[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JHMXQ5YQQQKB7P2MDAKPT":3,"skill-same:01M77JHMXQ5YQQQKB7P2MDAKPT":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M77JHMXQ5YQQQKB7P2MDAKPT","seshat-bi",null,"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.","Kemetra\u002FSeshat-BI","Kemetra","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F206601658?v=4","01M77J5APND9QAJK8XMBH5B1A8","01M77J5AR4TM1GN2G4GS5KH02J",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Fdistribution\u002Fbundle-templates\u002Fshared\u002Fskills\u002Fseshat-bi\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: seshat-bi\ndescription: >-\n  Route a BI project through Seshat BI's governed seven-stage readiness flow.\n  Use when a user asks to inspect a retail source, initialize a Seshat project,\n  find the truthful next action, validate readiness evidence, or stop at the\n  correct human approval gate.\n---\n\n# Seshat BI\n\nRead `..\u002F..\u002Fportable-operating-contract.md` before acting. Inspect the current\nworkspace and use installed `seshat` commands when available. If the workspace\nhas no `AGENTS.md`, this skill's portable operating contract still applies.\n\nFor subject reasoning, load only the relevant bundled skill:\n\n- SQL and source grain: `bi-sql-knowledge`\n- DAX and semantic measures: `bi-dax-knowledge`\n- Python\u002Fdataframe preparation: `bi-python-knowledge`\n- distributed data: `bi-bigdata-knowledge`\n- retail KPI meaning and contracts: `retail-kpi-knowledge`\n- decision-questions, framing, and story order from approved metrics:\n  `bi-analyst-knowledge`\n- Power BI design, review, theme, formatting, and PBIP adoption:\n  `powerbi-workflows`\n- governed dbt prerequisite, plan, shadow build, and evidence review:\n  `dbt-workflows`\n- governed Dagster preflight, gated medallion runs, and run-evidence review:\n  `dagster-workflows`\n- read-only Power BI MCP doctor, surface recommendation, and preflight:\n  `pbi-mcp-doctor`\n\nThe ten readiness verbs, in flow order. Each owns one stage transition and stops\nat its own gate; none of them self-grants an approval:\n\n- orient a new table on one card: `first-hour-compass`\n- sequence a table end to end and self-heal against the gate:\n  `retail-orchestrate`\n- discover a database metadata-only and propose governed scope:\n  `retail-discover-portfolio`\n- take a raw table from Source Ready to Mapping Ready: `retail-onboard-table`\n- interview the owner into the Decision Store: `business-knowledge-interview`\n- drive a raw table through the mapping gate: `source-mapping`\n- author an owner-ready metric contract: `kpi-contract-builder`\n- author the silver and gold migration SQL, then stop: `retail-build-warehouse`\n- run the static governance checker and read its findings: `retail-govern`\n- run the live data checks on materialized rows: `retail-validate`\n\nNot a readiness verb, but the surface a user asks for by name: to open the local\nanalyst console for one workspace in a browser -- readiness, tables, and the\napprovals a human still owes -- load `seshat-studio`. It renders recorded state\nand stops at the same gates; it grants no approval and advances no stage.\n\nEnd with one next action or one blocked stop. Cite evidence and named blockers;\nnever invent a pass or score.\n\n## Discovering the surface (no name memorization needed)\n\nA user or agent only needs this skill's name; everything else self-describes:\n\n- On Claude Code, `\u002Fseshat-bi:help` prints the full installed command map; on\n  Codex, the routing list above IS the map (there are no Codex slash\n  commands).\n- `seshat --help` lists every installed CLI verb, and\n  `seshat next --format agent` returns the one machine-readable governed next\n  action -- always prefer it over guessing a verb or a stage.\n- Use only the commands, verbs, and skill names those surfaces report; never\n  invent a name, and if `seshat` is not installed, say so and point to\n  `pipx install seshat-bi` instead of simulating output.\n\n## Agent-driven loop (programmatic automation)\n\nFor fully programmatic automation, the optional read-only MCP governor\n(`seshat mcp --repo \u003Cworkspace>`, installed via `pipx install \"seshat-bi[mcp]\"`)\nexposes six tools: `seshat_get_status`, `seshat_get_next_action`,\n`seshat_explain_blockers`, `seshat_prepare_approval_request`,\n`seshat_run_static_check`, and `seshat_export_evidence_pack`.\n\nThe governed loop is: get the next action, perform exactly that one action,\nre-run the static check, and repeat. When the next action is a named-human\ndecision, call `seshat_prepare_approval_request` to package it and STOP -- no\ntool in this loop grants an approval, advances a stage, or emits a score, and\nthe loop must never route around a blocked gate.\n\n## Existing PBIP projects\n\nFor an existing Power BI Project, first use the installed read-only entry path:\n\n```powershell\nseshat adopt-pbip assess --project \u003CPBIP-project-directory> --format text\n```\n\nTreat PBIP structure as candidate evidence only. The assessment must not create\nor approve mappings, metrics, business meaning, or readiness passes. It returns\none governed next action and an assessment digest. A `.pbix` is a conversion\nboundary: save it as PBIP in Power BI Desktop before continuing.\n\nOnly after a human reviews the exact digest, and only in a clean existing Git\nworktree, may the agent run:\n\n```powershell\nseshat adopt-pbip scaffold --project \u003CPBIP-project-directory> --accept-assessment \u003Cassessment-digest>\n```\n\nThis writes at most `.seshat\u002Fadoption\u002Fpbip-adoption.yaml`; it never initializes\nGit, overwrites existing files, grants approval, or advances readiness.\n\n## Resetting \u002F re-running a project\n\nUse the native verb first: `seshat reset \u003Ctable>` removes the complete derived\nfile-set for ONE table (its `mappings\u002F\u003Ctable>\u002F` incl. `dbt-evidence\u002F`, the\nexact-token silver\u002Fgold migrations, the three nested `dbt\u002Fmodels\u002F*\u002F\u003Ctable>\u002F`\nfolders, only this table's rows in the shared dbt files, and the table-scoped\ndagster run evidence under `.seshat\u002Fdagster\u002Fruns\u002F`), preserves the bronze\nlanding, and STAGES the deletions so `seshat check` runs clean afterwards. It\nnever touches a live database.\n\n```powershell\nseshat reset \u003Ctable> --dry-run   # print the exact plan first (writes nothing)\nseshat reset \u003Ctable>             # interactive confirm; --yes for automation\nseshat next --table \u003Ctable>      # should now report a fresh Source stage\n```\n\nRefusals exit non-zero with a named reason (an unsafe table name, a symlinked\npath, a shared dbt file the surgical row-edit cannot verify -- hand-edit that\nfile, then retry). In a non-interactive shell, pass `--yes` or the verb refuses\nrather than hanging.\n\nThe MANUAL checklist below is the fallback for when the verb refuses or is\nunavailable.\n\n**STOP first -- two cases neither the verb nor this manual reset covers; hand\nthem to the owner rather than deleting blindly:**\n\n1. **Shared conformed dimension.** If this table OWNS a conformed dimension that\n   another star reuses, the marts directory the dbt adapter generates for it holds\n   the sole dbt model\n   the reuser resolves via `ref()` (the kit emits no duplicate model for\n   non-owners). Deleting the marts folder would break the other star's build.\n   Check the conformed-dimension map, creating the file if absent: if this table is the OWNER\n   of any dimension listed with other-star reusers, **do not run this manual\n   reset** -- ownership transfer \u002F dependent regeneration is an owner decision.\n2. **Downstream Power BI artifacts.** If this table reached Semantic Model or\n   Dashboard, committed `powerbi\u002F*.SemanticModel` \u002F report artifacts still point\n   at the gold objects you are about to remove. This checklist does NOT rewrite\n   or quarantine them -- leaving them would let Power BI keep reading stale gold\n   while `seshat next` reports Source. If a `powerbi\u002F` artifact references this\n   table's gold entities, **stop and hand the PBIP teardown to the owner** (a\n   shared semantic model especially must be handled explicitly, never bulk\n   deleted).\n\nIf neither case applies (no conformed-dimension ownership, no downstream PBIP),\nthis table's artifacts are table-local and the reset is safe -- prefer\n`seshat reset \u003Ctable>` above; the manual fallback follows.\n\nFirst LIST what you are about to remove and confirm every path is for THIS\ntable -- never delete by a bare `\u003Ctable>*` wildcard. A prefix wildcard is\ndangerous when one table id is a prefix of another (e.g. `orders` also matches\n`orders_archive`): `*_create_silver_\u003Ctable>*.sql` would sweep the other table's\nmigrations too, and a later broad `git add` would then stage that unrelated data\nloss. Enumerate the exact migration files and eyeball them before removing:\n\n```powershell\n# 1. Enumerate the migration SQL for THIS table -- review the list first.\nGet-ChildItem warehouse\u002Fmigrations |\n  Where-Object { $_.Name -match \"_create_(silver|gold)_\u003Ctable>(_|\\.)\" }\n```\n\nOnce the list is confirmed to contain only this table's files, remove the\nderived artifacts (exact per-table paths, not prefix globs):\n\n```powershell\nRemove-Item -Recurse -Force mappings\u002F\u003Ctable>\n# remove ONLY the confirmed migration files from the list above, e.g.:\nRemove-Item -Force warehouse\u002Fmigrations\u002F0003_create_silver_\u003Ctable>.sql\nRemove-Item -Force warehouse\u002Fmigrations\u002F0004_create_gold_\u003Ctable>_star.sql\nRemove-Item -Recurse -Force dbt\u002Fmodels\u002Fstaging\u002F\u003Ctable>\nRemove-Item -Recurse -Force dbt\u002Fmodels\u002Fmarts\u002F\u003Ctable>\nRemove-Item -Recurse -Force dbt\u002Fmodels\u002Faudit\u002F\u003Ctable>\n```\n\nThis covers `mappings\u002F\u003Ctable>\u002F` (including its nested `dbt-evidence\u002F`\nsubfolder -- it lives under the mapping directory, not as a separate\ntop-level path), the silver and gold migration SQL for that table (plus any\ngenerated `warehouse\u002Fgold\u002F` or `warehouse\u002Fschema\u002F` outputs), and the three\nper-table dbt model folders. Do not touch the bronze landing. In a multi-table\nworkspace, also confirm the shared dbt files (`dbt\u002Fmodels\u002Fsources\u002F_sources.yml`,\n`dbt\u002Fselectors.yml`) no longer reference this table's gold entities -- edit out\nonly this table's rows, leaving other tables' rows intact.\n\nThe materialized dagster project under `orchestration\u002Fdagster\u002F` is\nregenerable rather than hand-edited; if it references the removed table,\nregenerate it with `seshat dagster init`.\n\nStage the deletions before running `seshat check` -- an unstaged delete can\nleave the static gate reading stale tracked content. Stage the SPECIFIC paths\nyou removed (and the shared-file edits), not a blanket `git add -A` -- a bare\n`-A` would also stage any unrelated working-tree change, including a mistaken\ndeletion of another table's files:\n\n```powershell\n# stage exactly the paths reset above -- review `git status` first\ngit add mappings\u002F\u003Ctable> `\n        warehouse\u002Fmigrations\u002F0003_create_silver_\u003Ctable>.sql `\n        warehouse\u002Fmigrations\u002F0004_create_gold_\u003Ctable>_star.sql `\n        dbt\u002Fmodels\u002Fstaging\u002F\u003Ctable> dbt\u002Fmodels\u002Fmarts\u002F\u003Ctable> `\n        dbt\u002Fmodels\u002Faudit\u002F\u003Ctable> `\n        dbt\u002Fmodels\u002Fsources\u002F_sources.yml dbt\u002Fselectors.yml\nseshat check\nseshat next --format agent --table \u003Ctable>\n```\n\nThen verify no residual state remains by inspecting the per-table and shared\nartifacts directly -- do NOT rely on `.seshat\u002Fmanifest.yaml`, which records the\nkit's integrity fingerprint (kit-source \u002F compass \u002F integration receipts), not\nonboarded tables, so it never mentions a table and would give a false\nall-clear. A truthful reset means: `mappings\u002F\u003Ctable>\u002F` is gone, no\n`*_\u003Ctable>*.sql` migration remains, the three `dbt\u002Fmodels\u002F*\u002F\u003Ctable>\u002F` folders\nare gone, and the shared dbt files carry no rows for this table. Pass\n`--table \u003Ctable>` to `seshat next` so it reports THIS table's stage (without it,\n`next` focuses the portfolio's most urgent OTHER table and cannot confirm the\nreset) -- it should now report a fresh Source stage; if it does not, the reset\nis incomplete.\n","# Seshat BI\n\nRead `..\u002F..\u002Fportable-operating-contract.md` before acting. Inspect the current\nworkspace and use installed `seshat` commands when available. If the workspace\nhas no `AGENTS.md`, this skill's portable operating contract still applies.\n\nFor subject reasoning, load only the relevant bundled skill:\n\n- SQL and source grain: `bi-sql-knowledge`\n- DAX and semantic measures: `bi-dax-knowledge`\n- Python\u002Fdataframe preparation: `bi-python-knowledge`\n- distributed data: `bi-bigdata-knowledge`\n- retail KPI meaning and contracts: `retail-kpi-knowledge`\n- decision-questions, framing, and story order from approved metrics:\n  `bi-analyst-knowledge`\n- Power BI design, review, theme, formatting, and PBIP adoption:\n  `powerbi-workflows`\n- governed dbt prerequisite, plan, shadow build, and evidence review:\n  `dbt-workflows`\n- governed Dagster preflight, gated medallion runs, and run-evidence review:\n  `dagster-workflows`\n- read-only Power BI MCP doctor, surface recommendation, and preflight:\n  `pbi-mcp-doctor`\n\nThe ten readiness verbs, in flow order. Each owns one stage transition and stops\nat its own gate; none of them self-grants an approval:\n\n- orient a new table on one card: `first-hour-compass`\n- sequence a table end to end and self-heal against the gate:\n  `retail-orchestrate`\n- discover a database metadata-only and propose governed scope:\n  `retail-discover-portfolio`\n- take a raw table from Source Ready to Mapping Ready: `retail-onboard-table`\n- interview the owner into the Decision Store: `business-knowledge-interview`\n- drive a raw table through the mapping gate: `source-mapping`\n- author an owner-ready metric contract: `kpi-contract-builder`\n- author the silver and gold migration SQL, then stop: `retail-build-warehouse`\n- run the static governance checker and read its findings: `retail-govern`\n- run the live data checks on materialized rows: `retail-validate`\n\nNot a readiness verb, but the surface a user asks for by name: to open the local\nanalyst console for one workspace in a browser -- readiness, tables, and the\napprovals a human still owes -- load `seshat-studio`. It renders recorded state\nand stops at the same gates; it grants no approval and advances no stage.\n\nEnd with one next action or one blocked stop. Cite evidence and named blockers;\nnever invent a pass or score.\n\n## Discovering the surface (no name memorization needed)\n\nA user or agent only needs this skill's name; everything else self-describes:\n\n- On Claude Code, `\u002Fseshat-bi:help` prints the full installed command map; on\n  Codex, the routing list above IS the map (there are no Codex slash\n  commands).\n- `seshat --help` lists every installed CLI verb, and\n  `seshat next --format agent` returns the one machine-readable governed next\n  action -- always prefer it over guessing a verb or a stage.\n- Use only the commands, verbs, and skill names those surfaces report; never\n  invent a name, and if `seshat` is not installed, say so and point to\n  `pipx install seshat-bi` instead of simulating output.\n\n## Agent-driven loop (programmatic automation)\n\nFor fully programmatic automation, the optional read-only MCP governor\n(`seshat mcp --repo \u003Cworkspace>`, installed via `pipx install \"seshat-bi[mcp]\"`)\nexposes six tools: `seshat_get_status`, `seshat_get_next_action`,\n`seshat_explain_blockers`, `seshat_prepare_approval_request`,\n`seshat_run_static_check`, and `seshat_export_evidence_pack`.\n\nThe governed loop is: get the next action, perform exactly that one action,\nre-run the static check, and repeat. When the next action is a named-human\ndecision, call `seshat_prepare_approval_request` to package it and STOP -- no\ntool in this loop grants an approval, advances a stage, or emits a score, and\nthe loop must never route around a blocked gate.\n\n## Existing PBIP projects\n\nFor an existing Power BI Project, first use the installed read-only entry path:\n\n```powershell\nseshat adopt-pbip assess --project \u003CPBIP-project-directory> --format text\n```\n\nTreat PBIP structure as candidate evidence only. The assessment must not create\nor approve mappings, metrics, business meaning, or readiness passes. It returns\none governed next action and an assessment digest. A `.pbix` is a conversion\nboundary: save it as PBIP in Power BI Desktop before continuing.\n\nOnly after a human reviews the exact digest, and only in a clean existing Git\nworktree, may the agent run:\n\n```powershell\nseshat adopt-pbip scaffold --project \u003CPBIP-project-directory> --accept-assessment \u003Cassessment-digest>\n```\n\nThis writes at most `.seshat\u002Fadoption\u002Fpbip-adoption.yaml`; it never initializes\nGit, overwrites existing files, grants approval, or advances readiness.\n\n## Resetting \u002F re-running a project\n\nUse the native verb first: `seshat reset \u003Ctable>` removes the complete derived\nfile-set for ONE table (its `mappings\u002F\u003Ctable>\u002F` incl. `dbt-evidence\u002F`, the\nexact-token silver\u002Fgold migrations, the three nested `dbt\u002Fmodels\u002F*\u002F\u003Ctable>\u002F`\nfolders, only this table's rows in the shared dbt files, and the table-scoped\ndagster run evidence under `.seshat\u002Fdagster\u002Fruns\u002F`), preserves the bronze\nlanding, and STAGES the deletions so `seshat check` runs clean afterwards. It\nnever touches a live database.\n\n```powershell\nseshat reset \u003Ctable> --dry-run   # print the exact plan first (writes nothing)\nseshat reset \u003Ctable>             # interactive confirm; --yes for automation\nseshat next --table \u003Ctable>      # should now report a fresh Source stage\n```\n\nRefusals exit non-zero with a named reason (an unsafe table name, a symlinked\npath, a shared dbt file the surgical row-edit cannot verify -- hand-edit that\nfile, then retry). In a non-interactive shell, pass `--yes` or the verb refuses\nrather than hanging.\n\nThe MANUAL checklist below is the fallback for when the verb refuses or is\nunavailable.\n\n**STOP first -- two cases neither the verb nor this manual reset covers; hand\nthem to the owner rather than deleting blindly:**\n\n1. **Shared conformed dimension.** If this table OWNS a conformed dimension that\n   another star reuses, the marts directory the dbt adapter generates for it holds\n   the sole dbt model\n   the reuser resolves via `ref()` (the kit emits no duplicate model for\n   non-owners). Deleting the marts folder would break the other star's build.\n   Check the conformed-dimension map, creating the file if absent: if this table is the OWNER\n   of any dimension listed with other-star reusers, **do not run this manual\n   reset** -- ownership transfer \u002F dependent regeneration is an owner decision.\n2. **Downstream Power BI artifacts.** If this table reached Semantic Model or\n   Dashboard, committed `powerbi\u002F*.SemanticModel` \u002F report artifacts still point\n   at the gold objects you are about to remove. This checklist does NOT rewrite\n   or quarantine them -- leaving them would let Power BI keep reading stale gold\n   while `seshat next` reports Source. If a `powerbi\u002F` artifact references this\n   table's gold entities, **stop and hand the PBIP teardown to the owner** (a\n   shared semantic model especially must be handled explicitly, never bulk\n   deleted).\n\nIf neither case applies (no conformed-dimension ownership, no downstream PBIP),\nthis table's artifacts are table-local and the reset is safe -- prefer\n`seshat reset \u003Ctable>` above; the manual fallback follows.\n\nFirst LIST what you are about to remove and confirm every path is for THIS\ntable -- never delete by a bare `\u003Ctable>*` wildcard. A prefix wildcard is\ndangerous when one table id is a prefix of another (e.g. `orders` also matches\n`orders_archive`): `*_create_silver_\u003Ctable>*.sql` would sweep the other table's\nmigrations too, and a later broad `git add` would then stage that unrelated data\nloss. Enumerate the exact migration files and eyeball them before removing:\n\n```powershell\n# 1. Enumerate the migration SQL for THIS table -- review the list first.\nGet-ChildItem warehouse\u002Fmigrations |\n  Where-Object { $_.Name -match \"_create_(silver|gold)_\u003Ctable>(_|\\.)\" }\n```\n\nOnce the list is confirmed to contain only this table's files, remove the\nderived artifacts (exact per-table paths, not prefix globs):\n\n```powershell\nRemove-Item -Recurse -Force mappings\u002F\u003Ctable>\n# remove ONLY the confirmed migration files from the list above, e.g.:\nRemove-Item -Force warehouse\u002Fmigrations\u002F0003_create_silver_\u003Ctable>.sql\nRemove-Item -Force warehouse\u002Fmigrations\u002F0004_create_gold_\u003Ctable>_star.sql\nRemove-Item -Recurse -Force dbt\u002Fmodels\u002Fstaging\u002F\u003Ctable>\nRemove-Item -Recurse -Force dbt\u002Fmodels\u002Fmarts\u002F\u003Ctable>\nRemove-Item -Recurse -Force dbt\u002Fmodels\u002Faudit\u002F\u003Ctable>\n```\n\nThis covers `mappings\u002F\u003Ctable>\u002F` (including its nested `dbt-evidence\u002F`\nsubfolder -- it lives under the mapping directory, not as a separate\ntop-level path), the silver and gold migration SQL for that table (plus any\ngenerated `warehouse\u002Fgold\u002F` or `warehouse\u002Fschema\u002F` outputs), and the three\nper-table dbt model folders. Do not touch the bronze landing. In a multi-table\nworkspace, also confirm the shared dbt files (`dbt\u002Fmodels\u002Fsources\u002F_sources.yml`,\n`dbt\u002Fselectors.yml`) no longer reference this table's gold entities -- edit out\nonly this table's rows, leaving other tables' rows intact.\n\nThe materialized dagster project under `orchestration\u002Fdagster\u002F` is\nregenerable rather than hand-edited; if it references the removed table,\nregenerate it with `seshat dagster init`.\n\nStage the deletions before running `seshat check` -- an unstaged delete can\nleave the static gate reading stale tracked content. Stage the SPECIFIC paths\nyou removed (and the shared-file edits), not a blanket `git add -A` -- a bare\n`-A` would also stage any unrelated working-tree change, including a mistaken\ndeletion of another table's files:\n\n```powershell\n# stage exactly the paths reset above -- review `git status` first\ngit add mappings\u002F\u003Ctable> `\n        warehouse\u002Fmigrations\u002F0003_create_silver_\u003Ctable>.sql `\n        warehouse\u002Fmigrations\u002F0004_create_gold_\u003Ctable>_star.sql `\n        dbt\u002Fmodels\u002Fstaging\u002F\u003Ctable> dbt\u002Fmodels\u002Fmarts\u002F\u003Ctable> `\n        dbt\u002Fmodels\u002Faudit\u002F\u003Ctable> `\n        dbt\u002Fmodels\u002Fsources\u002F_sources.yml dbt\u002Fselectors.yml\nseshat check\nseshat next --format agent --table \u003Ctable>\n```\n\nThen verify no residual state remains by inspecting the per-table and shared\nartifacts directly -- do NOT rely on `.seshat\u002Fmanifest.yaml`, which records the\nkit's integrity fingerprint (kit-source \u002F compass \u002F integration receipts), not\nonboarded tables, so it never mentions a table and would give a false\nall-clear. A truthful reset means: `mappings\u002F\u003Ctable>\u002F` is gone, no\n`*_\u003Ctable>*.sql` migration remains, the three `dbt\u002Fmodels\u002F*\u002F\u003Ctable>\u002F` folders\nare gone, and the shared dbt files carry no rows for this table. Pass\n`--table \u003Ctable>` to `seshat next` so it reports THIS table's stage (without it,\n`next` focuses the portfolio's most urgent OTHER table and cannot confirm the\nreset) -- it should now report a fresh Source stage; if it does not, the reset\nis incomplete.\n",{"name":5,"description":7},"main","6266e304556a72b75d951b9433fd833481c61233","distribution\u002Fbundle-templates\u002Fshared\u002Fskills\u002Fseshat-bi",0,"https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI","https:\u002F\u002Fpypi.org\u002Fproject\u002Fseshat-bi\u002F","https:\u002F\u002Fgithub.com\u002FKemetra","2026-11-11 21:44:25",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Kemetra\u002FSeshat-BI --skill seshat-bi",{"tool":37,"command":38},"bunx","bunx skills add Kemetra\u002FSeshat-BI --skill seshat-bi",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Kemetra\u002FSeshat-BI --skill seshat-bi","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Fdistribution\u002Fbundle-templates\u002Fshared\u002Fskills\u002Fseshat-bi\u002FSKILL.md",true,[],[46,53,58,64,69,76],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M77JWCTJ88JWPDD25WZ2NEY8","fake-skill","A fixture skill with declaring frontmatter, used as positive shipped evidence.","https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Ftests\u002Funit\u002Ffixtures\u002Fcapability_inventory\u002Funlisted\u002F.claude\u002Fskills\u002Ffake-skill\u002FSKILL.md",[],[],{"skillNo":54,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M77JWA0BTG4JB2HR52Q99216","https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Ftests\u002Funit\u002Ffixtures\u002Fcapability_inventory\u002Forphan\u002F.claude\u002Fskills\u002Ffake-skill\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M77JW6VE59XEFHWBTNDYAS2Q","bare-skill-no-frontmatter","https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Ftests\u002Funit\u002Ffixtures\u002Fcapability_inventory\u002Forphan\u002F.claude\u002Fskills\u002Fbare-skill-no-frontmatter\u002FSKILL.md",[],[],{"skillNo":65,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M77JW4TD1FNFSBNP5C0WXAA5","https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Ftests\u002Funit\u002Ffixtures\u002Fcapability_inventory\u002Fgood\u002F.claude\u002Fskills\u002Ffake-skill\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M77JVWCVE3WZ82ZNFCSFVDCP","retail-kpi-knowledge","Retail KPI \u002F 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\u002Fsemi\u002Fnon-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\u002Fdefinition + review layer, not an executor: it does not write DAX\u002FSQL\u002FPython, grant readiness, approve policy, or design dashboards. See INDEX.md for live\u002Fplanned routes; registry.yaml is the authoritative machine-readable inventory.","https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Fskills\u002Fretail-kpi-knowledge\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M77JVNDM1NGYGSCPTBW9ZCF5","bi-sql-knowledge","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\u002FNULL semantics, deduplication, validation queries, reconciliation queries, silver\u002Fgold transformation logic, window\u002Fdate-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\u002FDagster project, or automatic tuning service.","https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Fskills\u002Fbi-sql-knowledge\u002FSKILL.md",[],[]]