[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JCDS97JJ36Y00K7GFDFQG":3,"skill-same:01M77JCDS97JJ36Y00K7GFDFQG":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},"01M77JCDS97JJ36Y00K7GFDFQG","retail-discover-portfolio",null,"Discover an unfamiliar retail data portfolio before per-table onboarding. Produces one metadata-only Layer-A survey across every reachable table, proposes non-critical domain and first-delivery scope decisions, delegates selected tables to retail-onboard-table for Layer-B profiling, and hands off to the existing business-knowledge-interview. Never samples source values, self-confirms a decision, or advances beyond the interview handoff.","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\u002F.claude\u002Fskills\u002Fretail-discover-portfolio\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: retail-discover-portfolio\ndescription: >-\n  Discover an unfamiliar retail data portfolio before per-table onboarding.\n  Produces one metadata-only Layer-A survey across every reachable table, proposes\n  non-critical domain and first-delivery scope decisions, delegates selected\n  tables to retail-onboard-table for Layer-B profiling, and hands off to the\n  existing business-knowledge-interview. Never samples source values, self-confirms\n  a decision, or advances beyond the interview handoff.\n---\n\n# retail-discover-portfolio\n\nUse this skill when the owner has an unfamiliar database schema or file folder and\nneeds a governed route from portfolio discovery to the business interview.\n\n## Boundary\n\nThis is an agent-conducted flow, not a new state engine or CLI workflow:\n\nportfolio discovery -> domain -> scope -> selected-table onboarding -> interview handoff -> STOP\n\n- Layer A is the metadata-only portfolio survey in\n  templates\u002Fportfolio-survey.md.\n- Layer B is the existing value-backed, per-table Source Ready profile owned by\n  retail-onboard-table.\n- Never create a second profiler or author mappings\u002F\u003Ctable>\u002Fsource-profile.md here.\n- Never select a scale-out route. Record scale evidence for the existing\n  silver_gold_model_planning boundary to decide later.\n- Read the existing stage contracts and committed artifacts to derive exactly one\n  next action. Create no run-state, projection, or routing file.\n\nThe golden reference shapes are:\n\n- tests\u002Ffixtures\u002Fportfolio-survey\u002Fdb-schema\u002Fsurvey.md\n- tests\u002Ffixtures\u002Fportfolio-survey\u002Ffile-folder\u002Fsurvey.md\n\n## 1. Produce the Layer-A survey\n\nFor a database schema:\n\n1. Call seshat.portfolio_enumerate.enumerate_tables(schema). This helper is the\n   only DB table-enumeration path. Do not issue a raw information_schema.tables\n   query, and do not catch raw config, driver, or connection exceptions.\n2. If it returns an error, show only that redacted error. If no metadata is\n   readable, STOP and name the unblock: configure the gitignored .env, install\n   the matching retail DB extra, or grant metadata permission.\n3. For every returned table, read information_schema.columns plus declared PK\u002FFK\n   and catalog-estimate metadata through the same read-only boundary.\n\nFor a file folder, list every reachable CSV and Excel file and inspect only\nformat\u002Fschema metadata. Do not read source values.\n\nFill one committed survey from templates\u002Fportfolio-survey.md:\n\n- include every reachable table; never choose a table-count or time cap;\n- include declared types, declared PK\u002FFK metadata, catalog row estimates, and\n  name\u002Ftype-based date, PII-suspicion, grain, and structural-role hints;\n- label every inference candidate\u002Fhint, never a ruling;\n- for unavailable metadata, record [PENDING LIVE PROFILE] or needs_sample, the\n  exact reason, and the enabling step;\n- never measure uniqueness, missingness, date spans, or returns population;\n- never include raw or masked samples, suspected-PII values, credentials, DSNs,\n  or connection strings.\n\n## 2. Propose a domain\n\nPrecondition: a committed, non-empty portfolio survey exists. The inherited\ndomain_guess gate can pass with an absent store because its\nblocking_decision_categories is empty; therefore enforce this local precondition\nhere. If missing, STOP: \"portfolio survey missing; complete Layer-A discovery.\"\n\nLoad .seshat\u002Fsemantic-decisions.yaml first and append a non-critical proposal:\n\n- decision_type: domain_classification (free-form, not a critical type)\n- status: proposed\n- confidence: low | medium | high (proposal confidence only)\n- proposed_by: agent\n- proposed_at: ISO-8601 timestamp\n- evidence: non-empty citations to survey facts\n\nWhen evidence is ambiguous, record alternatives or \"undetermined\". Never approve,\nconfirm, or add an approval-authority.yaml row. A named human may confirm through\nthe existing low-risk batch path; follow spec 121's current status convention.\n\n## 3. Propose a bounded first-delivery scope\n\nPrecondition: the domain proposal exists. If missing, STOP:\n\"domain proposal missing; record a grounded domain guess.\"\n\nAppend a non-critical proposed scope decision with proposed_by, proposed_at,\nconfidence, and non-empty survey + domain evidence. Record candidate tables,\nbusiness questions, KPI names (not definitions), exclusions, and dependencies.\n\nBounding is deterministic:\n\n- honor an explicit owner-supplied scope limit;\n- otherwise prefer one coherent business process, one primary fact grain, and\n  KPI names sharing one model boundary;\n- when metadata crosses processes\u002Fgrains, present narrower coherent alternatives\n  or record needs_user_input.\n\nDescribe the result categorically as coherent, cross-boundary, unresolved, or\nneeds-user-input. Never store a numeric score, threshold, or rank. Partial\nacceptance creates a bounded new proposed record and marks the original\nsuperseded; never edit history in place.\n\nFor each selected table invoke retail-onboard-table. That existing skill alone\nproduces Layer-B source-profile.md. Do not deep-profile inside the survey.\n\n## 4. Hand off to the existing interview\n\nBefore handoff, require exactly the existing interview inputs:\n\n1. committed Layer-B per-table profiles for every selected table;\n2. the proposed scope;\n3. the existing Decision Store, loaded first and presented for confirmation or\n   supersession without overwriting any record.\n\nIf a selected table lacks its Layer-B profile, STOP and name that table plus the\nretail-onboard-table unblock. Then invoke business-knowledge-interview; do not\nre-implement it and do not record an interview outcome here. Route KPI-meaning\nquestions to the Retail KPI knowledge boundary.\n\nAt the interview handoff, STOP. This skill grants no approval and advances no\nreadiness stage.\n\n## Resume and local-stop table\n\n| Committed state | One next action |\n|-----------------|-----------------|\n| No survey | Produce the Layer-A portfolio survey. |\n| Survey, no domain proposal | Record the grounded domain proposal. |\n| Survey + domain, no scope | Record the bounded scope proposal. |\n| Scope, selected table lacks Layer-B profile | Invoke retail-onboard-table for that table. |\n| All Layer-B profiles + scope + loaded store | Hand off to business-knowledge-interview, then STOP. |\n| Request beyond interview handoff | STOP; continue under the downstream stage contract, not this skill. |\n\nEvery stop names the concrete missing artifact\u002Fdecision and the action that\nunblocks it. Existing Decision Store records are never overwritten; reruns present\nthem and changes use supersession.\n","# retail-discover-portfolio\n\nUse this skill when the owner has an unfamiliar database schema or file folder and\nneeds a governed route from portfolio discovery to the business interview.\n\n## Boundary\n\nThis is an agent-conducted flow, not a new state engine or CLI workflow:\n\nportfolio discovery -> domain -> scope -> selected-table onboarding -> interview handoff -> STOP\n\n- Layer A is the metadata-only portfolio survey in\n  templates\u002Fportfolio-survey.md.\n- Layer B is the existing value-backed, per-table Source Ready profile owned by\n  retail-onboard-table.\n- Never create a second profiler or author mappings\u002F\u003Ctable>\u002Fsource-profile.md here.\n- Never select a scale-out route. Record scale evidence for the existing\n  silver_gold_model_planning boundary to decide later.\n- Read the existing stage contracts and committed artifacts to derive exactly one\n  next action. Create no run-state, projection, or routing file.\n\nThe golden reference shapes are:\n\n- tests\u002Ffixtures\u002Fportfolio-survey\u002Fdb-schema\u002Fsurvey.md\n- tests\u002Ffixtures\u002Fportfolio-survey\u002Ffile-folder\u002Fsurvey.md\n\n## 1. Produce the Layer-A survey\n\nFor a database schema:\n\n1. Call seshat.portfolio_enumerate.enumerate_tables(schema). This helper is the\n   only DB table-enumeration path. Do not issue a raw information_schema.tables\n   query, and do not catch raw config, driver, or connection exceptions.\n2. If it returns an error, show only that redacted error. If no metadata is\n   readable, STOP and name the unblock: configure the gitignored .env, install\n   the matching retail DB extra, or grant metadata permission.\n3. For every returned table, read information_schema.columns plus declared PK\u002FFK\n   and catalog-estimate metadata through the same read-only boundary.\n\nFor a file folder, list every reachable CSV and Excel file and inspect only\nformat\u002Fschema metadata. Do not read source values.\n\nFill one committed survey from templates\u002Fportfolio-survey.md:\n\n- include every reachable table; never choose a table-count or time cap;\n- include declared types, declared PK\u002FFK metadata, catalog row estimates, and\n  name\u002Ftype-based date, PII-suspicion, grain, and structural-role hints;\n- label every inference candidate\u002Fhint, never a ruling;\n- for unavailable metadata, record [PENDING LIVE PROFILE] or needs_sample, the\n  exact reason, and the enabling step;\n- never measure uniqueness, missingness, date spans, or returns population;\n- never include raw or masked samples, suspected-PII values, credentials, DSNs,\n  or connection strings.\n\n## 2. Propose a domain\n\nPrecondition: a committed, non-empty portfolio survey exists. The inherited\ndomain_guess gate can pass with an absent store because its\nblocking_decision_categories is empty; therefore enforce this local precondition\nhere. If missing, STOP: \"portfolio survey missing; complete Layer-A discovery.\"\n\nLoad .seshat\u002Fsemantic-decisions.yaml first and append a non-critical proposal:\n\n- decision_type: domain_classification (free-form, not a critical type)\n- status: proposed\n- confidence: low | medium | high (proposal confidence only)\n- proposed_by: agent\n- proposed_at: ISO-8601 timestamp\n- evidence: non-empty citations to survey facts\n\nWhen evidence is ambiguous, record alternatives or \"undetermined\". Never approve,\nconfirm, or add an approval-authority.yaml row. A named human may confirm through\nthe existing low-risk batch path; follow spec 121's current status convention.\n\n## 3. Propose a bounded first-delivery scope\n\nPrecondition: the domain proposal exists. If missing, STOP:\n\"domain proposal missing; record a grounded domain guess.\"\n\nAppend a non-critical proposed scope decision with proposed_by, proposed_at,\nconfidence, and non-empty survey + domain evidence. Record candidate tables,\nbusiness questions, KPI names (not definitions), exclusions, and dependencies.\n\nBounding is deterministic:\n\n- honor an explicit owner-supplied scope limit;\n- otherwise prefer one coherent business process, one primary fact grain, and\n  KPI names sharing one model boundary;\n- when metadata crosses processes\u002Fgrains, present narrower coherent alternatives\n  or record needs_user_input.\n\nDescribe the result categorically as coherent, cross-boundary, unresolved, or\nneeds-user-input. Never store a numeric score, threshold, or rank. Partial\nacceptance creates a bounded new proposed record and marks the original\nsuperseded; never edit history in place.\n\nFor each selected table invoke retail-onboard-table. That existing skill alone\nproduces Layer-B source-profile.md. Do not deep-profile inside the survey.\n\n## 4. Hand off to the existing interview\n\nBefore handoff, require exactly the existing interview inputs:\n\n1. committed Layer-B per-table profiles for every selected table;\n2. the proposed scope;\n3. the existing Decision Store, loaded first and presented for confirmation or\n   supersession without overwriting any record.\n\nIf a selected table lacks its Layer-B profile, STOP and name that table plus the\nretail-onboard-table unblock. Then invoke business-knowledge-interview; do not\nre-implement it and do not record an interview outcome here. Route KPI-meaning\nquestions to the Retail KPI knowledge boundary.\n\nAt the interview handoff, STOP. This skill grants no approval and advances no\nreadiness stage.\n\n## Resume and local-stop table\n\n| Committed state | One next action |\n|-----------------|-----------------|\n| No survey | Produce the Layer-A portfolio survey. |\n| Survey, no domain proposal | Record the grounded domain proposal. |\n| Survey + domain, no scope | Record the bounded scope proposal. |\n| Scope, selected table lacks Layer-B profile | Invoke retail-onboard-table for that table. |\n| All Layer-B profiles + scope + loaded store | Hand off to business-knowledge-interview, then STOP. |\n| Request beyond interview handoff | STOP; continue under the downstream stage contract, not this skill. |\n\nEvery stop names the concrete missing artifact\u002Fdecision and the action that\nunblocks it. Existing Decision Store records are never overwritten; reruns present\nthem and changes use supersession.\n",{"name":5,"description":7},"main","6266e304556a72b75d951b9433fd833481c61233",".claude\u002Fskills\u002Fretail-discover-portfolio",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-discover-portfolio",{"tool":37,"command":38},"bunx","bunx skills add Kemetra\u002FSeshat-BI --skill retail-discover-portfolio",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Kemetra\u002FSeshat-BI --skill retail-discover-portfolio","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fretail-discover-portfolio\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",[],[]]