[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JSWJ8AE0SFS33BHNJR5C7":3,"skill-same:01M77JSWJ8AE0SFS33BHNJR5C7":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},"01M77JSWJ8AE0SFS33BHNJR5C7","retail-onboard-table",null,"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 \u003Cschema>.\u003Ctable>\", \"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).","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\u002Fretail-onboard-table\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retail-onboard-table\ndescription: >-\n  Walk a NEW raw retail table across the FIRST readiness transition -- Source Ready\n  (Stage 1) through Mapping Ready (Stage 2) -- and seed its per-table\n  readiness-status, in the Seshat BI repo. Use when someone says\n  \"onboard \u003Cschema>.\u003Ctable>\", \"take this new table from nothing to a reviewed map\",\n  or \"start the readiness journey for a table\". This is the stage-transition FRONT\n  DOOR: it sequences profile -> map -> gate, writes the readiness-status record, and\n  STOPS at Mapping Ready. It DELEGATES the five mapping artifacts to the\n  `source-mapping` skill (it does not re-implement mapping); it NEVER writes\n  `silver.*` SQL, NEVER self-grants the gate approval, and NEVER answers a\n  Principle-V judgment call (grain, PII, business rollup, product identity).\n---\n\n# retail-onboard-table\n\nThe onboarding front door for ONE table's first two readiness stages. The kit\nalready ships the verb that authors the mapping artifacts (`source-mapping`) and the\nconductor that sequences every verb end-to-end (`retail-orchestrate`). This skill is\nthe stage-scoped composition between them: \"I have a new raw table -- walk me from\nnothing to a reviewed map.\" It advances **Source Ready -> Mapping Ready**, seeds the\nper-table `readiness-status.yaml`, and STOPS. It is a procedure the agent performs\n(agent-first, Principle I); `seshat check` and the read-only profile are gates it\nCALLS, not a CLI subcommand.\n\n## Scope boundary (read first)\n\n- **Agent-first, no CLI.** This is a SKILL the agent runs; it adds no `retail`\n  subcommand and no Python.\n- **ENTERS at Source Ready, EXITS at Mapping Ready.** The terminal state is Mapping\n  Ready -- the three gate artifacts committed and either `mapping_ready: blocked`\n  (review pending, the common case) or `mapping_ready: pass` (only after a HUMAN has\n  recorded approval). Both are successful wizard runs.\n- **NEVER crosses into Silver Ready** (Principle IV, roadmap rule #2). It writes no\n  `silver.*` SQL, no migration, and never calls `retail-build-warehouse`. Its last\n  action is to seed\u002Fupdate the readiness-status, state the next allowed action, and\n  STOP.\n- **NEVER self-grants approval or invents a judgment call** (Principle V). The four\n  reserved seams -- grain, PII publish-safety, business rollup\u002Fsegment, product\n  identity -- are PROPOSED with a data fact and raised as `unresolved-questions.md`\n  rows; the wizard stops there.\n- **No fake confidence.** Readiness is the four explicit statuses\n  (`not_started` | `blocked` | `warning` | `pass`) + `evidence[]` +\n  `blocking_reasons[]`. No numeric score (roadmap rule #9).\n- **Delegates mapping; does not duplicate it.** Stage 2 invokes `source-mapping` to\n  author the five artifacts. This skill owns the WALK and the readiness bookkeeping,\n  not the mapping procedure.\n- ASCII only, UTF-8 no BOM (`->` arrows, `'' OR NULL`).\n\n## Run-state: read mappings\u002F\u003Ctable>\u002F FIRST (no new state file)\n\nCompute the current stage from what is already on disk -- there is NO onboarding\nstate file to create (mirrors `retail-orchestrate`'s run-state rule):\n\n| What you observe | Current stage \u002F action |\n|------------------|------------------------|\n| No `mappings\u002F\u003Ctable>\u002F` dir | Start at **Stage 1** (profile). |\n| `source-profile.md` present, no `source-map.yaml` | Resume at **Stage 2** (delegate to `source-mapping`). |\n| The five artifacts present, `unresolved-questions.md` shows `Gate status: OPEN` (or open rows) | **STOPPED at the gate** -- report the open questions; do not overwrite, do not advance. |\n| `Gate status: CLEARED`, zero open rows, an `approvals[]` entry recorded | **Mapping Ready reached** -- promote `mapping_ready: pass`; state Silver Ready is the next (out-of-scope) stage; STOP. |\n\nResume from the first incomplete artifact; NEVER clobber a committed (reviewed) one.\nYou may READ `Gate status`; you may NOT write `CLEARED` yourself (that is the\nreviewer's action).\n\n## Stage 1 -- Source Ready (profile + PROPOSE semantics)\n\nDrive the mechanical profile over a READ-ONLY connection and record into\n`mappings\u002F\u003Ctable>\u002Fsource-profile.md` (definition-of-done = `source-ready.md` `pass`):\n\n- row count + column count;\n- per-column missingness measured as `'' OR NULL` (never `IS NULL` alone -- RC5);\n- candidate-key uniqueness proof (does the proposed PK hold on the data?);\n- returns-column population.\n\nSemantic rows (what each column MEANS) are PROPOSED for human confirmation, never\ninvented. Record `source_ready: pass` with `source-profile.md` as evidence when the\nmechanical numbers are measured; `warning` in deferred-boundary mode (below); or\n`blocked` with the concrete reason if a required number is unmeasurable -- and then\ndo NOT enter Stage 2 (no mapping on an unprofiled source).\n\n## Stage 2 -- Mapping Ready (delegate to source-mapping)\n\nInvoke the `source-mapping` skill to author the five artifacts under\n`mappings\u002F\u003Ctable>\u002F` (definition-of-done = `mapping-ready.md`'s artifact set):\n\n- `source-map.yaml` -- grain, PK, every column's `pii:` flag, gold placement;\n- `assumptions.md` -- RC1-RC16 adopted\u002Fdeviated, each deviation citing a data fact;\n- `unresolved-questions.md` -- the open judgment calls (`Gate status: OPEN` until a\n  human clears it);\n- the `reconciliation-report.md` blank (the live-acceptance run, filled later).\n\nDo NOT duplicate the mapping procedure -- it lives in `source-mapping`. The wizard\nsequences the call and then does the readiness bookkeeping below.\n\n## Readiness-status bookkeeping\n\nSeed\u002Fupdate the per-table status from the readiness-status template at the\ncanonical `mappings\u002F\u003Ctable>\u002Freadiness-status.yaml` (ADR 0004 -- co-located with the\nmapping artifacts, spans all seven stages). The wizard is the FIRST writer of this\nfile. Set:\n\n- `source_ready`: `pass` (mechanical numbers measured) \u002F `warning` (deferred mode) \u002F\n  `blocked` (unmeasurable) -- with `evidence[]` or `blocking_reasons[]`;\n- `mapping_ready`: `blocked` (review pending) until a human records approval;\n- `current_stage`, `next_action`, `last_checked_at`, `checked_by`.\n\nEvery `pass` MUST carry `evidence[]`; every `blocked` MUST carry\n`blocking_reasons[]`; emit NO numeric confidence score.\n\n## Human seams -- HARD-STOP (Principle V; the wizard proposes, a human decides)\n\nEach is a judgment call the agent cannot settle from data alone. PROPOSE it with the\nsupporting data fact, raise an `unresolved-questions.md` row with a NAMED owner, set\nthe matching `blocking_reasons[]`, and STOP -- NEVER satisfiable by a silent default:\n\n| Seam | Trigger | Propose (with data fact) | Owner |\n|------|---------|--------------------------|-------|\n| **Grain** | candidate PK not unique on the rows | report the duplicate count; propose the finer grain \u002F composite PK -- never collapse or pick silently | analyst |\n| **PII publish-safety** | a `pii:true` candidate column | propose the default (drop before the BI layer, RC4); raise the publish-safety question | governance |\n| **Business rollup \u002F segment** | a categorical needing a value->group mapping | NEVER invent the mapping; raise it for the analyst-supplied table; default unmapped -> `UNMAPPED` | analyst |\n| **Product identity** | which column authoritatively identifies the entity (or two columns disagree) | report the conflict; never assert identity | analyst \u002F data owner |\n\n**Conflicting answer rule:** if an analyst answer contradicts a profiled data fact,\nsurface the conflict and STOP to reconcile -- do not proceed (evidence-cross-check).\n\n## Terminal: Mapping Ready -- STOP\n\nWhen the artifacts are authored and the gate is `OPEN` (review pending): emit the\nreconciliation blank, set `mapping_ready: blocked`, state the SINGLE next allowed\naction (\"human review + approval of the map\"), and explicitly confirm the wizard\nwrote NO `silver.*` and self-granted NO approval. When `Gate status: CLEARED` +\n`approvals[]` already exist (a human approved): promote `mapping_ready: pass`\n(evidence = the artifacts + the approval), state \"Mapping Ready reached; the next\nstage is Silver Ready \u002F `retail-build-warehouse` -- OUT of this wizard's scope\", and\nSTOP. The wizard never authors silver.\n\n## Deferred-boundary mode (no DSN or no `db` extra)\n\nIf no DSN is configured or the `db` extra is absent: do NOT traceback and do NOT\nfabricate profile numbers. Mark the mechanical rows `[PENDING LIVE PROFILE]`, record\n`source_ready: warning` (never `pass`), and print the enable steps:\n`pipx inject seshat-bi psycopg2-binary` (or `pip install \"seshat-bi[db]\"`), then set\n`DATABASE_URL` (or `ANALYTICS_DB_*`) in the git-ignored `.env` -- never commit a real\nDSN. The semantic stop-and-ask and the gate\nstop still run (they need no DB).\n\n## Generic, not C086\n\nThis skill and the onboarding checklist are GENERIC (roadmap rule 7). No\nC086\u002Fpharmacy specifics (billing codes, segment rollups, PII column names, pharmacy\ngrain keys) appear here -- placeholders only. A worked example is CITED as a filled\ninstance (see the filled worked examples), never copied.\n\n## See also\n\n- The two stages spanned: the Source Ready and Mapping Ready definitions.\n- The reviewable definition-of-done: the onboarding checklist.\n- The spine + state model: the readiness model and readiness pipeline, plus the\n  readiness-status template.\n- The delegated mapping leg: the `source-mapping` skill.\n- The downstream build verb (out of scope here): the `retail-build-warehouse`\n  skill.\n- The roadmap row: F006, Layers 1-2, Source -> Mapping.\n- Principles: constitution I, IV, V, VII, VIII, IX.\n\n## Orchestration\n\nWhen a table is driven end-to-end, the `retail-orchestrate` conductor invokes this\nwizard as its Source -> Mapping leg (Phases 1-4). This skill does that leg and STOPS\nat Mapping Ready; the cross-table self-heal loop (run gate -> classify -> auto-fix\nmechanical \u002F HARD-STOP judgment calls -> re-run) lives ONLY in `retail-orchestrate`,\nnever here. Mapping-gate approval is the reviewer's action; no loop self-grants it.\n","# retail-onboard-table\n\nThe onboarding front door for ONE table's first two readiness stages. The kit\nalready ships the verb that authors the mapping artifacts (`source-mapping`) and the\nconductor that sequences every verb end-to-end (`retail-orchestrate`). This skill is\nthe stage-scoped composition between them: \"I have a new raw table -- walk me from\nnothing to a reviewed map.\" It advances **Source Ready -> Mapping Ready**, seeds the\nper-table `readiness-status.yaml`, and STOPS. It is a procedure the agent performs\n(agent-first, Principle I); `seshat check` and the read-only profile are gates it\nCALLS, not a CLI subcommand.\n\n## Scope boundary (read first)\n\n- **Agent-first, no CLI.** This is a SKILL the agent runs; it adds no `retail`\n  subcommand and no Python.\n- **ENTERS at Source Ready, EXITS at Mapping Ready.** The terminal state is Mapping\n  Ready -- the three gate artifacts committed and either `mapping_ready: blocked`\n  (review pending, the common case) or `mapping_ready: pass` (only after a HUMAN has\n  recorded approval). Both are successful wizard runs.\n- **NEVER crosses into Silver Ready** (Principle IV, roadmap rule #2). It writes no\n  `silver.*` SQL, no migration, and never calls `retail-build-warehouse`. Its last\n  action is to seed\u002Fupdate the readiness-status, state the next allowed action, and\n  STOP.\n- **NEVER self-grants approval or invents a judgment call** (Principle V). The four\n  reserved seams -- grain, PII publish-safety, business rollup\u002Fsegment, product\n  identity -- are PROPOSED with a data fact and raised as `unresolved-questions.md`\n  rows; the wizard stops there.\n- **No fake confidence.** Readiness is the four explicit statuses\n  (`not_started` | `blocked` | `warning` | `pass`) + `evidence[]` +\n  `blocking_reasons[]`. No numeric score (roadmap rule #9).\n- **Delegates mapping; does not duplicate it.** Stage 2 invokes `source-mapping` to\n  author the five artifacts. This skill owns the WALK and the readiness bookkeeping,\n  not the mapping procedure.\n- ASCII only, UTF-8 no BOM (`->` arrows, `'' OR NULL`).\n\n## Run-state: read mappings\u002F\u003Ctable>\u002F FIRST (no new state file)\n\nCompute the current stage from what is already on disk -- there is NO onboarding\nstate file to create (mirrors `retail-orchestrate`'s run-state rule):\n\n| What you observe | Current stage \u002F action |\n|------------------|------------------------|\n| No `mappings\u002F\u003Ctable>\u002F` dir | Start at **Stage 1** (profile). |\n| `source-profile.md` present, no `source-map.yaml` | Resume at **Stage 2** (delegate to `source-mapping`). |\n| The five artifacts present, `unresolved-questions.md` shows `Gate status: OPEN` (or open rows) | **STOPPED at the gate** -- report the open questions; do not overwrite, do not advance. |\n| `Gate status: CLEARED`, zero open rows, an `approvals[]` entry recorded | **Mapping Ready reached** -- promote `mapping_ready: pass`; state Silver Ready is the next (out-of-scope) stage; STOP. |\n\nResume from the first incomplete artifact; NEVER clobber a committed (reviewed) one.\nYou may READ `Gate status`; you may NOT write `CLEARED` yourself (that is the\nreviewer's action).\n\n## Stage 1 -- Source Ready (profile + PROPOSE semantics)\n\nDrive the mechanical profile over a READ-ONLY connection and record into\n`mappings\u002F\u003Ctable>\u002Fsource-profile.md` (definition-of-done = `source-ready.md` `pass`):\n\n- row count + column count;\n- per-column missingness measured as `'' OR NULL` (never `IS NULL` alone -- RC5);\n- candidate-key uniqueness proof (does the proposed PK hold on the data?);\n- returns-column population.\n\nSemantic rows (what each column MEANS) are PROPOSED for human confirmation, never\ninvented. Record `source_ready: pass` with `source-profile.md` as evidence when the\nmechanical numbers are measured; `warning` in deferred-boundary mode (below); or\n`blocked` with the concrete reason if a required number is unmeasurable -- and then\ndo NOT enter Stage 2 (no mapping on an unprofiled source).\n\n## Stage 2 -- Mapping Ready (delegate to source-mapping)\n\nInvoke the `source-mapping` skill to author the five artifacts under\n`mappings\u002F\u003Ctable>\u002F` (definition-of-done = `mapping-ready.md`'s artifact set):\n\n- `source-map.yaml` -- grain, PK, every column's `pii:` flag, gold placement;\n- `assumptions.md` -- RC1-RC16 adopted\u002Fdeviated, each deviation citing a data fact;\n- `unresolved-questions.md` -- the open judgment calls (`Gate status: OPEN` until a\n  human clears it);\n- the `reconciliation-report.md` blank (the live-acceptance run, filled later).\n\nDo NOT duplicate the mapping procedure -- it lives in `source-mapping`. The wizard\nsequences the call and then does the readiness bookkeeping below.\n\n## Readiness-status bookkeeping\n\nSeed\u002Fupdate the per-table status from the readiness-status template at the\ncanonical `mappings\u002F\u003Ctable>\u002Freadiness-status.yaml` (ADR 0004 -- co-located with the\nmapping artifacts, spans all seven stages). The wizard is the FIRST writer of this\nfile. Set:\n\n- `source_ready`: `pass` (mechanical numbers measured) \u002F `warning` (deferred mode) \u002F\n  `blocked` (unmeasurable) -- with `evidence[]` or `blocking_reasons[]`;\n- `mapping_ready`: `blocked` (review pending) until a human records approval;\n- `current_stage`, `next_action`, `last_checked_at`, `checked_by`.\n\nEvery `pass` MUST carry `evidence[]`; every `blocked` MUST carry\n`blocking_reasons[]`; emit NO numeric confidence score.\n\n## Human seams -- HARD-STOP (Principle V; the wizard proposes, a human decides)\n\nEach is a judgment call the agent cannot settle from data alone. PROPOSE it with the\nsupporting data fact, raise an `unresolved-questions.md` row with a NAMED owner, set\nthe matching `blocking_reasons[]`, and STOP -- NEVER satisfiable by a silent default:\n\n| Seam | Trigger | Propose (with data fact) | Owner |\n|------|---------|--------------------------|-------|\n| **Grain** | candidate PK not unique on the rows | report the duplicate count; propose the finer grain \u002F composite PK -- never collapse or pick silently | analyst |\n| **PII publish-safety** | a `pii:true` candidate column | propose the default (drop before the BI layer, RC4); raise the publish-safety question | governance |\n| **Business rollup \u002F segment** | a categorical needing a value->group mapping | NEVER invent the mapping; raise it for the analyst-supplied table; default unmapped -> `UNMAPPED` | analyst |\n| **Product identity** | which column authoritatively identifies the entity (or two columns disagree) | report the conflict; never assert identity | analyst \u002F data owner |\n\n**Conflicting answer rule:** if an analyst answer contradicts a profiled data fact,\nsurface the conflict and STOP to reconcile -- do not proceed (evidence-cross-check).\n\n## Terminal: Mapping Ready -- STOP\n\nWhen the artifacts are authored and the gate is `OPEN` (review pending): emit the\nreconciliation blank, set `mapping_ready: blocked`, state the SINGLE next allowed\naction (\"human review + approval of the map\"), and explicitly confirm the wizard\nwrote NO `silver.*` and self-granted NO approval. When `Gate status: CLEARED` +\n`approvals[]` already exist (a human approved): promote `mapping_ready: pass`\n(evidence = the artifacts + the approval), state \"Mapping Ready reached; the next\nstage is Silver Ready \u002F `retail-build-warehouse` -- OUT of this wizard's scope\", and\nSTOP. The wizard never authors silver.\n\n## Deferred-boundary mode (no DSN or no `db` extra)\n\nIf no DSN is configured or the `db` extra is absent: do NOT traceback and do NOT\nfabricate profile numbers. Mark the mechanical rows `[PENDING LIVE PROFILE]`, record\n`source_ready: warning` (never `pass`), and print the enable steps:\n`pipx inject seshat-bi psycopg2-binary` (or `pip install \"seshat-bi[db]\"`), then set\n`DATABASE_URL` (or `ANALYTICS_DB_*`) in the git-ignored `.env` -- never commit a real\nDSN. The semantic stop-and-ask and the gate\nstop still run (they need no DB).\n\n## Generic, not C086\n\nThis skill and the onboarding checklist are GENERIC (roadmap rule 7). No\nC086\u002Fpharmacy specifics (billing codes, segment rollups, PII column names, pharmacy\ngrain keys) appear here -- placeholders only. A worked example is CITED as a filled\ninstance (see the filled worked examples), never copied.\n\n## See also\n\n- The two stages spanned: the Source Ready and Mapping Ready definitions.\n- The reviewable definition-of-done: the onboarding checklist.\n- The spine + state model: the readiness model and readiness pipeline, plus the\n  readiness-status template.\n- The delegated mapping leg: the `source-mapping` skill.\n- The downstream build verb (out of scope here): the `retail-build-warehouse`\n  skill.\n- The roadmap row: F006, Layers 1-2, Source -> Mapping.\n- Principles: constitution I, IV, V, VII, VIII, IX.\n\n## Orchestration\n\nWhen a table is driven end-to-end, the `retail-orchestrate` conductor invokes this\nwizard as its Source -> Mapping leg (Phases 1-4). This skill does that leg and STOPS\nat Mapping Ready; the cross-table self-heal loop (run gate -> classify -> auto-fix\nmechanical \u002F HARD-STOP judgment calls -> re-run) lives ONLY in `retail-orchestrate`,\nnever here. Mapping-gate approval is the reviewer's action; no loop self-grants it.\n",{"name":5,"description":7},"main","6266e304556a72b75d951b9433fd833481c61233","integrations\u002Fcodex\u002Fseshat-bi\u002Fskills\u002Fretail-onboard-table",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 retail-onboard-table",{"tool":37,"command":38},"bunx","bunx skills add Kemetra\u002FSeshat-BI --skill retail-onboard-table",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Kemetra\u002FSeshat-BI --skill retail-onboard-table","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002Fintegrations\u002Fcodex\u002Fseshat-bi\u002Fskills\u002Fretail-onboard-table\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",[],[]]