[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77JEGSC3JEJDNHY60GVNHT0":3,"skill-same:01M77JEGSC3JEJDNHY60GVNHT0":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},"01M77JEGSC3JEJDNHY60GVNHT0","showcase-build",null,"Compose a shareable, disclosure-safe, OFFLINE proof bundle of Seshat BI's committed readiness truth -- stages, evidence, blockers, approvals, next actions, metric lineage, a truthful badge\u002Fproject card, and a four-category disclosure manifest -- for a maintainer or analyst to hand to a reviewer, stakeholder, or prospective contributor. Use when someone asks for a \"shareable proof\", a \"showcase bundle\", a \"project card\", or \"something I can send to show what Seshat has governed here\". This is a Product Module, artifact-writing: it READS the shipped Explorer projection (`build_explorer_projection`), the Passport (`seshat.passport`), and the disclosure scanner (`seshat.disclosure.scan_disclosure`), composes ONE offline HTML bundle, and STOPS. It recomputes NO readiness, defines NO new evidence schema, invents NO meaning, and grants NO approval. It is fail-closed: a disclosure finding over the FULL composed body blocks generation and writes nothing. Generation is local-only (`.seshat-output\u002F`); publishing the bundle anywhere is a separate, explicit human action this skill never performs.","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\u002Fshowcase-build\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: showcase-build\ndescription: >-\n  Compose a shareable, disclosure-safe, OFFLINE proof bundle of Seshat BI's\n  committed readiness truth -- stages, evidence, blockers, approvals, next\n  actions, metric lineage, a truthful badge\u002Fproject card, and a four-category\n  disclosure manifest -- for a maintainer or analyst to hand to a reviewer,\n  stakeholder, or prospective contributor. Use when someone asks for a\n  \"shareable proof\", a \"showcase bundle\", a \"project card\", or \"something I\n  can send to show what Seshat has governed here\". This is a Product Module,\n  artifact-writing: it READS the shipped Explorer projection\n  (`build_explorer_projection`), the Passport (`seshat.passport`), and the\n  disclosure scanner (`seshat.disclosure.scan_disclosure`), composes ONE\n  offline HTML bundle, and STOPS. It recomputes NO readiness, defines NO new\n  evidence schema, invents NO meaning, and grants NO approval. It is\n  fail-closed: a disclosure finding over the FULL composed body blocks\n  generation and writes nothing. Generation is local-only\n  (`.seshat-output\u002F`); publishing the bundle anywhere is a separate, explicit\n  human action this skill never performs.\n---\n\n# showcase-build\n\n- **Roadmap feature \u002F spec:** `specs\u002F127-showcase-build\u002F` (Shareable Seshat\n  Proof \u002F Showcase Bundle).\n- **Authority category:** Product Module \u002F `artifact-writing`\n  (`docs\u002Farchitecture\u002Fproduct-modules.md`).\n- **Delivery shape:** a read-only skill over a reusable library function\n  (`src\u002Fseshat\u002Fshowcase\u002Fbuild.py`), per the ratified Option B decision\n  (`docs\u002Froadmap\u002Fdecisions\u002Fcli-verbs-vs-skill-driven.md`, 2026-07-07). **No\n  new top-level CLI verb is added** -- `seshat.cli._DISPATCH` has no\n  `showcase` key, and importing `seshat.showcase` adds no network\u002Fdriver\n  import (mirrors the B1\u002FB3 lazy-import guard).\n\nA \"shareable proof\" is a single offline folder that answers \"what has Seshat\ngoverned here, and can I trust it?\" -- the readiness spine, the evidence, the\nblockers, the approvals, and the metric lineage together, a truthful badge\n(never a fabricated score), and a disclosure manifest stating exactly what is\nincluded, redacted, omitted, and unavailable. This skill is the COMPOSER: it\nfills the bundle from surfaces that already ship (the Explorer projection,\nthe Passport, the disclosure scanner); it originates no readiness truth of\nits own.\n\n## Module contract (the filled F024 declaration)\n\n- **Authority category:** Product Module\n- **Capability level:** `artifact-writing` *(exactly one)*\n- **Product layer:** `6` *(delivery\u002Fhandoff rendering, sibling of the F013\n  handoff pack and the F026\u002FF028 read-only lenses)*\n- **Owner:** the analyst or maintainer requesting the proof\n- **Status:** Authored\n\n### What it does (one line)\n\n> Composes the already-committed readiness projection, an evidence-derived\n> badge, and a four-category disclosure manifest into one offline HTML\n> bundle, running the fail-closed disclosure scan over the FULL composed\n> body before ever writing a file.\n\n### Core Authority it READS\n\n- `seshat.explorer.build.build_explorer_projection` -- stages, evidence\n  states (`available` \u002F `missing` \u002F `deferred`), blockers, approvals,\n  next actions, metric lineage, and input-defect entries.\n- `seshat.passport` (`verify_passport`) -- ONLY when two snapshot paths are\n  supplied, to compute the optional before\u002Fafter section.\n- `seshat.disclosure.scan_disclosure` -- the shared fail-closed scanner, run\n  over the full composed bundle body (not merely the base projection).\n- `seshat.cli.guards.resolve_local_output` -- the contained-output guard.\n\n### Derived evidence it WRITES\n\n- One offline HTML file (default `showcase\u002Findex.html`) under the contained\n  `.seshat-output\u002F` root, plus any inlined\u002Fembedded sidecar content (nothing\n  external is ever referenced).\n\n### Approved step it EXECUTES\n\n- none. It composes and writes ONE local file, then STOPS. It runs no\n  `seshat check` \u002F `retail validate` of its own, opens no database, and\n  calls no Power BI execution adapter.\n\n### Forbidden operations\n\n- MUST NOT recompute readiness, define a new evidence schema, or invent a\n  new Explorer\u002FPassport (FR-001\u002FFR-002) -- it renders the existing ones.\n- MUST NOT show any stage as `pass` without inspectable evidence (FR-003).\n- MUST NOT write outside the contained `.seshat-output\u002F` root (FR-006).\n- MUST NOT publish, upload, track users, or call any external network\u002FAPI\n  (FR-007\u002FFR-008) -- every asset is inlined or a data URI.\n- MUST NOT grant or imply any approval or publish sign-off (FR-011).\n- MUST NOT express a percentage, grade, or any other fabricated confidence\n  number anywhere in the badge, card, or manifest (FR-013, FR-026; hard\n  rule #9).\n- MUST NOT modify `src\u002Fseshat\u002Fexplorer\u002Fassets\u002Fexplorer.css` \u002F\n  `explorer.js`, or any source readiness artifact (FR-025).\n- MUST NOT add a new top-level CLI verb (FR-005; ratified Option B).\n\n### How it handles a missing or unsafe input\n\n- A missing artifact renders as missing; a malformed readiness file renders\n  as an input defect; a deferred live check renders as unavailable -- never\n  as a pass (FR-003; Principle V, stop-and-ask, never invent).\n- A live disclosure finding (secret, DSN, PII value, or a residual absolute\n  path that survives portability normalization) in the FULL composed body\n  BLOCKS generation fail-closed: no partial or redacted file is written; the\n  findings are printed (FR-009\u002FFR-010).\n- Two Passport snapshots that are not comparable (different `scope`,\n  different `schema_version`, or fewer than two supplied) omit the\n  before\u002Fafter section gracefully with a truthful note -- never a\n  fabricated delta (FR-020\u002FFR-021).\n\n## Scope boundary (read first)\n\n- **Composes, never invents.** Every fact in the bundle traces to the\n  reused Explorer projection or a supplied Passport snapshot. A missing\n  artifact is missing; a deferred live check is unavailable; a malformed\n  file is an input defect. Nothing is inferred into a pass.\n- **Read-only over every source.** Generating or browsing the bundle never\n  modifies a readiness status file, a database, or a Power BI model. After a\n  run, `git status` shows only new files under `.seshat-output\u002F` (typically\n  git-ignored).\n- **Fail-closed disclosure, full body.** The scan runs over tables, enriched\n  lineage, approval receipts, the badge, the manifest, and any before\u002Fafter\n  content -- INCLUDING user-supplied snapshot content the base projection\n  never saw. A blocking finding writes nothing.\n- **No fake confidence, ever.** The badge states the highest CONTIGUOUS\n  `pass` stage and the passed-stage count (e.g. \"3\u002F7 stages ready --\n  Gold: blocked\"). It never states a percentage, a grade, or an invented\n  score (hard rule #9). When no stage has passed, it states the truthful\n  onboarding status, never an empty or celebratory claim.\n- **Four-category manifest, no silent drops.** Every composed item lands\n  under exactly one of included \u002F unavailable \u002F omitted \u002F redacted, each\n  with a locator. \"Redacted\" names ONLY the composer's own by-design\n  portability normalizations (an absolute path reduced to repo-relative, a\n  private\u002Finternal URL stripped) -- never the suppression of a disclosure\n  finding (those block, they are not redacted).\n- **Own shell, untouched Explorer.** The bundle renders `showcase.css` \u002F\n  `showcase.js` (its own assets); it never reads or edits\n  `explorer.css` \u002F `explorer.js`.\n- **Generation is not publication.** Producing the bundle never grants a\n  publish approval or PII sign-off. Sharing the file anywhere is a separate,\n  explicit human action outside this skill.\n- **Generic.** No worked-example specifics baked in; `retail_store_sales`\n  (`docs\u002Fworked-examples\u002Fretail-store-sales.md`) is a cited filled instance,\n  never hard-coded (Principle VII). ASCII + UTF-8 no BOM for any text this\n  skill's caller writes back into the repo (the skill itself only writes\n  under `.seshat-output\u002F`, which is not tracked).\n\n## Procedure (numbered; do not reorder)\n\n1. **Resolve inputs.** Workspace root (default `.`); optional output path\n   (must resolve inside `.seshat-output\u002F`); optional `rtl` render mode;\n   optional two Passport snapshot file paths for the before\u002Fafter section.\n2. **Compose.** Call\n   `seshat.showcase.build.build_showcase_bundle(root, snapshots=...)`. This\n   reads the Explorer projection, derives the badge and manifest, applies\n   portability normalization (absolute path -> repo-relative; private URL\n   stripped -- each listed under the manifest's `redacted` category), and\n   computes the optional comparison if two snapshots were supplied.\n3. **Disclosure gate.** If `bundle[\"disclosure\"][\"status\"] != \"pass\"`: STOP\n   fail-closed. Print every finding (`rule`, `locator`, `message`). Write\n   NOTHING. This is not a partial-write case -- no file appears.\n4. **Resolve the output path.** Call\n   `seshat.cli.guards.resolve_local_output(root, output)`. If the path\n   escapes `.seshat-output\u002F`, refuse and write nothing (FR-006).\n5. **Render and write.** Call\n   `seshat.showcase.build.render_showcase_html(bundle, repo=root, rtl=...)`\n   and write the result to the resolved path.\n6. **Report and STOP.** Print the written path and this reminder verbatim:\n   \"This is a local offline snapshot generated from committed evidence only.\n   Publishing it anywhere is a separate, explicit human action.\" Do not\n   publish, upload, or record any approval. Any judgment call surfaced in\n   the bundle (an unresolved assumption, a blocked gate, a retracted\n   approval) is a stop-and-ask for the named human (Principle V) -- this\n   skill only renders it.\n\n## Refusals\n\n- **Uncontained output path** -- refuse before writing; nothing is written\n  outside `.seshat-output\u002F`.\n- **Blocking disclosure finding** -- refuse fail-closed; print the findings;\n  write nothing (no partial\u002Fredacted bundle).\n- **A request to publish, upload, or otherwise distribute the bundle** --\n  out of scope. This skill only writes a local file; publishing is the\n  named human's separate, explicit action.\n- **A request for a numeric confidence\u002Fhealth\u002Fpercent-ready score** --\n  refuse; the badge\u002Fmanifest already state the truthful stage-and-count\n  summary (hard rule #9).\n\n## Honest-state rules (never invent, never silently resolve)\n\n| Situation | What the skill does |\n|-----------|----------------------|\n| No table has reached any stage (or the workspace has no onboarded table) | badge states the truthful onboarding status; never an empty or celebratory claim |\n| A readiness file is malformed | rendered as an input defect in the table panel AND listed under the manifest's `omitted` category |\n| A secret \u002F DSN \u002F PII value \u002F residual absolute path is present anywhere in the composed body | generation blocks fail-closed; findings printed; nothing written |\n| A metric contract is unreadable | rendered as an input-defect lineage node, never a valid metric |\n| Two snapshots share scope but one is malformed or a different schema | treated as not comparable; the before\u002Fafter section is omitted with a note |\n| Only one snapshot (or none) is supplied | no before\u002Fafter section; no fabricated delta |\n\n## See also\n\n- The spec: `specs\u002F127-showcase-build\u002Fspec.md`, `plan.md`, `data-model.md`,\n  `contracts\u002Fshowcase-contract.md`, `quickstart.md`, `research.md`.\n- The library it composes: `src\u002Fseshat\u002Fshowcase\u002Fbuild.py`,\n  `src\u002Fseshat\u002Fshowcase\u002Fbadge.py`, `src\u002Fseshat\u002Fshowcase\u002Fmanifest.py`,\n  `src\u002Fseshat\u002Fshowcase\u002Fcompare.py`.\n- The reused shipped surfaces: `src\u002Fseshat\u002Fexplorer\u002Fbuild.py`,\n  `src\u002Fseshat\u002Fpassport.py`, `src\u002Fseshat\u002Fdisclosure.py`,\n  `src\u002Fseshat\u002Fcli\u002Fguards.py`.\n- The nearest sibling read-only lenses: `.claude\u002Fskills\u002Freadiness-viewer\u002F`\n  (stage matrix), `.claude\u002Fskills\u002Fevidence-pack-generator\u002F` (late-stage\n  pack) -- this skill's delta is that it renders an OFFLINE, SHAREABLE,\n  disclosure-scanned bundle with a badge and a manifest, not an in-repo\n  markdown artifact.\n- The Option B ratification this delivery shape applies:\n  `docs\u002Froadmap\u002Fdecisions\u002Fcli-verbs-vs-skill-driven.md`.\n- A cited filled worked example: `docs\u002Fworked-examples\u002Fretail-store-sales.md`.\n","# showcase-build\n\n- **Roadmap feature \u002F spec:** `specs\u002F127-showcase-build\u002F` (Shareable Seshat\n  Proof \u002F Showcase Bundle).\n- **Authority category:** Product Module \u002F `artifact-writing`\n  (`docs\u002Farchitecture\u002Fproduct-modules.md`).\n- **Delivery shape:** a read-only skill over a reusable library function\n  (`src\u002Fseshat\u002Fshowcase\u002Fbuild.py`), per the ratified Option B decision\n  (`docs\u002Froadmap\u002Fdecisions\u002Fcli-verbs-vs-skill-driven.md`, 2026-07-07). **No\n  new top-level CLI verb is added** -- `seshat.cli._DISPATCH` has no\n  `showcase` key, and importing `seshat.showcase` adds no network\u002Fdriver\n  import (mirrors the B1\u002FB3 lazy-import guard).\n\nA \"shareable proof\" is a single offline folder that answers \"what has Seshat\ngoverned here, and can I trust it?\" -- the readiness spine, the evidence, the\nblockers, the approvals, and the metric lineage together, a truthful badge\n(never a fabricated score), and a disclosure manifest stating exactly what is\nincluded, redacted, omitted, and unavailable. This skill is the COMPOSER: it\nfills the bundle from surfaces that already ship (the Explorer projection,\nthe Passport, the disclosure scanner); it originates no readiness truth of\nits own.\n\n## Module contract (the filled F024 declaration)\n\n- **Authority category:** Product Module\n- **Capability level:** `artifact-writing` *(exactly one)*\n- **Product layer:** `6` *(delivery\u002Fhandoff rendering, sibling of the F013\n  handoff pack and the F026\u002FF028 read-only lenses)*\n- **Owner:** the analyst or maintainer requesting the proof\n- **Status:** Authored\n\n### What it does (one line)\n\n> Composes the already-committed readiness projection, an evidence-derived\n> badge, and a four-category disclosure manifest into one offline HTML\n> bundle, running the fail-closed disclosure scan over the FULL composed\n> body before ever writing a file.\n\n### Core Authority it READS\n\n- `seshat.explorer.build.build_explorer_projection` -- stages, evidence\n  states (`available` \u002F `missing` \u002F `deferred`), blockers, approvals,\n  next actions, metric lineage, and input-defect entries.\n- `seshat.passport` (`verify_passport`) -- ONLY when two snapshot paths are\n  supplied, to compute the optional before\u002Fafter section.\n- `seshat.disclosure.scan_disclosure` -- the shared fail-closed scanner, run\n  over the full composed bundle body (not merely the base projection).\n- `seshat.cli.guards.resolve_local_output` -- the contained-output guard.\n\n### Derived evidence it WRITES\n\n- One offline HTML file (default `showcase\u002Findex.html`) under the contained\n  `.seshat-output\u002F` root, plus any inlined\u002Fembedded sidecar content (nothing\n  external is ever referenced).\n\n### Approved step it EXECUTES\n\n- none. It composes and writes ONE local file, then STOPS. It runs no\n  `seshat check` \u002F `retail validate` of its own, opens no database, and\n  calls no Power BI execution adapter.\n\n### Forbidden operations\n\n- MUST NOT recompute readiness, define a new evidence schema, or invent a\n  new Explorer\u002FPassport (FR-001\u002FFR-002) -- it renders the existing ones.\n- MUST NOT show any stage as `pass` without inspectable evidence (FR-003).\n- MUST NOT write outside the contained `.seshat-output\u002F` root (FR-006).\n- MUST NOT publish, upload, track users, or call any external network\u002FAPI\n  (FR-007\u002FFR-008) -- every asset is inlined or a data URI.\n- MUST NOT grant or imply any approval or publish sign-off (FR-011).\n- MUST NOT express a percentage, grade, or any other fabricated confidence\n  number anywhere in the badge, card, or manifest (FR-013, FR-026; hard\n  rule #9).\n- MUST NOT modify `src\u002Fseshat\u002Fexplorer\u002Fassets\u002Fexplorer.css` \u002F\n  `explorer.js`, or any source readiness artifact (FR-025).\n- MUST NOT add a new top-level CLI verb (FR-005; ratified Option B).\n\n### How it handles a missing or unsafe input\n\n- A missing artifact renders as missing; a malformed readiness file renders\n  as an input defect; a deferred live check renders as unavailable -- never\n  as a pass (FR-003; Principle V, stop-and-ask, never invent).\n- A live disclosure finding (secret, DSN, PII value, or a residual absolute\n  path that survives portability normalization) in the FULL composed body\n  BLOCKS generation fail-closed: no partial or redacted file is written; the\n  findings are printed (FR-009\u002FFR-010).\n- Two Passport snapshots that are not comparable (different `scope`,\n  different `schema_version`, or fewer than two supplied) omit the\n  before\u002Fafter section gracefully with a truthful note -- never a\n  fabricated delta (FR-020\u002FFR-021).\n\n## Scope boundary (read first)\n\n- **Composes, never invents.** Every fact in the bundle traces to the\n  reused Explorer projection or a supplied Passport snapshot. A missing\n  artifact is missing; a deferred live check is unavailable; a malformed\n  file is an input defect. Nothing is inferred into a pass.\n- **Read-only over every source.** Generating or browsing the bundle never\n  modifies a readiness status file, a database, or a Power BI model. After a\n  run, `git status` shows only new files under `.seshat-output\u002F` (typically\n  git-ignored).\n- **Fail-closed disclosure, full body.** The scan runs over tables, enriched\n  lineage, approval receipts, the badge, the manifest, and any before\u002Fafter\n  content -- INCLUDING user-supplied snapshot content the base projection\n  never saw. A blocking finding writes nothing.\n- **No fake confidence, ever.** The badge states the highest CONTIGUOUS\n  `pass` stage and the passed-stage count (e.g. \"3\u002F7 stages ready --\n  Gold: blocked\"). It never states a percentage, a grade, or an invented\n  score (hard rule #9). When no stage has passed, it states the truthful\n  onboarding status, never an empty or celebratory claim.\n- **Four-category manifest, no silent drops.** Every composed item lands\n  under exactly one of included \u002F unavailable \u002F omitted \u002F redacted, each\n  with a locator. \"Redacted\" names ONLY the composer's own by-design\n  portability normalizations (an absolute path reduced to repo-relative, a\n  private\u002Finternal URL stripped) -- never the suppression of a disclosure\n  finding (those block, they are not redacted).\n- **Own shell, untouched Explorer.** The bundle renders `showcase.css` \u002F\n  `showcase.js` (its own assets); it never reads or edits\n  `explorer.css` \u002F `explorer.js`.\n- **Generation is not publication.** Producing the bundle never grants a\n  publish approval or PII sign-off. Sharing the file anywhere is a separate,\n  explicit human action outside this skill.\n- **Generic.** No worked-example specifics baked in; `retail_store_sales`\n  (`docs\u002Fworked-examples\u002Fretail-store-sales.md`) is a cited filled instance,\n  never hard-coded (Principle VII). ASCII + UTF-8 no BOM for any text this\n  skill's caller writes back into the repo (the skill itself only writes\n  under `.seshat-output\u002F`, which is not tracked).\n\n## Procedure (numbered; do not reorder)\n\n1. **Resolve inputs.** Workspace root (default `.`); optional output path\n   (must resolve inside `.seshat-output\u002F`); optional `rtl` render mode;\n   optional two Passport snapshot file paths for the before\u002Fafter section.\n2. **Compose.** Call\n   `seshat.showcase.build.build_showcase_bundle(root, snapshots=...)`. This\n   reads the Explorer projection, derives the badge and manifest, applies\n   portability normalization (absolute path -> repo-relative; private URL\n   stripped -- each listed under the manifest's `redacted` category), and\n   computes the optional comparison if two snapshots were supplied.\n3. **Disclosure gate.** If `bundle[\"disclosure\"][\"status\"] != \"pass\"`: STOP\n   fail-closed. Print every finding (`rule`, `locator`, `message`). Write\n   NOTHING. This is not a partial-write case -- no file appears.\n4. **Resolve the output path.** Call\n   `seshat.cli.guards.resolve_local_output(root, output)`. If the path\n   escapes `.seshat-output\u002F`, refuse and write nothing (FR-006).\n5. **Render and write.** Call\n   `seshat.showcase.build.render_showcase_html(bundle, repo=root, rtl=...)`\n   and write the result to the resolved path.\n6. **Report and STOP.** Print the written path and this reminder verbatim:\n   \"This is a local offline snapshot generated from committed evidence only.\n   Publishing it anywhere is a separate, explicit human action.\" Do not\n   publish, upload, or record any approval. Any judgment call surfaced in\n   the bundle (an unresolved assumption, a blocked gate, a retracted\n   approval) is a stop-and-ask for the named human (Principle V) -- this\n   skill only renders it.\n\n## Refusals\n\n- **Uncontained output path** -- refuse before writing; nothing is written\n  outside `.seshat-output\u002F`.\n- **Blocking disclosure finding** -- refuse fail-closed; print the findings;\n  write nothing (no partial\u002Fredacted bundle).\n- **A request to publish, upload, or otherwise distribute the bundle** --\n  out of scope. This skill only writes a local file; publishing is the\n  named human's separate, explicit action.\n- **A request for a numeric confidence\u002Fhealth\u002Fpercent-ready score** --\n  refuse; the badge\u002Fmanifest already state the truthful stage-and-count\n  summary (hard rule #9).\n\n## Honest-state rules (never invent, never silently resolve)\n\n| Situation | What the skill does |\n|-----------|----------------------|\n| No table has reached any stage (or the workspace has no onboarded table) | badge states the truthful onboarding status; never an empty or celebratory claim |\n| A readiness file is malformed | rendered as an input defect in the table panel AND listed under the manifest's `omitted` category |\n| A secret \u002F DSN \u002F PII value \u002F residual absolute path is present anywhere in the composed body | generation blocks fail-closed; findings printed; nothing written |\n| A metric contract is unreadable | rendered as an input-defect lineage node, never a valid metric |\n| Two snapshots share scope but one is malformed or a different schema | treated as not comparable; the before\u002Fafter section is omitted with a note |\n| Only one snapshot (or none) is supplied | no before\u002Fafter section; no fabricated delta |\n\n## See also\n\n- The spec: `specs\u002F127-showcase-build\u002Fspec.md`, `plan.md`, `data-model.md`,\n  `contracts\u002Fshowcase-contract.md`, `quickstart.md`, `research.md`.\n- The library it composes: `src\u002Fseshat\u002Fshowcase\u002Fbuild.py`,\n  `src\u002Fseshat\u002Fshowcase\u002Fbadge.py`, `src\u002Fseshat\u002Fshowcase\u002Fmanifest.py`,\n  `src\u002Fseshat\u002Fshowcase\u002Fcompare.py`.\n- The reused shipped surfaces: `src\u002Fseshat\u002Fexplorer\u002Fbuild.py`,\n  `src\u002Fseshat\u002Fpassport.py`, `src\u002Fseshat\u002Fdisclosure.py`,\n  `src\u002Fseshat\u002Fcli\u002Fguards.py`.\n- The nearest sibling read-only lenses: `.claude\u002Fskills\u002Freadiness-viewer\u002F`\n  (stage matrix), `.claude\u002Fskills\u002Fevidence-pack-generator\u002F` (late-stage\n  pack) -- this skill's delta is that it renders an OFFLINE, SHAREABLE,\n  disclosure-scanned bundle with a badge and a manifest, not an in-repo\n  markdown artifact.\n- The Option B ratification this delivery shape applies:\n  `docs\u002Froadmap\u002Fdecisions\u002Fcli-verbs-vs-skill-driven.md`.\n- A cited filled worked example: `docs\u002Fworked-examples\u002Fretail-store-sales.md`.\n",{"name":5,"description":7},"main","6266e304556a72b75d951b9433fd833481c61233",".claude\u002Fskills\u002Fshowcase-build",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 showcase-build",{"tool":37,"command":38},"bunx","bunx skills add Kemetra\u002FSeshat-BI --skill showcase-build",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Kemetra\u002FSeshat-BI --skill showcase-build","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKemetra\u002FSeshat-BI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fshowcase-build\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",[],[]]