[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JS2SK8Q1SNTGZ7F549RG3":3,"skill-same:01M77JS2SK8Q1SNTGZ7F549RG3":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},"01M77JS2SK8Q1SNTGZ7F549RG3","pbi-mcp-doctor",null,"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.","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\u002Fcodex\u002Fseshat-bi\u002Fskills\u002Fpbi-mcp-doctor\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: pbi-mcp-doctor\ndescription: >-\n  Use when a user asks whether or how to wire Microsoft's official Power BI\n  MCP servers into a Seshat BI workspace: run the read-only environment\n  doctor, map a task to the governed Power BI surface (including the official\n  report-authoring skill), generate a safe read-only config template, or run\n  the mocked read-only preflight.\n---\n\n# Power BI MCP doctor (read-only)\n\nRead `..\u002F..\u002Fportable-operating-contract.md` before acting. Use only the\ninstalled `seshat pbi-mcp` verbs; never launch an MCP server directly, never\nedit `.mcp.json` by hand when the generator can produce it, and never treat\nany output of this family as an approval. F016 (the Power BI execution\nadapter) is PARKED: no mutation path exists anywhere in this family.\n\n## Fixed workflow\n\n1. Map the user's task to the governed surface, read-only:\n\n   `seshat pbi-mcp doctor --repo . --intent \u003Ctask> [--target \u003Ctable>] [--harness \u003Cclaude-code|codex>] [--json] [--write-advisory]`\n\n   `--intent` is a closed vocabulary: `model-edit`, `published-query`,\n   `report-authoring`, `report-formatting`, `desktop-verification`, `db-connectivity`,\n   `ci-validation`, `sensitive-production`. Report the recommendation, its\n   missing prerequisites, and the next HUMAN step verbatim. A blocked\n   recommendation (exit 2) names the gate -- stop there; never route around\n   it. `--write-advisory` records the result once at\n   `.seshat\u002Fpowerbi-mcp-recommendation.yaml` (write-once; it refuses to\n   overwrite) and is never a side effect.\n\n   `report-authoring` additionally requires an exact `--target \u003Ctable>`. It\n   selects Microsoft's official `powerbi-report-authoring` skill, but remains\n   blocked until that target has a committed semantic-model pass, a complete\n   named-human `dashboard_ready` approval, and the Spec 148 harness probe reports\n   the skill discoverable. Approval does not itself claim `dashboard_ready:\n   pass`. Installed is not the same as activated.\n\n2. Generate config only through the safe generator:\n\n   `seshat pbi-mcp generate-config [--transport local|remote|both] [--setup-doc] [--out \u003Cpath>]`\n\n   Output is placeholder-only and read-only (`--readonly`); it is\n   secret-scanned before emission and refuses to overwrite an existing file.\n   If it refuses because output would be secret-shaped, stop and report --\n   never bypass the scan by writing the file yourself.\n\n3. Preflight the runtime read-only (graceful when absent):\n\n   `seshat pbi-mcp preflight [--target \u003Ct> --allow \u003Ct>] [--require-tool \u003Cname>] [--json] [--write-artifact]`\n\n   It refuses a write-mode config, hard-refuses `--skipconfirmation`\n   anywhere, fails closed while `semantic_model_ready` has not passed, and\n   reports \"runtime not present -- preflight skipped\" when no MCP runtime is\n   installed (that is a graceful skip, exit 0, not a failure).\n   `--write-artifact` records the result at\n   `.seshat\u002Fpowerbi-mcp-preflight.json` -- derived evidence only, the shape\n   the adapter-compatibility matrix's F016 row references.\n\n## The recommendation matrix in plain language\n\n- Create or modify a PBIP\u002FTMDL semantic model -> BLOCKED while F016 remains\n  parked, even when `semantic_model_ready` has passed. The official local Power\n  BI Modeling MCP is a future execution-only adapter, never a source of metric\n  meaning or approval.\n- Query an already-published semantic model -> the official REMOTE Power BI\n  MCP server, only once its tenant-side prerequisites are verified (tenant\n  preview setting, Build permission, Copilot license for Generate Query);\n  otherwise stop and name the missing prerequisite.\n- Create or modify native report pages, visuals, filters, slicers, bindings, or\n  themes beyond Seshat's bounded allow-list -> Microsoft's official\n  `powerbi-report-authoring` skill after the exact target semantic pass and a\n  named-human dashboard-design approval; if discovery is unverified, stop\n  rather than emulate it.\n- Theme, page layout, geometry, or visual formatting -> the existing\n  PBIR-authoring gap adapter only for its bounded allow-listed operations and\n  only with the same exact-target semantic and human-approval evidence; broader\n  native report authoring routes to the official skill, not MCP.\n- Live Desktop verification or screenshots -> the Power BI Desktop Bridge, a\n  separate optional integration; never in CI.\n- Database connectivity or scheduled refresh -> the Power BI Gateway +\n  Service; neither MCP server touches these.\n- Semantic readiness not passed -> everything Power BI-mutating is BLOCKED;\n  report the gate and the named next human step.\n- CI \u002F Linux \u002F no Desktop -> deterministic PBIP\u002FTMDL file validation only;\n  Power BI Desktop is never required; an unavailable remote server is a\n  graceful skip.\n- Sensitive \u002F production environment -> read-only plus stricter named-human\n  approval; never a Service-Principal query path where row-level security\n  matters.\n\n## How to read the advisory records\n\n- `.seshat\u002Fpowerbi-mcp-recommendation.yaml` -- detected facts + one\n  categorical recommendation. Its `generated_note` is binding: it grants\n  nothing.\n- `.seshat\u002Fpowerbi-mcp-preflight.json` -- `authority` is fixed at\n  `derived-evidence-only` and `readiness_effect` at `none; named-human\n  approval required`. `status: skipped` means the runtime was absent;\n  `blocked` lists categorical blockers by id. There is no numeric score and\n  never will be.\n\n## What this family will NEVER do\n\n- Never mutate a semantic model, a report, or any file other than the two\n  advisory records above (each behind an explicit flag).\n- Never grant, imply, or record an approval; never advance a readiness\n  stage; never emit a numeric score.\n- Never contact a live tenant, database, or network endpoint -- the real MCP\n  transport is deliberately absent in this slice.\n- Never run or recommend `--skipconfirmation`, `--readwrite`, or any\n  write-mode invocation; mutations are slice-5 territory behind an\n  owner-ratified ADR and a named-human `publish_ready` approval.\n- Never write a credential, tenant id, hostname, or user path into any\n  generated output -- the secret scan refuses, and the refusal is final.\n","# Power BI MCP doctor (read-only)\n\nRead `..\u002F..\u002Fportable-operating-contract.md` before acting. Use only the\ninstalled `seshat pbi-mcp` verbs; never launch an MCP server directly, never\nedit `.mcp.json` by hand when the generator can produce it, and never treat\nany output of this family as an approval. F016 (the Power BI execution\nadapter) is PARKED: no mutation path exists anywhere in this family.\n\n## Fixed workflow\n\n1. Map the user's task to the governed surface, read-only:\n\n   `seshat pbi-mcp doctor --repo . --intent \u003Ctask> [--target \u003Ctable>] [--harness \u003Cclaude-code|codex>] [--json] [--write-advisory]`\n\n   `--intent` is a closed vocabulary: `model-edit`, `published-query`,\n   `report-authoring`, `report-formatting`, `desktop-verification`, `db-connectivity`,\n   `ci-validation`, `sensitive-production`. Report the recommendation, its\n   missing prerequisites, and the next HUMAN step verbatim. A blocked\n   recommendation (exit 2) names the gate -- stop there; never route around\n   it. `--write-advisory` records the result once at\n   `.seshat\u002Fpowerbi-mcp-recommendation.yaml` (write-once; it refuses to\n   overwrite) and is never a side effect.\n\n   `report-authoring` additionally requires an exact `--target \u003Ctable>`. It\n   selects Microsoft's official `powerbi-report-authoring` skill, but remains\n   blocked until that target has a committed semantic-model pass, a complete\n   named-human `dashboard_ready` approval, and the Spec 148 harness probe reports\n   the skill discoverable. Approval does not itself claim `dashboard_ready:\n   pass`. Installed is not the same as activated.\n\n2. Generate config only through the safe generator:\n\n   `seshat pbi-mcp generate-config [--transport local|remote|both] [--setup-doc] [--out \u003Cpath>]`\n\n   Output is placeholder-only and read-only (`--readonly`); it is\n   secret-scanned before emission and refuses to overwrite an existing file.\n   If it refuses because output would be secret-shaped, stop and report --\n   never bypass the scan by writing the file yourself.\n\n3. Preflight the runtime read-only (graceful when absent):\n\n   `seshat pbi-mcp preflight [--target \u003Ct> --allow \u003Ct>] [--require-tool \u003Cname>] [--json] [--write-artifact]`\n\n   It refuses a write-mode config, hard-refuses `--skipconfirmation`\n   anywhere, fails closed while `semantic_model_ready` has not passed, and\n   reports \"runtime not present -- preflight skipped\" when no MCP runtime is\n   installed (that is a graceful skip, exit 0, not a failure).\n   `--write-artifact` records the result at\n   `.seshat\u002Fpowerbi-mcp-preflight.json` -- derived evidence only, the shape\n   the adapter-compatibility matrix's F016 row references.\n\n## The recommendation matrix in plain language\n\n- Create or modify a PBIP\u002FTMDL semantic model -> BLOCKED while F016 remains\n  parked, even when `semantic_model_ready` has passed. The official local Power\n  BI Modeling MCP is a future execution-only adapter, never a source of metric\n  meaning or approval.\n- Query an already-published semantic model -> the official REMOTE Power BI\n  MCP server, only once its tenant-side prerequisites are verified (tenant\n  preview setting, Build permission, Copilot license for Generate Query);\n  otherwise stop and name the missing prerequisite.\n- Create or modify native report pages, visuals, filters, slicers, bindings, or\n  themes beyond Seshat's bounded allow-list -> Microsoft's official\n  `powerbi-report-authoring` skill after the exact target semantic pass and a\n  named-human dashboard-design approval; if discovery is unverified, stop\n  rather than emulate it.\n- Theme, page layout, geometry, or visual formatting -> the existing\n  PBIR-authoring gap adapter only for its bounded allow-listed operations and\n  only with the same exact-target semantic and human-approval evidence; broader\n  native report authoring routes to the official skill, not MCP.\n- Live Desktop verification or screenshots -> the Power BI Desktop Bridge, a\n  separate optional integration; never in CI.\n- Database connectivity or scheduled refresh -> the Power BI Gateway +\n  Service; neither MCP server touches these.\n- Semantic readiness not passed -> everything Power BI-mutating is BLOCKED;\n  report the gate and the named next human step.\n- CI \u002F Linux \u002F no Desktop -> deterministic PBIP\u002FTMDL file validation only;\n  Power BI Desktop is never required; an unavailable remote server is a\n  graceful skip.\n- Sensitive \u002F production environment -> read-only plus stricter named-human\n  approval; never a Service-Principal query path where row-level security\n  matters.\n\n## How to read the advisory records\n\n- `.seshat\u002Fpowerbi-mcp-recommendation.yaml` -- detected facts + one\n  categorical recommendation. Its `generated_note` is binding: it grants\n  nothing.\n- `.seshat\u002Fpowerbi-mcp-preflight.json` -- `authority` is fixed at\n  `derived-evidence-only` and `readiness_effect` at `none; named-human\n  approval required`. `status: skipped` means the runtime was absent;\n  `blocked` lists categorical blockers by id. There is no numeric score and\n  never will be.\n\n## What this family will NEVER do\n\n- Never mutate a semantic model, a report, or any file other than the two\n  advisory records above (each behind an explicit flag).\n- Never grant, imply, or record an approval; never advance a readiness\n  stage; never emit a numeric score.\n- Never contact a live tenant, database, or network endpoint -- the real MCP\n  transport is deliberately absent in this slice.\n- Never run or recommend `--skipconfirmation`, `--readwrite`, or any\n  write-mode invocation; mutations are slice-5 territory behind an\n  owner-ratified ADR and a named-human `publish_ready` approval.\n- Never write a credential, tenant id, hostname, or user path into any\n  generated output -- the secret scan refuses, and the refusal is final.\n",{"name":5,"description":7},"main","6266e304556a72b75d951b9433fd833481c61233","integrations\u002Fcodex\u002Fseshat-bi\u002Fskills\u002Fpbi-mcp-doctor",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 pbi-mcp-doctor",{"tool":37,"command":38},"bunx","bunx skills add Kemetra\u002FSeshat-BI --skill pbi-mcp-doctor",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Kemetra\u002FSeshat-BI --skill pbi-mcp-doctor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Fintegrations\u002Fcodex\u002Fseshat-bi\u002Fskills\u002Fpbi-mcp-doctor\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",[],[]]