [Seshat BI repository](https://github.com/Kemetra/Seshat-BI) - Network accessline 943
- [Retail KPI knowledge router](https://github.com/Kemetra/Seshat-BI/blob/main/skills/retail-kpi-knowledge/INDEX.md) - Network accessline 944
- [Retail KPI registry](https://github.com/Kemetra/Seshat-BI/blob/main/skills/retail-kpi-knowledge/registry.yaml) - Network accessline 945
- [Metric contract template](https://github.com/Kemetra/Seshat-BI/blob/main/templates/metric-contract.yaml) - Network accessline 946
- [KPI pack template](https://github.com/Kemetra/Seshat-BI/blob/main/templates/kpi-pack.yaml) - Network accessline 953
- [ISO 22400-1: manufacturing KPI concepts and terminology](https://www.iso.org/standard/56847.html) - Network accessline 954
- [ASQ quality glossary: OEE definition](https://asq.org/quality-resources/quality-glossary) - Network accessline 955
- [PMI: earned value management](https://www.pmi.org/learning/library/2019/04/07/15/04/earned-value-gauge-components-method-extensions-2512) - Network accessline 956
- [ASCM SCOR Digital Standard introduction](https://www.ascm.org/globalassets/ascm_website_assets/docs/intro-and-front-matter-scor-digital-standard2.pdf) - Network accessline 957
- [APQC: selecting process measures and benchmarks](https://www.apqc.org/resource-library/resource-listing/picking-process-measures-and-benchmarking-how-apply-pcf) - Network accessline 958
- [SEC: guide to financial statements](https://www.sec.gov/about/reports-publications/investorpubsbegfinstmtguide) - Network accessline 959
- [IFRS 18 key terms and management-defined performance measures](https://www.ifrs.org/supporting-implementation/supporting-materials-by-ifrs-standards/ifrs-18/key-terms/) - Network accessline 960
- [Bain: Net Promoter System calculation](https://www.bain.com/contentassets/a0e49354bbe74390831ae2b899be35d1/loyalty_insights_1_introducing_the_net_promoter_system_update.pdf) - Network accessline 961
- [Google Analytics: GA4 engagement and bounce rates](https://support.google.com/analytics/answer/12195621?hl=en) - Network accessline 962
- [ISO 30414:2025 human capital reporting and disclosure](https://www.iso.org/standard/30414) - Network accessline 963
- [GHG Protocol: Corporate Standard FAQ and emissions scopes](https://ghgprotocol.org/corporate-standard-frequently-asked-questions) - Network accessline 964
- [GRI Standards](https://www.globalreporting.org/standards/) - Network accessline 965
- [Klout shutdown record](https://arstechnica.com/information-technology/2018/05/klout-is-out-social-media-mojo-ranking-service-to-shutter/)
scripts/export_rule_fix_table.py
skills/bi-bigdata-knowledge/references/research-notes.md
- Network accessline 10
### Spark performance, shuffle, partition tuning, AQE - Apache Spark — Performance Tuning (official docs): https://spark.apache.org/docs/latest/sql-performance-tuning.html - Network accessline 11
- Apache Spark — Performance Tuning (official docs): https://spark.apache.org/docs/latest/sql-performance-tuning.html - Network accessline 12
- Databricks — Adaptive Query Execution: https://www.databricks.com/blog/2020/05/29/adaptive-query-execution-speeding-up-spark-sql-at-runtime.html - Network accessline 13
- Spark partition tuning (luminousmen): https://luminousmen.com/post/spark-tips-partition-tuning/ - Network accessline 14
- AWS Glue — Optimize shuffles: https://docs.aws.amazon.com/prescriptive-guidance/latest/tuning-aws-glue-for-apache-spark/optimize-shuffles.html - Network accessline 16
### Data skew, salting, broadcast vs shuffle joins - Mitigating data skew in Spark (canadiandataguy): https://www.canadiandataguy.com/p/a-deep-dive-into-skewed-joins-groupby - Network accessline 17
- Mitigating data skew in Spark (canadiandataguy): https://www.canadiandataguy.com/p/a-deep-dive-into-skewed-joins-groupby - Network accessline 18
- Spark joins / broadcast / skew (DataCamp): https://www.datacamp.com/tutorial/pyspark-joins - Network accessline 19
- Accelerating Spark joins (dev.to): https://dev.to/sandeepk27/day-8-accelerating-spark-joins-broadcast-shuffle-optimization-skew-handling-13gd - Network accessline 21
### Anti-patterns: collect()/driver memory, small files, coalesce(1), UDFs - Bringing too much data back to the driver (Spark flowchart): https://holdenk.github.io/spark-flowchart/details/best-pratice-collect/ - Network accessline 22
- Bringing too much data back to the driver (Spark flowchart): https://holdenk.github.io/spark-flowchart/details/best-pratice-collect/ - Network accessline 23
- Top Spark code mistakes (Databricks community): https://community.databricks.com/t5/technical-blog/top-10-code-mistakes-that-degrade-your-spark-performance/ba-p/118468 - Network accessline 24
- Anti-patterns in a PySpark ETL pipeline (Medium): https://medium.com/@ChillData/breaking-the-bottlenecks-lessons-from-anti-patterns-in-our-pyspark-etl-pipeline-660fc297b25e - Network accessline 26
### Single-node engines vs Spark (Polars, DuckDB) - DuckDB vs Polars on large Parquet (codecentric): https://www.codecentric.de/en/knowledge-hub/blog/duckdb-vs-polars-performance-and-memory-with-massive-parquet-data - Network accessline 27
- DuckDB vs Polars on large Parquet (codecentric): https://www.codecentric.de/en/knowledge-hub/blog/duckdb-vs-polars-performance-and-memory-with-massive-parquet-data - Network accessline 28
- 650GB Delta Lake — Polars vs DuckDB vs Spark (data engineering central): https://dataengineeringcentral.substack.com/p/650gb-of-data-delta-lake-on-s3-polars - Network accessline 29
- DuckDB/Polars won't replace Spark (Medium / israeli-tech-radar): https://medium.com/israeli-tech-radar/will-duckdb-replace-spark-maybe-polars-will-9728f6d86c8d - Network accessline 31
### Data quality / reconciliation at scale - Great Expectations — data quality volume: https://greatexpectations.io/blog/exploring-data-quality-volume/ - Network accessline 32
- Great Expectations — data quality volume: https://greatexpectations.io/blog/exploring-data-quality-volume/ - Network accessline 33
- Data quality with PySpark + Great Expectations (Databricks community): https://community.databricks.com/t5/community-articles/data-quality-with-pyspark-and-great-expectations-on-databricks/td-p/128912 - Network accessline 34
- Data quality & reconciliation concepts (Medium / Geeks Data): https://medium.com/geeks-data/data-quality-and-data-reconciliation-in-data-engineering-concepts-and-processes-5672c081d2fa - Network accessline 36
### File / table formats, incremental, idempotency (Parquet, Delta, Iceberg) - Iceberg vs Delta Lake — schema & partition evolution (Flexera): https://www.flexera.com/blog/finops/iceberg-vs-delta-lake-schema-partition/ - Network accessline 37
- Iceberg vs Delta Lake — schema & partition evolution (Flexera): https://www.flexera.com/blog/finops/iceberg-vs-delta-lake-schema-partition/ - Network accessline 38
- Delta / Parquet / Iceberg update guide (Medium): https://medium.com/@shreerajgujar/delta-lake-parquet-or-iceberg-a-guide-to-efficient-data-updates-in-data-lakes-7a5ae8fc80d7 - Network accessline 39
- Iceberg vs Delta Lake (DataCamp): https://www.datacamp.com/blog/iceberg-vs-delta-lake
skills/bi-dax-knowledge/knowledge/dax-function-semantics.md
- Network accessline 8
> file is the per-function reference layer. Examples use the reference retail schema. Original > teaching material — no book text or examples reproduced. For an exhaustive per-function > reference (every argument, every version), defer to h - Network accessline 10
> reference (every argument, every version), defer to https://dax.guide.
skills/bi-dax-knowledge/references/source-map.md
- Network accessline 5
- **DAX Patterns, 2nd edition** — Marco Russo & Alberto Ferrari, SQLBI Corp., 2020. ISBN 978-1-7353652-0-6. Companion site: https://www.daxpatterns.com - Network accessline 6
ISBN 978-1-7353652-0-6. Companion site: https://www.daxpatterns.com - Network accessline 114
- DAX Patterns (book + daxpatterns.com) — full pattern library with all variations. - The Definitive Guide to DAX — deep theory (contexts, engines, optimization). - DAX Guide (https://dax.guide) — per-function reference and return types. - Network accessline 116
- DAX Guide (https://dax.guide) — per-function reference and return types.
skills/retail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md
- Network accessline 942
- [Seshat BI repository](https://github.com/Kemetra/Seshat-BI) - Network accessline 943
- [Retail KPI knowledge router](https://github.com/Kemetra/Seshat-BI/blob/main/skills/retail-kpi-knowledge/INDEX.md) - Network accessline 944
- [Retail KPI registry](https://github.com/Kemetra/Seshat-BI/blob/main/skills/retail-kpi-knowledge/registry.yaml) - Network accessline 945
- [Metric contract template](https://github.com/Kemetra/Seshat-BI/blob/main/templates/metric-contract.yaml) - Network accessline 946
- [KPI pack template](https://github.com/Kemetra/Seshat-BI/blob/main/templates/kpi-pack.yaml) - Network accessline 953
- [ISO 22400-1: manufacturing KPI concepts and terminology](https://www.iso.org/standard/56847.html) - Network accessline 954
- [ASQ quality glossary: OEE definition](https://asq.org/quality-resources/quality-glossary) - Network accessline 955
- [PMI: earned value management](https://www.pmi.org/learning/library/2019/04/07/15/04/earned-value-gauge-components-method-extensions-2512) - Network accessline 956
- [ASCM SCOR Digital Standard introduction](https://www.ascm.org/globalassets/ascm_website_assets/docs/intro-and-front-matter-scor-digital-standard2.pdf) - Network accessline 957
- [APQC: selecting process measures and benchmarks](https://www.apqc.org/resource-library/resource-listing/picking-process-measures-and-benchmarking-how-apply-pcf) - Network accessline 958
- [SEC: guide to financial statements](https://www.sec.gov/about/reports-publications/investorpubsbegfinstmtguide) - Network accessline 959
- [IFRS 18 key terms and management-defined performance measures](https://www.ifrs.org/supporting-implementation/supporting-materials-by-ifrs-standards/ifrs-18/key-terms/) - Network accessline 960
- [Bain: Net Promoter System calculation](https://www.bain.com/contentassets/a0e49354bbe74390831ae2b899be35d1/loyalty_insights_1_introducing_the_net_promoter_system_update.pdf) - Network accessline 961
- [Google Analytics: GA4 engagement and bounce rates](https://support.google.com/analytics/answer/12195621?hl=en) - Network accessline 962
- [ISO 30414:2025 human capital reporting and disclosure](https://www.iso.org/standard/30414) - Network accessline 963
- [GHG Protocol: Corporate Standard FAQ and emissions scopes](https://ghgprotocol.org/corporate-standard-frequently-asked-questions) - Network accessline 964
- [GRI Standards](https://www.globalreporting.org/standards/) - Network accessline 965
- [Klout shutdown record](https://arstechnica.com/information-technology/2018/05/klout-is-out-social-media-mojo-ranking-service-to-shutter/)
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 149 facts
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:10Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:11Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:12Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:13Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:14Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:16Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:17Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:18Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:19Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:21Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:22Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:23Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:24Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:26Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:27Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:28Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:29Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:31Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:32Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:33Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:34Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:36Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:37Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:38Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:39Low confidence
- Network access in prose of documentationbi-dax-knowledge/knowledge/dax-function-semantics.md:8Low confidence
- Network access in prose of documentationbi-dax-knowledge/knowledge/dax-function-semantics.md:10Low confidence
- Network access in prose of documentationbi-dax-knowledge/references/source-map.md:5Low confidence
- Network access in prose of documentationbi-dax-knowledge/references/source-map.md:6Low confidence
- Network access in prose of documentationbi-dax-knowledge/references/source-map.md:114Low confidence
- Network access in prose of documentationbi-dax-knowledge/references/source-map.md:116Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:942Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:943Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:944Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:945Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:946Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:953Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:954Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:955Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:956Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:957Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:958Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:959Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:960Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:961Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:962Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:963Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:964Low confidence
- Network access in prose of documentationretail-kpi-knowledge/references/enterprise-kpi-knowledge-layer.md:965Low confidence
- Network access in prose of documentationbi-bigdata-knowledge/references/research-notes.md:10Low confidence
and 99 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md distribution/bundle-templates/shared/skills/bi-analyst-knowledge/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md distribution/bundle-templates/shared/skills/bi-analyst-knowledge/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md distribution/bundle-templates/shared/skills/bi-analyst-knowledge/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md distribution/bundle-templates/shared/skills/bi-analyst-knowledge/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
