[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JKWW3Y4RYHECTFW6GR0M9":3,"skill-same:01M77JKWW3Y4RYHECTFW6GR0M9":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},"01M77JKWW3Y4RYHECTFW6GR0M9","dbt-workflows",null,"Route dbt intent to Seshat's governed shadow workflow or the official dbt Labs competence and execution owner, without bypassing readiness or evidence.","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\u002Fintegrations\u002Fclaude-code\u002Fseshat-bi\u002Fskills\u002Fdbt-workflows\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: dbt-workflows\ndescription: >-\n  Route dbt intent to Seshat's governed shadow workflow or the official dbt\n  Labs competence and execution owner, without bypassing readiness or evidence.\n---\n\n# Governed dbt workflows\n\nRead `..\u002F..\u002Fportable-operating-contract.md` before acting. For a governed\nSeshat shadow workflow, use only the installed `seshat dbt` helpers; never\nbypass their fixed selector, target, profile, lock, redaction, or artifact\nchecks with raw dbt commands.\n\n## Intent ownership\n\n| User intent | Seshat pre-gate | Execution owner | Seshat afterward |\n|---|---|---|---|\n| Decide whether dbt fits the current BI stage | Readiness and approved-mapping context | Seshat selection policy | State one truthful next action |\n| Scaffold governed shadow models | Approved committed source map | Seshat source-map-derived scaffold | Validate citations and the `meta.seshat` contract |\n| 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 |\n| Generic dbt model authoring, test design, syntax, docs, or troubleshooting | Prove the official skill is activated and discoverable | Official dbt Labs agent skills | If the work enters Seshat's governed project, return through the Seshat gates above |\n| Native dbt MCP configuration or tool use | Prove the exact MCP registration is activated and discoverable | Official dbt MCP and its official configuration skill | Do not infer a readiness effect; route governed execution back through `seshat dbt` |\n| Switch from migrations to dbt | Passing parity evidence plus a named-human approval | Named human | Retain migrations as parity oracle and rollback path |\n\nSpec 148 provides the read-only harness proof for the official dbt Labs agent\nskills. Before routing generic competence, run\n`seshat integrations setup --profile analytics-full --harness \u003Cclaude-code|codex>`\nand require the `dbt-agent-skills` result to be discoverable. MCP liveness remains\na separate preflight fact. Report the exact blocker for either surface; do not\ncopy official guidance into this router, claim an installed payload is usable,\nor execute raw dbt commands against the governed project as a fallback.\n\n## Fixed workflow\n\n1. Check prerequisites without a database query:\n\n   `seshat dbt doctor --format json`\n\n2. Materialize the governed model set from the approved map (once per table):\n\n   `seshat dbt scaffold --table \u003Ctable> --format json`\n\n   This writes, FROM the approved committed source map, the staging model, one\n   gold model per fact\u002Fdim, the parity-audit model, their native dbt contracts,\n   the `seshat_table_\u003Ctable>` selector row, and the `bronze` + `migration_gold`\n   sources. It is non-destructive (an existing file is kept) and needs no\n   database. The generated `.sql` files are SKELETONS: their SELECT column list\n   is the governed output contract (do not rename or drop columns), but the\n   joins, casts, and surrogate-key logic are yours to complete before the live\n   build. NOTE: scaffold is non-destructive (it never overwrites an existing\n   model), so after a source-map re-commit a plain re-run does NOT refresh a\n   stale `source_map_revision` — you must update each model's `source_map_revision`\n   by hand, or delete the generated `_models.yml` and re-scaffold. See \"The\n   `meta.seshat` model contract\" below for the shape scaffold emits and `validate`\n   enforces.\n\n3. Validate the Mapping Ready gate, shadow schemas, selector, and citations:\n\n   `seshat dbt validate --table \u003Ctable> --format json`\n\n5. Produce and review the immutable plan:\n\n   `seshat dbt plan --table \u003Ctable> --format json`\n\n   Confirm the approved mapping identity, pinned dbt versions, exact selected\n   model\u002Ftest IDs, and shadow-only schemas. The returned `digest` is the only\n   valid `--accept-plan` value; it is neither a mapping approval nor a readiness\n   approval.\n\n6. With the reviewed digest, execute the fixed graph:\n\n   `seshat dbt build --table \u003Ctable> --accept-plan \u003Cdigest> --format json`\n\n   Use `seshat dbt test --table \u003Ctable> --accept-plan \u003Cdigest> --format json`\n   only for a test-only rerun. Both recompute the plan before database access;\n   drift stops execution and requires a new plan and review.\n\n7. Review the returned normalized evidence. When a user supplies an existing\n   run directory under `.seshat\u002Fdbt\u002Fruns\u002F`, revalidate it offline with:\n\n   `seshat dbt inspect-run --table \u003Ctable> --artifacts \u003Crun-directory> --format json`\n\n   Do not invent a run directory or treat `inspect-run` as a required second\n   build. Report parity failures and `blocking_reasons`, then stop for a named human.\n   Passing output is derived evidence only.\n\n## The `meta.seshat` model contract\n\n`seshat dbt scaffold` emits this shape and `seshat dbt validate` enforces it; you\nshould never need to reverse-engineer it from a gate error. Each `_models.yml`\nrow carries, at the TOP level of the row (NOT under `config` -- nesting\n`meta` there silently orphans the model, because the validator reads\n`row['meta']` while the tag reads `row['config']['tags']`):\n\n    - name: \u003Cmodel_name>              # dim_* \u002F stg_* \u002F audit_* \u002F the one fact\n      config:\n        tags: [seshat_table_\u003Ctable>]  # the governed selector tag\n      meta:\n        seshat:\n          table_id: \u003Ctable>\n          source_map: mappings\u002F\u003Ctable>\u002Fsource-map.yaml\n          source_map_revision: \u003Cgit blob sha of the committed map>\n          grain: \u003Cone row = ...>\n          business_key: [\u003Ckey column(s)>]\n          authority: derived          # always exactly \"derived\"\n      columns:\n        - name: \u003Ccolumn>\n          data_type: \u003Cpostgres type>  # ADVISORY (source columns only), not an\n                                       # enforced contract; the human owns casts\n          meta:\n            seshat:\n              source_columns: [bronze.\u003Ctable>.\u003Csrc>]   # OR:\n              # derivation: surrogate_key | date_spine | unknown_member | parity_measure\n\n`source_map_revision` is the git BLOB sha of the committed map\n(`git rev-parse HEAD:mappings\u002F\u003Ctable>\u002Fsource-map.yaml`), so every model is\ncoupled to one committed map revision: any map edit needs a re-commit AND a\nre-scaffold, or `validate` reports `DBT_MODEL_CITATION_STALE`. Every output\ncolumn MUST carry either `source_columns` (an approved-map citation) or one of\nthe four governed `derivation` values -- an uncited column is a defect.\n\nThe parity-audit model emits exactly the assertion rows `dbt show` consumes: one\n`fact_row_count`, one `business_key_count` (subject = `\u003Cfact>.\u003Ckey cols>`), one\n`additive_money_total` per approved money measure, and one\n`dimension_member_count` per built dimension (tolerances: money `0.01`, else `0`).\nScaffold derives this set from the approved map's `gold_star.fact` tags\n(`business_key`, `additive_money_measures`) and the built `dim_*` models; do not\nhand-edit it out of agreement with the map.\n\n## Hard boundaries\n\n- Stop before planning unless Mapping Ready has a named-human approval.\n- Put real `SESHAT_DBT_*` values only in the gitignored `.env`; keep\n  `profiles.yml` as `env_var()` references.\n- If the dbt extra, profile, DSN, or live database is absent, report\n  `[PENDING LIVE PROFILE]` with enable steps; never fabricate compile, build,\n  test, or parity success.\n- Migrations remain the default build path after parity. A separate named\n  human must approve switching the active path, and migrations remain the\n  parity oracle and rollback path until separately retired.\n- Never write a readiness pass, migration-switch approval, confidence score,\n  raw adapter output, credential, DSN, or absolute local path.\n\n## Exit meanings\n\n- exit 0: command completed; dbt output remains derived evidence.\n- exit 1: handled model, test, or parity failure.\n- exit 2: usage or runtime\u002Fprofile\u002Fdatabase prerequisite unavailable.\n- exit 3: governance refusal, lock conflict, or accepted-plan drift.\n- exit 4: artifact or normalized-evidence integrity failure.\n","# Governed dbt workflows\n\nRead `..\u002F..\u002Fportable-operating-contract.md` before acting. For a governed\nSeshat shadow workflow, use only the installed `seshat dbt` helpers; never\nbypass their fixed selector, target, profile, lock, redaction, or artifact\nchecks with raw dbt commands.\n\n## Intent ownership\n\n| User intent | Seshat pre-gate | Execution owner | Seshat afterward |\n|---|---|---|---|\n| Decide whether dbt fits the current BI stage | Readiness and approved-mapping context | Seshat selection policy | State one truthful next action |\n| Scaffold governed shadow models | Approved committed source map | Seshat source-map-derived scaffold | Validate citations and the `meta.seshat` contract |\n| 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 |\n| Generic dbt model authoring, test design, syntax, docs, or troubleshooting | Prove the official skill is activated and discoverable | Official dbt Labs agent skills | If the work enters Seshat's governed project, return through the Seshat gates above |\n| Native dbt MCP configuration or tool use | Prove the exact MCP registration is activated and discoverable | Official dbt MCP and its official configuration skill | Do not infer a readiness effect; route governed execution back through `seshat dbt` |\n| Switch from migrations to dbt | Passing parity evidence plus a named-human approval | Named human | Retain migrations as parity oracle and rollback path |\n\nSpec 148 provides the read-only harness proof for the official dbt Labs agent\nskills. Before routing generic competence, run\n`seshat integrations setup --profile analytics-full --harness \u003Cclaude-code|codex>`\nand require the `dbt-agent-skills` result to be discoverable. MCP liveness remains\na separate preflight fact. Report the exact blocker for either surface; do not\ncopy official guidance into this router, claim an installed payload is usable,\nor execute raw dbt commands against the governed project as a fallback.\n\n## Fixed workflow\n\n1. Check prerequisites without a database query:\n\n   `seshat dbt doctor --format json`\n\n2. Materialize the governed model set from the approved map (once per table):\n\n   `seshat dbt scaffold --table \u003Ctable> --format json`\n\n   This writes, FROM the approved committed source map, the staging model, one\n   gold model per fact\u002Fdim, the parity-audit model, their native dbt contracts,\n   the `seshat_table_\u003Ctable>` selector row, and the `bronze` + `migration_gold`\n   sources. It is non-destructive (an existing file is kept) and needs no\n   database. The generated `.sql` files are SKELETONS: their SELECT column list\n   is the governed output contract (do not rename or drop columns), but the\n   joins, casts, and surrogate-key logic are yours to complete before the live\n   build. NOTE: scaffold is non-destructive (it never overwrites an existing\n   model), so after a source-map re-commit a plain re-run does NOT refresh a\n   stale `source_map_revision` — you must update each model's `source_map_revision`\n   by hand, or delete the generated `_models.yml` and re-scaffold. See \"The\n   `meta.seshat` model contract\" below for the shape scaffold emits and `validate`\n   enforces.\n\n3. Validate the Mapping Ready gate, shadow schemas, selector, and citations:\n\n   `seshat dbt validate --table \u003Ctable> --format json`\n\n5. Produce and review the immutable plan:\n\n   `seshat dbt plan --table \u003Ctable> --format json`\n\n   Confirm the approved mapping identity, pinned dbt versions, exact selected\n   model\u002Ftest IDs, and shadow-only schemas. The returned `digest` is the only\n   valid `--accept-plan` value; it is neither a mapping approval nor a readiness\n   approval.\n\n6. With the reviewed digest, execute the fixed graph:\n\n   `seshat dbt build --table \u003Ctable> --accept-plan \u003Cdigest> --format json`\n\n   Use `seshat dbt test --table \u003Ctable> --accept-plan \u003Cdigest> --format json`\n   only for a test-only rerun. Both recompute the plan before database access;\n   drift stops execution and requires a new plan and review.\n\n7. Review the returned normalized evidence. When a user supplies an existing\n   run directory under `.seshat\u002Fdbt\u002Fruns\u002F`, revalidate it offline with:\n\n   `seshat dbt inspect-run --table \u003Ctable> --artifacts \u003Crun-directory> --format json`\n\n   Do not invent a run directory or treat `inspect-run` as a required second\n   build. Report parity failures and `blocking_reasons`, then stop for a named human.\n   Passing output is derived evidence only.\n\n## The `meta.seshat` model contract\n\n`seshat dbt scaffold` emits this shape and `seshat dbt validate` enforces it; you\nshould never need to reverse-engineer it from a gate error. Each `_models.yml`\nrow carries, at the TOP level of the row (NOT under `config` -- nesting\n`meta` there silently orphans the model, because the validator reads\n`row['meta']` while the tag reads `row['config']['tags']`):\n\n    - name: \u003Cmodel_name>              # dim_* \u002F stg_* \u002F audit_* \u002F the one fact\n      config:\n        tags: [seshat_table_\u003Ctable>]  # the governed selector tag\n      meta:\n        seshat:\n          table_id: \u003Ctable>\n          source_map: mappings\u002F\u003Ctable>\u002Fsource-map.yaml\n          source_map_revision: \u003Cgit blob sha of the committed map>\n          grain: \u003Cone row = ...>\n          business_key: [\u003Ckey column(s)>]\n          authority: derived          # always exactly \"derived\"\n      columns:\n        - name: \u003Ccolumn>\n          data_type: \u003Cpostgres type>  # ADVISORY (source columns only), not an\n                                       # enforced contract; the human owns casts\n          meta:\n            seshat:\n              source_columns: [bronze.\u003Ctable>.\u003Csrc>]   # OR:\n              # derivation: surrogate_key | date_spine | unknown_member | parity_measure\n\n`source_map_revision` is the git BLOB sha of the committed map\n(`git rev-parse HEAD:mappings\u002F\u003Ctable>\u002Fsource-map.yaml`), so every model is\ncoupled to one committed map revision: any map edit needs a re-commit AND a\nre-scaffold, or `validate` reports `DBT_MODEL_CITATION_STALE`. Every output\ncolumn MUST carry either `source_columns` (an approved-map citation) or one of\nthe four governed `derivation` values -- an uncited column is a defect.\n\nThe parity-audit model emits exactly the assertion rows `dbt show` consumes: one\n`fact_row_count`, one `business_key_count` (subject = `\u003Cfact>.\u003Ckey cols>`), one\n`additive_money_total` per approved money measure, and one\n`dimension_member_count` per built dimension (tolerances: money `0.01`, else `0`).\nScaffold derives this set from the approved map's `gold_star.fact` tags\n(`business_key`, `additive_money_measures`) and the built `dim_*` models; do not\nhand-edit it out of agreement with the map.\n\n## Hard boundaries\n\n- Stop before planning unless Mapping Ready has a named-human approval.\n- Put real `SESHAT_DBT_*` values only in the gitignored `.env`; keep\n  `profiles.yml` as `env_var()` references.\n- If the dbt extra, profile, DSN, or live database is absent, report\n  `[PENDING LIVE PROFILE]` with enable steps; never fabricate compile, build,\n  test, or parity success.\n- Migrations remain the default build path after parity. A separate named\n  human must approve switching the active path, and migrations remain the\n  parity oracle and rollback path until separately retired.\n- Never write a readiness pass, migration-switch approval, confidence score,\n  raw adapter output, credential, DSN, or absolute local path.\n\n## Exit meanings\n\n- exit 0: command completed; dbt output remains derived evidence.\n- exit 1: handled model, test, or parity failure.\n- exit 2: usage or runtime\u002Fprofile\u002Fdatabase prerequisite unavailable.\n- exit 3: governance refusal, lock conflict, or accepted-plan drift.\n- exit 4: artifact or normalized-evidence integrity failure.\n",{"name":5,"description":7},"main","6266e304556a72b75d951b9433fd833481c61233","integrations\u002Fclaude-code\u002Fseshat-bi\u002Fskills\u002Fdbt-workflows",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 dbt-workflows",{"tool":37,"command":38},"bunx","bunx skills add Kemetra\u002FSeshat-BI --skill dbt-workflows",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Kemetra\u002FSeshat-BI --skill dbt-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Fintegrations\u002Fclaude-code\u002Fseshat-bi\u002Fskills\u002Fdbt-workflows\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",[],[]]