@wildo-ai/framework-knowledge 1.1.1 → 1.1.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (240) hide show
  1. package/dist/esm/framework-knowledge.definitions.d.ts +1 -1
  2. package/dist/esm/framework-knowledge.definitions.d.ts.map +1 -1
  3. package/dist/esm/framework-knowledge.definitions.js +43 -2
  4. package/dist/esm/framework-knowledge.definitions.js.map +1 -1
  5. package/dist/esm/framework-knowledge.loader.d.ts +19 -0
  6. package/dist/esm/framework-knowledge.loader.d.ts.map +1 -1
  7. package/dist/esm/framework-knowledge.loader.js +32 -0
  8. package/dist/esm/framework-knowledge.loader.js.map +1 -1
  9. package/dist/esm/framework-knowledge.schemas.d.ts +12 -0
  10. package/dist/esm/framework-knowledge.schemas.d.ts.map +1 -1
  11. package/dist/esm/framework-knowledge.schemas.js.map +1 -1
  12. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts +46 -0
  13. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts.map +1 -0
  14. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js +55 -0
  15. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js.map +1 -0
  16. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts +4 -4
  17. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js +3 -3
  18. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js.map +1 -1
  19. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts +0 -3
  20. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts.map +1 -1
  21. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js +0 -1
  22. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js.map +1 -1
  23. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts +0 -3
  24. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts.map +1 -1
  25. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js +0 -1
  26. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js.map +1 -1
  27. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts +2 -7
  28. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts.map +1 -1
  29. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js +0 -1
  30. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js.map +1 -1
  31. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts +8 -3
  32. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts.map +1 -1
  33. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js +22 -1
  34. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js.map +1 -1
  35. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts +0 -3
  36. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts.map +1 -1
  37. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js +0 -1
  38. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js.map +1 -1
  39. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.d.ts +4 -1
  40. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.d.ts.map +1 -1
  41. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.js +4 -1
  42. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.js.map +1 -1
  43. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.d.ts +1 -1
  44. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js +13 -13
  45. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js.map +1 -1
  46. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts +3 -4
  47. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts.map +1 -1
  48. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js +3 -3
  49. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js.map +1 -1
  50. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts +2 -7
  51. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts.map +1 -1
  52. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js +0 -1
  53. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js.map +1 -1
  54. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.d.ts +2 -7
  55. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.d.ts.map +1 -1
  56. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.js +0 -1
  57. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.js.map +1 -1
  58. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts +54 -0
  59. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts.map +1 -0
  60. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js +127 -0
  61. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js.map +1 -0
  62. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts +76 -0
  63. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts.map +1 -0
  64. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js +92 -0
  65. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js.map +1 -0
  66. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.d.ts +30 -0
  67. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.d.ts.map +1 -0
  68. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.js +29 -0
  69. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.js.map +1 -0
  70. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts +9 -44
  71. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts.map +1 -1
  72. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js +4 -53
  73. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js.map +1 -1
  74. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.d.ts +31 -0
  75. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.d.ts.map +1 -0
  76. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.js +26 -0
  77. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.js.map +1 -0
  78. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.d.ts +2 -7
  79. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.d.ts.map +1 -1
  80. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.js +0 -1
  81. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.js.map +1 -1
  82. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts +0 -8
  83. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts.map +1 -1
  84. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js +0 -1
  85. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js.map +1 -1
  86. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts +2 -7
  87. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts.map +1 -1
  88. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js +0 -1
  89. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js.map +1 -1
  90. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts +2 -7
  91. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts.map +1 -1
  92. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js +0 -1
  93. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js.map +1 -1
  94. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts +2 -7
  95. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts.map +1 -1
  96. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js +5 -3
  97. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js.map +1 -1
  98. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts +0 -3
  99. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts.map +1 -1
  100. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.js +0 -1
  101. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.js.map +1 -1
  102. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts +4 -5
  103. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts.map +1 -1
  104. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js +25 -4
  105. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js.map +1 -1
  106. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/authority-basis.json +1 -1
  107. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/external-framework-mapping.json +1 -0
  108. package/dist/knowledge/manifest.json +8 -8
  109. package/dist/knowledge/playbooks/bottom_up.assemble-verify/method.md +51 -0
  110. package/dist/knowledge/playbooks/bottom_up.assemble-verify/playbook.json +43 -0
  111. package/dist/knowledge/playbooks/bottom_up.build-decompose/method.md +27 -10
  112. package/dist/knowledge/playbooks/bottom_up.build-decompose/playbook.json +8 -7
  113. package/dist/knowledge/playbooks/bottom_up.build-dispatch/method.md +6 -4
  114. package/dist/knowledge/playbooks/bottom_up.build-dispatch/playbook.json +4 -6
  115. package/dist/knowledge/playbooks/bottom_up.build-scale/method.md +5 -4
  116. package/dist/knowledge/playbooks/bottom_up.build-scale/playbook.json +4 -6
  117. package/dist/knowledge/playbooks/bottom_up.domain-plan/method.md +0 -4
  118. package/dist/knowledge/playbooks/bottom_up.domain-plan/playbook.json +4 -6
  119. package/dist/knowledge/playbooks/bottom_up.foundation/method.md +49 -22
  120. package/dist/knowledge/playbooks/bottom_up.foundation/playbook.json +14 -6
  121. package/dist/knowledge/playbooks/bottom_up.placement-plan/playbook.json +2 -4
  122. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/method.md +46 -1
  123. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/playbook.json +7 -3
  124. package/dist/knowledge/playbooks/refinement.document-facts/method.md +18 -4
  125. package/dist/knowledge/playbooks/refinement.document-facts/playbook.json +4 -2
  126. package/dist/knowledge/playbooks/top_down.brand-identity/method.md +2 -3
  127. package/dist/knowledge/playbooks/top_down.brand-identity/playbook.json +8 -7
  128. package/dist/knowledge/playbooks/top_down.business-model/playbook.json +3 -5
  129. package/dist/knowledge/playbooks/top_down.capability-map/method.md +0 -2
  130. package/dist/knowledge/playbooks/top_down.capability-map/playbook.json +4 -6
  131. package/dist/knowledge/playbooks/top_down.compliance-analysis/method.md +41 -0
  132. package/dist/knowledge/playbooks/top_down.compliance-analysis/playbook.json +100 -0
  133. package/dist/knowledge/playbooks/top_down.compliance-conception/method.md +117 -0
  134. package/dist/knowledge/playbooks/top_down.compliance-conception/playbook.json +86 -0
  135. package/dist/knowledge/playbooks/top_down.compliance-evidence-adequacy/method.md +61 -0
  136. package/dist/knowledge/playbooks/top_down.compliance-evidence-adequacy/playbook.json +41 -0
  137. package/dist/knowledge/playbooks/top_down.compliance-posture/method.md +21 -4
  138. package/dist/knowledge/playbooks/top_down.compliance-posture/playbook.json +14 -57
  139. package/dist/knowledge/playbooks/top_down.compliance-research/method.md +76 -0
  140. package/dist/knowledge/playbooks/top_down.compliance-research/playbook.json +42 -0
  141. package/dist/knowledge/playbooks/top_down.market-analysis/playbook.json +3 -5
  142. package/dist/knowledge/playbooks/top_down.market-evidence-adequacy/playbook.json +3 -1
  143. package/dist/knowledge/playbooks/top_down.market-research/playbook.json +3 -1
  144. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/playbook.json +3 -5
  145. package/dist/knowledge/playbooks/top_down.phase-gate/method.md +8 -4
  146. package/dist/knowledge/playbooks/top_down.phase-gate/playbook.json +4 -6
  147. package/dist/knowledge/playbooks/top_down.requirements-definition/method.md +9 -7
  148. package/dist/knowledge/playbooks/top_down.requirements-definition/playbook.json +4 -6
  149. package/dist/knowledge/playbooks/top_down.scope-roadmap/method.md +2 -2
  150. package/dist/knowledge/playbooks/top_down.scope-roadmap/playbook.json +8 -7
  151. package/dist/knowledge/playbooks/top_down.value-proposition/method.md +0 -2
  152. package/dist/knowledge/playbooks/top_down.value-proposition/playbook.json +4 -6
  153. package/dist/knowledge/playbooks/top_down.vision-elicitation/method.md +2 -2
  154. package/dist/knowledge/playbooks/top_down.vision-elicitation/playbook.json +8 -7
  155. package/dist/knowledge/references/companion.technical-doc.service.md +102 -2
  156. package/dist/knowledge/references/example.config.app-shell.full.md +0 -1
  157. package/dist/knowledge/references/example.module.companion-exports.full.md +1 -0
  158. package/dist/knowledge/references/platform.config.saas.md +1 -0
  159. package/dist/knowledge/references/presets.models.surface-policy.md +19 -10
  160. package/dist/knowledge/references/saas.frontend.app-level-component.configuration.md +25 -1
  161. package/dist/knowledge/references/saas.frontend.composite-view.authoring.md +45 -0
  162. package/dist/knowledge/references/saas.frontend.display-layout.reading-measure.md +34 -0
  163. package/dist/knowledge/references/saas.frontend.navigation.operation-override.md +45 -0
  164. package/dist/knowledge/references/saas.frontend.public-shell.identity-mode.md +65 -0
  165. package/dist/knowledge/references/saas.frontend.resource-operation-frontend-config.md +89 -0
  166. package/dist/knowledge/references/saas.models.data-mode-read-list.md +31 -4
  167. package/dist/knowledge/references/saas.models.engine-capabilities.md +26 -6
  168. package/dist/knowledge/references/saas.models.file-upload-grant.md +179 -0
  169. package/dist/knowledge/references/saas.models.navigation.surface-vocabulary.md +124 -0
  170. package/dist/knowledge/references/saas.models.navigation.transition-vocabulary.md +99 -0
  171. package/dist/knowledge/references/saas.models.navigation.zone-declaration.md +127 -0
  172. package/dist/knowledge/references/saas.models.provider-capabilities.md +4 -3
  173. package/dist/knowledge/references/saas.models.resource-config.operation-variant-client-timeout.md +42 -0
  174. package/dist/knowledge/references/saas.specifications.application-authored-document-fact-specification.contract.md +29 -0
  175. package/dist/knowledge/references/saas.specifications.application-document-fact-specification.contract.md +11 -31
  176. package/dist/knowledge/references/saas.specifications.assurance-document-blueprint.contract.md +32 -2
  177. package/dist/knowledge/references/saas.specifications.assurance-program.contract.md +29 -6
  178. package/dist/knowledge/references/saas.specifications.companion-exports.contract.md +20 -0
  179. package/dist/knowledge/references/saas.specifications.resource-spec-config.md +22 -0
  180. package/dist/knowledge/references/zod.decorators.display-edit-modes.md +6 -0
  181. package/dist/knowledge/references/zod.decorators.field-spec-params.md +31 -5
  182. package/dist/knowledge/references/zod.decorators.per-primitive-ui.md +43 -0
  183. package/dist/knowledge/references/zod.decorators.primitive-ui.md +3 -0
  184. package/dist/knowledge/references/zod.decorators.shared-structural-params.md +15 -0
  185. package/dist/knowledge/registries/assurance-authority-bases.json +3 -2
  186. package/dist/knowledge/registries/framework-topics.json +99 -1
  187. package/dist/knowledge/registries/playbooks.json +81 -8
  188. package/dist/knowledge/registries/source-tags.json +757 -588
  189. package/dist/knowledge/skills/INDEX.md +3 -3
  190. package/dist/knowledge/skills/brand-logo-authoring/SKILL.md +2 -1
  191. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-governance.md +5 -1
  192. package/dist/knowledge/skills/compliance-document-authoring/references/framework-application-document-fact-specification-contract.md +66 -37
  193. package/dist/knowledge/skills/compliance-document-authoring/references/framework-assurance-document-blueprint-contract.md +40 -7
  194. package/dist/knowledge/skills/config-app-shell/SKILL.md +25 -1
  195. package/dist/knowledge/skills/config-app-shell/references/framework-app-shell-api.md +25 -1
  196. package/dist/knowledge/skills/config-app-shell/references/framework-public-shell-identity-api.md +124 -0
  197. package/dist/knowledge/skills/config-design-system/SKILL.md +23 -1
  198. package/dist/knowledge/skills/config-design-system/references/framework-surface-policy-api.md +19 -10
  199. package/dist/knowledge/skills/config-design-system/references/loading-placeholder-authoring.md +47 -0
  200. package/dist/knowledge/skills/config-navigation/SKILL.md +75 -2
  201. package/dist/knowledge/skills/config-navigation/references/framework-content-width-api.md +98 -0
  202. package/dist/knowledge/skills/config-navigation/references/framework-navigation-operation-override-api.md +54 -0
  203. package/dist/knowledge/skills/config-navigation/references/framework-navigation-vocabulary-api.md +232 -0
  204. package/dist/knowledge/skills/config-navigation/references/framework-navigation-zone-declaration-api.md +149 -0
  205. package/dist/knowledge/skills/config-navigation/references/how-navigation-resolves.md +114 -0
  206. package/dist/knowledge/skills/config-navigation/references/navigation-configuration-map.md +133 -0
  207. package/dist/knowledge/skills/config-saas/SKILL.md +19 -2
  208. package/dist/knowledge/skills/config-saas/references/compliance-declarations.md +111 -0
  209. package/dist/knowledge/skills/config-saas/references/framework-provider-capabilities-api.md +30 -9
  210. package/dist/knowledge/skills/config-saas/references/framework-wildo-saas-config-api.md +1 -0
  211. package/dist/knowledge/skills/flows-actors-a2a-exposure/SKILL.md +2 -1
  212. package/dist/knowledge/skills/flows-actors-a2a-exposure/references/framework-flows-actors-a2a-contract.md +4 -3
  213. package/dist/knowledge/skills/market-companion-prompt-enrichment/SKILL.md +20 -0
  214. package/dist/knowledge/skills/market-companion-prompt-enrichment/references/framework-companion-behavior-api.md +20 -0
  215. package/dist/knowledge/skills/module-companion-exports/SKILL.md +1 -0
  216. package/dist/knowledge/skills/module-companion-exports/references/companion-exports-by-package.md +20 -0
  217. package/dist/knowledge/skills/resource-add-field/SKILL.md +3 -3
  218. package/dist/knowledge/skills/resource-add-field/references/framework-field-cross-layer-api.md +104 -0
  219. package/dist/knowledge/skills/resource-config-wiring/SKILL.md +13 -0
  220. package/dist/knowledge/skills/resource-config-wiring/references/framework-saas-models-resource-config-api.md +71 -4
  221. package/dist/knowledge/skills/resource-custom-view/references/custom-view-contracts.md +89 -0
  222. package/dist/knowledge/skills/resource-mcp-tool-exposure/SKILL.md +22 -1
  223. package/dist/knowledge/skills/resource-mcp-tool-exposure/references/framework-file-upload-grant-contract.md +192 -0
  224. package/dist/knowledge/skills/resource-rag-source-fields/references/framework-embeddings-capability-api.md +28 -8
  225. package/dist/knowledge/skills/resource-schema-authoring/references/framework-shared-structural-params-api.md +15 -0
  226. package/dist/knowledge/skills/resource-ui-behavior/references/framework-display-edit-modes-api.md +6 -0
  227. package/dist/knowledge/skills/resource-ui-behavior/references/framework-frontend-resource-ui-contracts-api.md +89 -0
  228. package/dist/knowledge/skills/resource-ui-behavior/references/framework-per-primitive-ui-api.md +43 -0
  229. package/dist/knowledge/skills/resource-ui-behavior/references/framework-primitive-ui-api.md +3 -0
  230. package/dist/knowledge/skills/settings-placement-authoring/SKILL.md +1 -1
  231. package/dist/knowledge/skills/spec-companion-exports/SKILL.md +1 -0
  232. package/dist/knowledge/skills/spec-companion-exports/references/framework-companion-exports-contract-api.md +20 -0
  233. package/dist/knowledge/skills/spec-resource-update/references/framework-field-spec-params-api.md +31 -5
  234. package/dist/knowledge/skills/spec-resource-update/references/framework-spec-resource-contracts-api.md +22 -0
  235. package/dist/knowledge/skills/views-composite-authoring/references/framework-composite-view-contracts-api.md +45 -0
  236. package/dist/knowledge/topic-index.json +504 -156
  237. package/dist/tsconfig.build.tsbuildinfo +1 -1
  238. package/dist/tsconfig.tsbuildinfo +1 -1
  239. package/package.json +4 -4
  240. package/dist/esm/.builder.pid +0 -9
@@ -5,10 +5,6 @@
5
5
  "intent": "Map accepted market benefits and requirements to coherent product capabilities, atomically refining the market benefit-to-feature edges and producing ref-less feature specification drafts. FIT/Kano remains a pluggable fit signal, never an implicit build-order ranking.",
6
6
  "functionalTopics": [],
7
7
  "preconditions": [
8
- {
9
- "kind": "phase_is",
10
- "phase": "top_down"
11
- },
12
8
  {
13
9
  "kind": "artifact_valid",
14
10
  "selector": {
@@ -53,7 +49,7 @@
53
49
  ],
54
50
  "stepOutputs": [],
55
51
  "method": {
56
- "guidance": "# Capability Map — Benefit → Feature Pivot Method (v1 scaffold)\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\n> **This is a v1 scaffold methodology.** It is a working first cut meant to be\n> iterated. The mapping order, the draft-authoring posture, and the\n> prioritization rubric below are deliberately explicit so they can be tuned\n> against real runs — treat them as a starting rubric, not a frozen contract.\n> The *analytical depth* of the capability work (quantified FIT / Kano scoring\n> precision, a real prioritization model) is intentionally shallow here and is\n> deepened in a later phase; do not perfect it in this playbook.\n\n## What this playbook does\n\nYou are the **capability architect**. This playbook is the **pivot**: it turns\nthe *value proposition* (what the product promises the market) into *product\ncapability* (the features that actually deliver those promises). Value-proposition\nsharpening already produced a **MarketSnapshot** whose benefits carry weighted\nrelieves/creates/advances edges and per-ICP Kano categories. Your one job is to\nanswer, for every benefit: **which feature delivers this, and does that feature\nexist yet?** — and then record the answer in two places:\n\n1. **The benefit → feature edge** — on the SAME MarketSnapshot, wire every\n benefit's `deliveredByFeatureRefs[]` to the feature(s) that deliver it. This\n edge is the authoritative capability-mapping link (`FeatureBenefitConfig.\n deliveredByFeatureRefs`, required and non-empty): a benefit that is not\n deliverable by any feature is not a real capability. (`market-add-feature-benefit`)\n2. **The spec-first feature drafts** — for every feature the map introduces that\n has **no code registry entry yet**, author a `FeatureSpecificationDraft`\n (purpose, businessRole, lifecycleRole, useWhen/avoidWhen, availabilityRole —\n all in prose). These are **spec-first**: you author them BEFORE the runtime\n `FeatureDefinition` exists; the factory injects the `ref` later from the\n runtime identifier, so a draft is authored ref-less (`Omit<…, 'ref'>`). The\n cross-registry validators are deliberately **fail-soft while the feature\n registry is empty** — so authoring the spec before the code does NOT\n crash-loop the app. (`spec-feature-update`)\n\nThen you **prioritize** the resulting feature set with a FIT-scoring + Kano\nstep — kept pluggable and versioned (see \"The scoring seam\" below).\n\nThis is a **focused pivot pass**, distinct from value-proposition sharpening\n(which weighted the benefits) and from scope/roadmap (which slots the features\ninto releases). Where value-proposition made the benefits sharp, you make each\nbenefit *deliverable* and give every new capability its first spec.\n\n## Read state first — the two families you read, the two you write\n\nThis playbook is **idempotent** and a *refinement*: a MarketSnapshot must\nalready exist (the `artifact_exists` precondition enforces it). Before mapping\nanything:\n\n1. Read the current journey state and scope through the `journey-status` skill\n (it owns the read; do not re-derive it here).\n2. Read the existing **MarketSnapshot** (the benefits and their weighting),\n the **requirements** (`requirements` family — the functional/non-functional\n requirements the features must satisfy), and the **VisionSnapshot**\n (`vision-brief` — the differentiation anchor). You map capability against the\n real market intent, the real requirements, and the real differentiation — not\n from scratch.\n\n// TODO CLI COMMAND: wildo context journey-status (read current journey scope + artifacts)\n// TODO CLI COMMAND: wildo context market-snapshot (read the benefits to map + any existing feature edges)\n\nYou **read** `market-snapshot` + `requirements` + `vision-brief`; you **write**\nthe refined `market-snapshot` (edge wired) and the `feature-drafts` family (the\nnew drafts).\n\n## The mapping loop (benefit by benefit)\n\nFor each benefit in the snapshot:\n\n1. **Identify the delivering feature(s).** Ask what capability the product must\n have for this benefit's claim to be true. Prefer *one clear feature per\n benefit*; a benefit may legitimately need more than one, and one feature may\n deliver several benefits.\n2. **Reuse before you create.** If a delivering feature already appears on\n another benefit's `deliveredByFeatureRefs`, or already has a draft from an\n earlier run, **reuse that same feature ref** — never mint a second ref for the\n same capability. Reusing refs is what keeps the map coherent and lets the\n downstream scope/roadmap playbook slot each feature exactly once.\n3. **Wire the edge.** Add the feature ref(s) to the benefit's\n `deliveredByFeatureRefs[]`. Every benefit must end with a non-empty edge —\n the gate fails a benefit with an empty `deliveredByFeatureRefs` as\n `EMPTY_BENEFIT_DELIVERED_BY` (ERROR).\n4. **Draft the new feature (spec-first).** If the feature is new (no code\n registry entry, no prior draft), author its `FeatureSpecificationDraft` into\n the `feature-drafts` family. A draft is the **prose subset** of a feature\n spec: a business-language `purpose`, its `businessRole` / optional\n `lifecycleRole`, `useWhen` / `avoidWhen`, optional `businessConstraints`, and\n the `availabilityRole` (how the feature gates / packages). **Author ONLY these\n prose fields.** Do NOT author a `ref` — the factory injects it later from the\n runtime feature identifier, which is why a draft is authored ref-less. Do NOT\n wire `codeHandling` (it links a spec back to a runtime enum member +\n collection entry that does not exist yet at this phase) — the code-handling\n provenance is added when the feature is actually built, not now.\n `spec-feature-update` is the field-shape authority for a feature spec; here\n you use its prose surface only. Keep it a *capability contract*, not an\n implementation. (`spec-feature-update`)\n5. **Trace to requirements + vision.** A feature only earns its place if it\n delivers a benefit that traces to the vision's differentiation AND satisfies\n real requirements. When a benefit's delivering feature has no requirement\n behind it, that is a signal to either add the requirement upstream or drop the\n claim — not to invent a feature the product does not need.\n\n## The scoring seam — FIT + Kano, kept PLUGGABLE and VERSIONED\n\nAssess the mapped capability set with a **FIT-scoring + Kano** step, and let that\nassessment inform how the capabilities get prioritized.\n\n**FIT is a fit signal, NOT a priority ranking — do not conflate them.**\n`computeFeatureFitScoreForICP` answers one narrow question: *how well does this\nfeature serve this ICP* on a deterministic 0–100 scale (edge `degree` × the ICP's\nown edge weight). It deliberately does NOT answer \"which feature do we build\nfirst\" — that is prioritization, a separate, deferred concern. Combine the FIT\nscore with the per-ICP Kano category (`THRESHOLD` = table-stakes, `PERFORMANCE` =\nmore-is-better, `DELIGHTER` = upside) to read *table-stakes vs. upside per\nsegment* — a fit judgement, not a build-order. Bending the FIT score into a\nbuild-order ranking yields wrong answers (this is the locked FIT-vs-priority\nvocabulary the `market-scoring-interpretation` skill enforces).\n\n**This step is a pluggable, versioned interface — bind to it, never embed it.**\nThe scoring / prioritization methodology is expected to change substantially in a\nlater phase, so this playbook references the scoring *interface* (via the\n`market-scoring-interpretation` skill) and consumes its output; it does **not**\nre-implement the scoring math and does **not** hard-couple to any specific scoring\nfunction (`computeFeatureFitScoreForICP` today, a different scorer tomorrow). Treat\nthe scorer as a swappable black box: feed it the snapshot, read back the per-ICP\nFIT scores + Kano categories, and use them to sanity-check the capability set. If\nyou find yourself hand-writing a scoring formula, tuning weights to hit a target\nresult, or building an actual build-order prioritization model, **stop** — that is\nthe depth phase's job, and hard-coding it here would break the pluggability\ncontract (OQ-6).\n\nAt scaffold depth this is a *fit sanity check on the capability set*, not a\ndefended prioritization. The headline gap it surfaces: a table-stakes capability\n(a `THRESHOLD` benefit for a `CORE`/`EXPANSION` ICP) whose delivering feature has\nno draft.\n\n## Refine, don't re-author\n\n- **Keep what still holds.** Do not rewrite edges or drafts that are already\n correct. Only add/correct where a benefit lacks a delivering feature, a new\n benefit appeared, or a draft is genuinely wrong.\n- **Never orphan a ref.** A benefit points at feature refs; those refs must have\n a draft (for new features) or a real registry entry (once code exists).\n Removing a feature that a benefit still delivers, or a draft a benefit still\n points at, orphans the edge. Feature-ref orphans are only resolution-checked\n once a feature registry is passed to the validator (not at this phase — the\n registry is empty and the check is fail-soft), so honest refinement must not\n create the orphan in the first place.\n- **One capability, one ref.** When two benefits are delivered by the same\n capability, they share the feature ref — do not fork it.\n\n## Quality gate\n\nThe refined MarketSnapshot is checked by the deterministic `market-snapshot-valid`\ngate (`validateMarketSnapshot`) before anything downstream consumes it. The\ncapability-mapping invariants it enforces:\n\n- **`EMPTY_BENEFIT_DELIVERED_BY` (ERROR)** — a benefit's `deliveredByFeatureRefs[]`\n is empty; every benefit must be deliverable. This is the headline check this\n playbook clears.\n- **`ORPHAN_REF` (ERROR)** — a benefit naming a missing pain/gain/job (feature-ref\n orphans are only checked once a feature registry is passed — not at this phase).\n- The value-proposition invariants inherited from the prior pass\n (`MISSING_POSITIONING_FOR_ICP`, `THRESHOLD_BENEFIT_WITHOUT_JOB`,\n `MULTIPLE_THRESHOLDS_PER_ICP_JOB`) still apply — do not regress them.\n\nRead `market-snapshot-validation` for the full issue catalogue.\n\nThe `feature-drafts` family has **no snapshot-level deterministic gate at this\nphase** — the only feature-spec validator is per-item and needs a ref-bearing\nconfig, which a spec-first draft deliberately omits. Author each draft to the\n`spec-feature-update` skill's contract (which carries the per-draft validity\ncheck); the collection-level gate is a filed depth-phase item (see below).\n\n## Scaffold-depth boundary (deferred to a later depth phase)\n\nKeep this playbook at scaffold depth. Explicitly **out of scope here**:\n\n- **A real prioritization model.** The FIT/Kano step here is a *fit* sanity\n check, not a defended, weighted, capacity-fitted *prioritization* (RICE/WSJF\n and the like are later-phase — and FIT is not priority, see the scoring seam).\n The scoring seam stays pluggable — do NOT build or tune a scoring or\n build-order model in this playbook.\n- **Deep feature-spec drafts.** A draft here is a first-cut capability contract\n (purpose / roles / use-when). Rich operation inventories, interaction\n semantics, and UX are the bottom-up build phase's job, not the capability map.\n- **A snapshot-level `feature-drafts` validator.** No deterministic validator\n exists yet for a *collection* of spec-first drafts (the per-item\n `validateFeatureSpecification` needs a ref, which drafts omit). Authoring the\n collection-level gate — and deciding whether draft prioritization output is\n itself a gated artifact — is depth-phase work.\n- **Requirement pain/gain traceability.** A requirement today cross-refs ICPs and\n jobs but NOT market pains/gains, so the \"this requirement delivers\n `gain-X`\" trace that would let capability mapping run benefit → requirement →\n feature *deterministically* is lossy (expressible only in prose). Whether the\n requirements family should gain a pain/gain edge is a filed depth-phase\n question — do NOT reshape the requirements contract here.\n\nIf you find yourself perfecting any of the above, stop and leave the slice at\nscaffold depth — depth is a dedicated later pass done once, holistically.\n\n## What you emit\n\nTwo artifacts for this journey:\n\n1. The SAME **MarketSnapshot** at `specifications/src/market/index.ts`,\n with every benefit's `deliveredByFeatureRefs` edge wired to its delivering\n feature(s), passing the `market-snapshot-valid` gate.\n2. The **feature-drafts** at `specifications/src/feature-drafts/index.ts` —\n one spec-first `FeatureSpecificationDraft` per new delivering feature.\n\nThe creator reviews the result (approval posture `approve_result`) before it is\naccepted as the journey's capability map.\n\n## References\n\n- `.claude/skills/journey-status/SKILL.md` — read the current journey state and\n scope, and confirm a `market-snapshot` already exists to map from.\n- `.claude/skills/market-add-feature-benefit/SKILL.md` — author/adjust the benefit\n claims and wire their `deliveredByFeatureRefs` edges.\n- `.claude/skills/spec-feature-update/SKILL.md` — author the spec-first\n `FeatureSpecificationDraft`(s) for the new delivering features.\n- `.claude/skills/market-scoring-interpretation/SKILL.md` — the FIT/Kano scoring\n interface: interpret the deterministic scorer's ranking to sanity-check the\n capability set (pluggable seam — consume it, do not re-implement it).\n- `.claude/skills/market-snapshot-validation/SKILL.md` — the full validation issue\n catalogue the quality gate enforces.\n",
52
+ "guidance": "# Capability Map — Benefit → Feature Pivot Method (v1 scaffold)\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\n> **This is a v1 scaffold methodology.** It is a working first cut meant to be\n> iterated. The mapping order, the draft-authoring posture, and the\n> prioritization rubric below are deliberately explicit so they can be tuned\n> against real runs — treat them as a starting rubric, not a frozen contract.\n> The *analytical depth* of the capability work (quantified FIT / Kano scoring\n> precision, a real prioritization model) is intentionally shallow here and is\n> deepened in a later phase; do not perfect it in this playbook.\n\n## What this playbook does\n\nYou are the **capability architect**. This playbook is the **pivot**: it turns\nthe *value proposition* (what the product promises the market) into *product\ncapability* (the features that actually deliver those promises). Value-proposition\nsharpening already produced a **MarketSnapshot** whose benefits carry weighted\nrelieves/creates/advances edges and per-ICP Kano categories. Your one job is to\nanswer, for every benefit: **which feature delivers this, and does that feature\nexist yet?** — and then record the answer in two places:\n\n1. **The benefit → feature edge** — on the SAME MarketSnapshot, wire every\n benefit's `deliveredByFeatureRefs[]` to the feature(s) that deliver it. This\n edge is the authoritative capability-mapping link (`FeatureBenefitConfig.\n deliveredByFeatureRefs`, required and non-empty): a benefit that is not\n deliverable by any feature is not a real capability. (`market-add-feature-benefit`)\n2. **The spec-first feature drafts** — for every feature the map introduces that\n has **no code registry entry yet**, author a `FeatureSpecificationDraft`\n (purpose, businessRole, lifecycleRole, useWhen/avoidWhen, availabilityRole —\n all in prose). These are **spec-first**: you author them BEFORE the runtime\n `FeatureDefinition` exists; the factory injects the `ref` later from the\n runtime identifier, so a draft is authored ref-less (`Omit<…, 'ref'>`). The\n cross-registry validators are deliberately **fail-soft while the feature\n registry is empty** — so authoring the spec before the code does NOT\n crash-loop the app. (`spec-feature-update`)\n\nThen you **prioritize** the resulting feature set with a FIT-scoring + Kano\nstep — kept pluggable and versioned (see \"The scoring seam\" below).\n\nThis is a **focused pivot pass**, distinct from value-proposition sharpening\n(which weighted the benefits) and from scope/roadmap (which slots the features\ninto releases). Where value-proposition made the benefits sharp, you make each\nbenefit *deliverable* and give every new capability its first spec.\n\n## Read state first — the two families you read, the two you write\n\nThis playbook is **idempotent** and a *refinement*: a MarketSnapshot must\nalready exist (the `artifact_exists` precondition enforces it). Before mapping\nanything:\n\n1. Read the current journey state and scope through the `journey-status` skill\n (it owns the read; do not re-derive it here).\n2. Read the existing **MarketSnapshot** (the benefits and their weighting),\n the **requirements** (`requirements` family — the functional/non-functional\n requirements the features must satisfy), and the **VisionSnapshot**\n (`vision-brief` — the differentiation anchor). You map capability against the\n real market intent, the real requirements, and the real differentiation — not\n from scratch.\n\n\nYou **read** `market-snapshot` + `requirements` + `vision-brief`; you **write**\nthe refined `market-snapshot` (edge wired) and the `feature-drafts` family (the\nnew drafts).\n\n## The mapping loop (benefit by benefit)\n\nFor each benefit in the snapshot:\n\n1. **Identify the delivering feature(s).** Ask what capability the product must\n have for this benefit's claim to be true. Prefer *one clear feature per\n benefit*; a benefit may legitimately need more than one, and one feature may\n deliver several benefits.\n2. **Reuse before you create.** If a delivering feature already appears on\n another benefit's `deliveredByFeatureRefs`, or already has a draft from an\n earlier run, **reuse that same feature ref** — never mint a second ref for the\n same capability. Reusing refs is what keeps the map coherent and lets the\n downstream scope/roadmap playbook slot each feature exactly once.\n3. **Wire the edge.** Add the feature ref(s) to the benefit's\n `deliveredByFeatureRefs[]`. Every benefit must end with a non-empty edge —\n the gate fails a benefit with an empty `deliveredByFeatureRefs` as\n `EMPTY_BENEFIT_DELIVERED_BY` (ERROR).\n4. **Draft the new feature (spec-first).** If the feature is new (no code\n registry entry, no prior draft), author its `FeatureSpecificationDraft` into\n the `feature-drafts` family. A draft is the **prose subset** of a feature\n spec: a business-language `purpose`, its `businessRole` / optional\n `lifecycleRole`, `useWhen` / `avoidWhen`, optional `businessConstraints`, and\n the `availabilityRole` (how the feature gates / packages). **Author ONLY these\n prose fields.** Do NOT author a `ref` — the factory injects it later from the\n runtime feature identifier, which is why a draft is authored ref-less. Do NOT\n wire `codeHandling` (it links a spec back to a runtime enum member +\n collection entry that does not exist yet at this phase) — the code-handling\n provenance is added when the feature is actually built, not now.\n `spec-feature-update` is the field-shape authority for a feature spec; here\n you use its prose surface only. Keep it a *capability contract*, not an\n implementation. (`spec-feature-update`)\n5. **Trace to requirements + vision.** A feature only earns its place if it\n delivers a benefit that traces to the vision's differentiation AND satisfies\n real requirements. When a benefit's delivering feature has no requirement\n behind it, that is a signal to either add the requirement upstream or drop the\n claim — not to invent a feature the product does not need.\n\n## The scoring seam — FIT + Kano, kept PLUGGABLE and VERSIONED\n\nAssess the mapped capability set with a **FIT-scoring + Kano** step, and let that\nassessment inform how the capabilities get prioritized.\n\n**FIT is a fit signal, NOT a priority ranking — do not conflate them.**\n`computeFeatureFitScoreForICP` answers one narrow question: *how well does this\nfeature serve this ICP* on a deterministic 0–100 scale (edge `degree` × the ICP's\nown edge weight). It deliberately does NOT answer \"which feature do we build\nfirst\" — that is prioritization, a separate, deferred concern. Combine the FIT\nscore with the per-ICP Kano category (`THRESHOLD` = table-stakes, `PERFORMANCE` =\nmore-is-better, `DELIGHTER` = upside) to read *table-stakes vs. upside per\nsegment* — a fit judgement, not a build-order. Bending the FIT score into a\nbuild-order ranking yields wrong answers (this is the locked FIT-vs-priority\nvocabulary the `market-scoring-interpretation` skill enforces).\n\n**This step is a pluggable, versioned interface — bind to it, never embed it.**\nThe scoring / prioritization methodology is expected to change substantially in a\nlater phase, so this playbook references the scoring *interface* (via the\n`market-scoring-interpretation` skill) and consumes its output; it does **not**\nre-implement the scoring math and does **not** hard-couple to any specific scoring\nfunction (`computeFeatureFitScoreForICP` today, a different scorer tomorrow). Treat\nthe scorer as a swappable black box: feed it the snapshot, read back the per-ICP\nFIT scores + Kano categories, and use them to sanity-check the capability set. If\nyou find yourself hand-writing a scoring formula, tuning weights to hit a target\nresult, or building an actual build-order prioritization model, **stop** — that is\nthe depth phase's job, and hard-coding it here would break the pluggability\ncontract (OQ-6).\n\nAt scaffold depth this is a *fit sanity check on the capability set*, not a\ndefended prioritization. The headline gap it surfaces: a table-stakes capability\n(a `THRESHOLD` benefit for a `CORE`/`EXPANSION` ICP) whose delivering feature has\nno draft.\n\n## Refine, don't re-author\n\n- **Keep what still holds.** Do not rewrite edges or drafts that are already\n correct. Only add/correct where a benefit lacks a delivering feature, a new\n benefit appeared, or a draft is genuinely wrong.\n- **Never orphan a ref.** A benefit points at feature refs; those refs must have\n a draft (for new features) or a real registry entry (once code exists).\n Removing a feature that a benefit still delivers, or a draft a benefit still\n points at, orphans the edge. Feature-ref orphans are only resolution-checked\n once a feature registry is passed to the validator (not at this phase — the\n registry is empty and the check is fail-soft), so honest refinement must not\n create the orphan in the first place.\n- **One capability, one ref.** When two benefits are delivered by the same\n capability, they share the feature ref — do not fork it.\n\n## Quality gate\n\nThe refined MarketSnapshot is checked by the deterministic `market-snapshot-valid`\ngate (`validateMarketSnapshot`) before anything downstream consumes it. The\ncapability-mapping invariants it enforces:\n\n- **`EMPTY_BENEFIT_DELIVERED_BY` (ERROR)** — a benefit's `deliveredByFeatureRefs[]`\n is empty; every benefit must be deliverable. This is the headline check this\n playbook clears.\n- **`ORPHAN_REF` (ERROR)** — a benefit naming a missing pain/gain/job (feature-ref\n orphans are only checked once a feature registry is passed — not at this phase).\n- The value-proposition invariants inherited from the prior pass\n (`MISSING_POSITIONING_FOR_ICP`, `THRESHOLD_BENEFIT_WITHOUT_JOB`,\n `MULTIPLE_THRESHOLDS_PER_ICP_JOB`) still apply — do not regress them.\n\nRead `market-snapshot-validation` for the full issue catalogue.\n\nThe `feature-drafts` family has **no snapshot-level deterministic gate at this\nphase** — the only feature-spec validator is per-item and needs a ref-bearing\nconfig, which a spec-first draft deliberately omits. Author each draft to the\n`spec-feature-update` skill's contract (which carries the per-draft validity\ncheck); the collection-level gate is a filed depth-phase item (see below).\n\n## Scaffold-depth boundary (deferred to a later depth phase)\n\nKeep this playbook at scaffold depth. Explicitly **out of scope here**:\n\n- **A real prioritization model.** The FIT/Kano step here is a *fit* sanity\n check, not a defended, weighted, capacity-fitted *prioritization* (RICE/WSJF\n and the like are later-phase — and FIT is not priority, see the scoring seam).\n The scoring seam stays pluggable — do NOT build or tune a scoring or\n build-order model in this playbook.\n- **Deep feature-spec drafts.** A draft here is a first-cut capability contract\n (purpose / roles / use-when). Rich operation inventories, interaction\n semantics, and UX are the bottom-up build phase's job, not the capability map.\n- **A snapshot-level `feature-drafts` validator.** No deterministic validator\n exists yet for a *collection* of spec-first drafts (the per-item\n `validateFeatureSpecification` needs a ref, which drafts omit). Authoring the\n collection-level gate — and deciding whether draft prioritization output is\n itself a gated artifact — is depth-phase work.\n- **Requirement pain/gain traceability.** A requirement today cross-refs ICPs and\n jobs but NOT market pains/gains, so the \"this requirement delivers\n `gain-X`\" trace that would let capability mapping run benefit → requirement →\n feature *deterministically* is lossy (expressible only in prose). Whether the\n requirements family should gain a pain/gain edge is a filed depth-phase\n question — do NOT reshape the requirements contract here.\n\nIf you find yourself perfecting any of the above, stop and leave the slice at\nscaffold depth — depth is a dedicated later pass done once, holistically.\n\n## What you emit\n\nTwo artifacts for this journey:\n\n1. The SAME **MarketSnapshot** at `specifications/src/market/index.ts`,\n with every benefit's `deliveredByFeatureRefs` edge wired to its delivering\n feature(s), passing the `market-snapshot-valid` gate.\n2. The **feature-drafts** at `specifications/src/feature-drafts/index.ts` —\n one spec-first `FeatureSpecificationDraft` per new delivering feature.\n\nThe creator reviews the result (approval posture `approve_result`) before it is\naccepted as the journey's capability map.\n\n## References\n\n- `.claude/skills/journey-status/SKILL.md` — read the current journey state and\n scope, and confirm a `market-snapshot` already exists to map from.\n- `.claude/skills/market-add-feature-benefit/SKILL.md` — author/adjust the benefit\n claims and wire their `deliveredByFeatureRefs` edges.\n- `.claude/skills/spec-feature-update/SKILL.md` — author the spec-first\n `FeatureSpecificationDraft`(s) for the new delivering features.\n- `.claude/skills/market-scoring-interpretation/SKILL.md` — the FIT/Kano scoring\n interface: interpret the deterministic scorer's ranking to sanity-check the\n capability set (pluggable seam — consume it, do not re-implement it).\n- `.claude/skills/market-snapshot-validation/SKILL.md` — the full validation issue\n catalogue the quality gate enforces.\n",
57
53
  "skillRefs": [
58
54
  "journey-status",
59
55
  "market-add-feature-benefit",
@@ -62,7 +58,9 @@
62
58
  "spec-feature-update"
63
59
  ],
64
60
  "contextSources": [],
65
- "suspendsForClarification": false
61
+ "suspendsForClarification": false,
62
+ "briefAdequacyGate": false,
63
+ "briefAdequacyExcludedSources": []
66
64
  },
67
65
  "executor": "companion_agent",
68
66
  "approval": "approve_result",
@@ -0,0 +1,41 @@
1
+ # Compliance Analysis — the evidence-grounded posture composite
2
+
3
+ ### Target Application Framing
4
+
5
+ This knowledge is for configuring behavior in the target application.
6
+ Wildo is the framework surface being used, not the product being built.
7
+
8
+ Read and apply these patterns from the application-developer point of view:
9
+
10
+ - how the application should configure the relevant app-level file
11
+ - how the application should use framework-provided factories, enums, and helpers
12
+ - how the application should avoid mixing frontend, backend, and infrastructure concerns
13
+
14
+
15
+ You are the **conductor's scheduler**, not an author. This composite exists so the
16
+ application's compliance posture rests on regime texts and regulator pages someone
17
+ actually read — not on what a model remembers about the law, which is confident,
18
+ fluent, and stale in exactly the cases that carry liability.
19
+
20
+ ## The shape
21
+
22
+ Three children, self-ordered by their own preconditions:
23
+
24
+ 1. **compliance-research** — a read-only web lane gathering regime evidence for the
25
+ jurisdictions, data classes and sector the vision (and the creator's answers)
26
+ put in scope. Returns a condensed, source-attributed brief.
27
+ 2. **compliance-evidence-adequacy** — judges whether the evidence is ENOUGH to
28
+ state a posture from, and when it is not, names precisely what is missing so the
29
+ next research round is aimed rather than repeated.
30
+ 3. **compliance-posture** — the artifact-producing child: records each applicable
31
+ regime as a `compliance`-kind constraint on the vision, deriving from the
32
+ creator's elicitation answers AND the gathered evidence, only once the adequacy
33
+ gate has returned ADEQUATE.
34
+
35
+ ## What a round's research objective should name
36
+
37
+ Compose each research objective for THIS round: on the first pass, the candidate
38
+ regimes the vision's jurisdictions/data/sector suggest (verify applicability
39
+ triggers against authoritative sources — regulator pages, official texts, not
40
+ blogs); on later passes, exactly the gaps the adequacy verdict named. Never re-ask
41
+ what a prior round established — its evidence is in the step results.
@@ -0,0 +1,100 @@
1
+ {
2
+ "ref": "top_down.compliance-analysis",
3
+ "version": "0.1.3",
4
+ "phase": "top_down",
5
+ "intent": "Establish the compliance posture by gathering regime EVIDENCE from authoritative sources, judging whether it is enough, and recording the applicable regimes as vision constraints only once it is. An umbrella: it authors nothing itself — its deliverable is what its children land, and the order between them is decided by their own preconditions rather than declared here.",
6
+ "functionalTopics": [],
7
+ "preconditions": [
8
+ {
9
+ "kind": "artifact_valid",
10
+ "selector": {
11
+ "family": "vision-brief"
12
+ }
13
+ }
14
+ ],
15
+ "inputs": [
16
+ {
17
+ "family": "vision-brief"
18
+ }
19
+ ],
20
+ "outputs": [],
21
+ "stepOutputs": [],
22
+ "method": {
23
+ "guidance": "# Compliance Analysis — the evidence-grounded posture composite\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\nYou are the **conductor's scheduler**, not an author. This composite exists so the\napplication's compliance posture rests on regime texts and regulator pages someone\nactually read — not on what a model remembers about the law, which is confident,\nfluent, and stale in exactly the cases that carry liability.\n\n## The shape\n\nThree children, self-ordered by their own preconditions:\n\n1. **compliance-research** — a read-only web lane gathering regime evidence for the\n jurisdictions, data classes and sector the vision (and the creator's answers)\n put in scope. Returns a condensed, source-attributed brief.\n2. **compliance-evidence-adequacy** — judges whether the evidence is ENOUGH to\n state a posture from, and when it is not, names precisely what is missing so the\n next research round is aimed rather than repeated.\n3. **compliance-posture** — the artifact-producing child: records each applicable\n regime as a `compliance`-kind constraint on the vision, deriving from the\n creator's elicitation answers AND the gathered evidence, only once the adequacy\n gate has returned ADEQUATE.\n\n## What a round's research objective should name\n\nCompose each research objective for THIS round: on the first pass, the candidate\nregimes the vision's jurisdictions/data/sector suggest (verify applicability\ntriggers against authoritative sources — regulator pages, official texts, not\nblogs); on later passes, exactly the gaps the adequacy verdict named. Never re-ask\nwhat a prior round established — its evidence is in the step results.\n",
24
+ "skillRefs": [
25
+ "journey-status"
26
+ ],
27
+ "elicitation": {
28
+ "questions": [
29
+ {
30
+ "ref": "handles-regulated-data",
31
+ "question": "Does the product store, process, or transmit personal data or otherwise regulated data (health, financial, biometric, children's, government) — either from end users or on behalf of customers?",
32
+ "kind": "confirm"
33
+ },
34
+ {
35
+ "ref": "data-classes",
36
+ "question": "Which classes of sensitive data does the product touch? List them (e.g. names/emails, health records, payment card data, government IDs, precise location, employee data). Answer \"none\" if it handles no personal or sensitive data.",
37
+ "kind": "free_text"
38
+ },
39
+ {
40
+ "ref": "vendor-establishment",
41
+ "question": "Where is the VENDOR established — the legal entity (or intended entity) operating the product, its country/region, and where is the product hosted or planned to be hosted? Territorial-scope tests (GDPR Art. 3, UK GDPR, CCPA \"doing business\") turn on the vendor's establishment and conduct, not only on where users live. Answer \"not yet decided\" for whatever is genuinely open.",
42
+ "kind": "free_text"
43
+ },
44
+ {
45
+ "ref": "jurisdictions",
46
+ "question": "In which jurisdictions do your users live and your data reside or transit (e.g. EU/EEA, UK, US, California, Canada, specific countries)? This is what drives which privacy regimes apply.",
47
+ "kind": "free_text"
48
+ },
49
+ {
50
+ "ref": "sector",
51
+ "question": "Does the product operate in a regulated sector with its own rules (healthcare, finance/banking, insurance, education, government, telecoms)? Name the sector, or answer \"none\".",
52
+ "kind": "free_text"
53
+ },
54
+ {
55
+ "ref": "gdpr-applies",
56
+ "question": "Do you serve EU/EEA (or UK) individuals or process their personal data? (This is the primary trigger for GDPR / UK GDPR.)",
57
+ "kind": "confirm"
58
+ },
59
+ {
60
+ "ref": "hipaa-applies",
61
+ "question": "Do you handle US protected health information as, or on behalf of, a covered entity or business associate? (This is the primary trigger for HIPAA.)",
62
+ "kind": "confirm"
63
+ },
64
+ {
65
+ "ref": "external-assurance-applies",
66
+ "question": "Do enterprise customers (or your own security posture) require an independent attestation or certification covering security / availability / confidentiality of the service? Name the requested target only as an external source requirement.",
67
+ "kind": "confirm"
68
+ },
69
+ {
70
+ "ref": "data-residency",
71
+ "question": "Are there data-residency or sovereignty requirements — must certain data stay within a region or country (e.g. EU-only hosting, in-country storage)? Describe them, or answer \"none\".",
72
+ "kind": "free_text"
73
+ },
74
+ {
75
+ "ref": "additional-regimes",
76
+ "question": "Any other legal regimes, sector frameworks, government programs, or contractual security commitments that apply? List the externally named sources, or answer \"none\".",
77
+ "kind": "free_text"
78
+ }
79
+ ]
80
+ },
81
+ "contextSources": [],
82
+ "choreography": {
83
+ "admits": [
84
+ "top_down.compliance-posture",
85
+ "top_down.compliance-research",
86
+ "top_down.compliance-evidence-adequacy"
87
+ ],
88
+ "maximumIterations": 14,
89
+ "maximumLanesPerIteration": 3,
90
+ "maximumDepth": 1,
91
+ "maximumDurationMs": 4800000
92
+ },
93
+ "suspendsForClarification": false,
94
+ "briefAdequacyGate": false,
95
+ "briefAdequacyExcludedSources": []
96
+ },
97
+ "approval": "approve_result",
98
+ "budget": {},
99
+ "onFailure": "keep_and_flag"
100
+ }
@@ -0,0 +1,117 @@
1
+ # Compliance Conception — Derivation Method (v1)
2
+
3
+ ### Target Application Framing
4
+
5
+ This knowledge is for configuring behavior in the target application.
6
+ Wildo is the framework surface being used, not the product being built.
7
+
8
+ Read and apply these patterns from the application-developer point of view:
9
+
10
+ - how the application should configure the relevant app-level file
11
+ - how the application should use framework-provided factories, enums, and helpers
12
+ - how the application should avoid mixing frontend, backend, and infrastructure concerns
13
+
14
+
15
+ > **This is the first step in the journey that makes a POSITIVE compliance claim.** Everything before
16
+ > it describes the product. This one says what the product commits to, and a governed document will
17
+ > later quote it. Treat every sentence you write as something an auditor may read back to the
18
+ > operator.
19
+
20
+ ## What this playbook does
21
+
22
+ The compliance-posture step decided **which regimes apply**, in prose, as `compliance`-kind
23
+ constraints on the vision. You turn that into the application's **assurance programme**: which Wildo
24
+ control objectives this product binds, which external requirement each one answers, who is
25
+ accountable, and what is explicitly undetermined.
26
+
27
+ You do **not** re-elicit the vision, design the domain, or draft any document. You produce one
28
+ artifact — the `compliance-program` family — and nothing else.
29
+
30
+ ## The one rule that governs everything below
31
+
32
+ **A vision sentence is not a control mapping.** The posture step recorded "must be GDPR-compliant for
33
+ EU customer personal data". That is product intent. It is *not* a decision that this application binds
34
+ `WILDO.PRIVACY.SUBJECT_DATA_EXPORT`, and converting one into the other by reading is exactly what the
35
+ posture step's own method forbids: the transition "must not reinterpret a vision sentence as a control
36
+ mapping or positive compliance claim."
37
+
38
+ So every element of the programme comes from one of exactly three places:
39
+
40
+ | element | comes from |
41
+ |---|---|
42
+ | which objectives exist, what they demand, what proves them | the **engine authority** you were shown — never invented |
43
+ | which sources exist, their edition, authority and rights | the **source registry** — you supply only a slug |
44
+ | does this application meet the objective; who is accountable; when reviewed | the **creator's answers in this run** |
45
+
46
+ If something comes from none of those, it does not go in the programme. Say it is `UNDETERMINED`, or
47
+ state it as a limitation.
48
+
49
+ ## What you will be refused for
50
+
51
+ The runtime normalizes your answer and **rejects** it — spending one of three runs — if you:
52
+
53
+ - bind an objective the authority basis states no expectation for. The basis covers a small set; you
54
+ were shown exactly which. There is no partial credit for a plausible objective.
55
+ - cite a source the registry does not carry. `sourceSlug` is the registry ref minus its `source:`
56
+ prefix, spelled exactly.
57
+ - schedule the next review before the review that scheduled it.
58
+ - bind the same objective twice.
59
+
60
+ These are not style checks. Each one is a claim the framework cannot stand behind, and the rejection
61
+ message names what you got wrong — read it and fix that, rather than restructuring the answer.
62
+
63
+ ## Deciding an obligation
64
+
65
+ For each objective you were shown, ask three questions **in order**, and stop at the first "no".
66
+
67
+ 1. **Does this application actually do what the intent describes?** You have its resource declarations
68
+ — erasure treatment, data-subject kinds, whether subject export is declared. Use them. An objective
69
+ whose intent describes something the declarations do not show is not bound.
70
+ 2. **Which external requirement does it answer, and does that source reach this application?** If the
71
+ product serves no EU data subjects, GDPR does not reach it and no obligation should cite it.
72
+ 3. **Does the creator approve binding it?** Their answer is the coverage decision. `APPROVED` records
73
+ that a human reviewed the claim; it is not yours to assume.
74
+
75
+ An objective that fails (1) or (2) is simply absent from the programme. **Absence is a legitimate,
76
+ readable answer** — a programme binding one objective honestly is worth more than one binding four
77
+ hopefully.
78
+
79
+ ### Applicability: `APPLICABLE` or `UNDETERMINED`, never a guess
80
+
81
+ `UNDETERMINED` with a reason is the right answer whenever the run cannot settle it, and the posture
82
+ step asks for exactly that. It is visible, it is actionable, and a later pass can close it. A confident
83
+ `APPLICABLE` that nobody could justify is invisible and reads as a decision somebody made.
84
+
85
+ `NOT_APPLICABLE` is not offered to you. That branch requires evidence that the obligation does not
86
+ apply, and evidence is not something a derivation can produce.
87
+
88
+ ## Limitations are required, and they are the honest part
89
+
90
+ You must state at least one. The programme you produce binds a handful of objectives out of everything
91
+ a regime demands, and a reader who is not told that will read it as a complete posture. Say plainly
92
+ what it does not cover: which objectives are unbound, that no operating effectiveness is claimed, and
93
+ that the programme is not a conformity assertion for any named regime.
94
+
95
+ This is not a disclaimer bolted on. It is what makes the rest of the document quotable.
96
+
97
+ ## What you never do
98
+
99
+ - **Never author a rights record, an edition, or an authority name.** Those come from the registry
100
+ because they govern what may be reproduced from a source. Inventing one is a licensing claim nobody
101
+ reviewed.
102
+ - **Never invent a review, a reviewer or a date.** A coverage decision is a human-reviewed claim. The
103
+ creator gave you the role and the date; carry them through unchanged. If they did not, stop and say
104
+ so rather than filling the field.
105
+ - **Never state operating effectiveness.** That a control is configured is not that it has worked. The
106
+ programme has no way to say the latter, and a document downstream is refused for claiming it.
107
+ - **Never widen the scope you were given.** The creator named what the programme covers. An
108
+ application, its environments and its services — not the operator's whole organisation.
109
+
110
+ ## Where this leaves the journey
111
+
112
+ The programme you land is the accepted answer for which controls this product commits to. It is what
113
+ an obligation register reads, what a governed document cites when it says the operator has a
114
+ programme, and what a later mapping pass binds to external framework identifiers.
115
+
116
+ It is accepted the way everything is accepted here: a human commits it. Nothing in this run accepts
117
+ anything.
@@ -0,0 +1,86 @@
1
+ {
2
+ "ref": "top_down.compliance-conception",
3
+ "version": "0.1.0",
4
+ "phase": "top_down",
5
+ "intent": "Compliance-conception pass: turn the applicable regimes the posture step recorded as prose constraints into the application's accepted `compliance-program` — the structured, reviewable record of which Wildo control objectives this product binds, which external requirement each answers, who is accountable, and what is explicitly undetermined. It does NOT re-elicit the vision and it does not draft any document. It is the first step in the lane that produces a POSITIVE compliance claim, so every claim it makes is either derived from an engine authority or answered by the creator in this run; nothing is inferred from a vision sentence.",
6
+ "functionalTopics": [],
7
+ "preconditions": [
8
+ {
9
+ "kind": "artifact_exists",
10
+ "selector": {
11
+ "family": "vision-brief"
12
+ }
13
+ }
14
+ ],
15
+ "inputs": [
16
+ {
17
+ "family": "vision-brief"
18
+ }
19
+ ],
20
+ "outputs": [
21
+ {
22
+ "family": "compliance-program",
23
+ "schemaRef": "saas-specifications:AssuranceProgramSpecification",
24
+ "description": "The application's accepted assurance programme: source references and their applicability, one obligation per bound Wildo objective with its coverage decision and implementation decision, responsibility assignments, and the limitations it does not claim beyond. Answered against the STRICT generation contract (`AssuranceProgramGenerationSchema`) and normalized into a v3 `AssuranceProgramSpecification` — the runtime stamps every ref, version and ordering, and refuses an objective the authority basis has no expectation for or a source the registry does not carry."
25
+ }
26
+ ],
27
+ "stepOutputs": [],
28
+ "method": {
29
+ "guidance": "# Compliance Conception — Derivation Method (v1)\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\n> **This is the first step in the journey that makes a POSITIVE compliance claim.** Everything before\n> it describes the product. This one says what the product commits to, and a governed document will\n> later quote it. Treat every sentence you write as something an auditor may read back to the\n> operator.\n\n## What this playbook does\n\nThe compliance-posture step decided **which regimes apply**, in prose, as `compliance`-kind\nconstraints on the vision. You turn that into the application's **assurance programme**: which Wildo\ncontrol objectives this product binds, which external requirement each one answers, who is\naccountable, and what is explicitly undetermined.\n\nYou do **not** re-elicit the vision, design the domain, or draft any document. You produce one\nartifact — the `compliance-program` family — and nothing else.\n\n## The one rule that governs everything below\n\n**A vision sentence is not a control mapping.** The posture step recorded \"must be GDPR-compliant for\nEU customer personal data\". That is product intent. It is *not* a decision that this application binds\n`WILDO.PRIVACY.SUBJECT_DATA_EXPORT`, and converting one into the other by reading is exactly what the\nposture step's own method forbids: the transition \"must not reinterpret a vision sentence as a control\nmapping or positive compliance claim.\"\n\nSo every element of the programme comes from one of exactly three places:\n\n| element | comes from |\n|---|---|\n| which objectives exist, what they demand, what proves them | the **engine authority** you were shown — never invented |\n| which sources exist, their edition, authority and rights | the **source registry** — you supply only a slug |\n| does this application meet the objective; who is accountable; when reviewed | the **creator's answers in this run** |\n\nIf something comes from none of those, it does not go in the programme. Say it is `UNDETERMINED`, or\nstate it as a limitation.\n\n## What you will be refused for\n\nThe runtime normalizes your answer and **rejects** it — spending one of three runs — if you:\n\n- bind an objective the authority basis states no expectation for. The basis covers a small set; you\n were shown exactly which. There is no partial credit for a plausible objective.\n- cite a source the registry does not carry. `sourceSlug` is the registry ref minus its `source:`\n prefix, spelled exactly.\n- schedule the next review before the review that scheduled it.\n- bind the same objective twice.\n\nThese are not style checks. Each one is a claim the framework cannot stand behind, and the rejection\nmessage names what you got wrong — read it and fix that, rather than restructuring the answer.\n\n## Deciding an obligation\n\nFor each objective you were shown, ask three questions **in order**, and stop at the first \"no\".\n\n1. **Does this application actually do what the intent describes?** You have its resource declarations\n — erasure treatment, data-subject kinds, whether subject export is declared. Use them. An objective\n whose intent describes something the declarations do not show is not bound.\n2. **Which external requirement does it answer, and does that source reach this application?** If the\n product serves no EU data subjects, GDPR does not reach it and no obligation should cite it.\n3. **Does the creator approve binding it?** Their answer is the coverage decision. `APPROVED` records\n that a human reviewed the claim; it is not yours to assume.\n\nAn objective that fails (1) or (2) is simply absent from the programme. **Absence is a legitimate,\nreadable answer** — a programme binding one objective honestly is worth more than one binding four\nhopefully.\n\n### Applicability: `APPLICABLE` or `UNDETERMINED`, never a guess\n\n`UNDETERMINED` with a reason is the right answer whenever the run cannot settle it, and the posture\nstep asks for exactly that. It is visible, it is actionable, and a later pass can close it. A confident\n`APPLICABLE` that nobody could justify is invisible and reads as a decision somebody made.\n\n`NOT_APPLICABLE` is not offered to you. That branch requires evidence that the obligation does not\napply, and evidence is not something a derivation can produce.\n\n## Limitations are required, and they are the honest part\n\nYou must state at least one. The programme you produce binds a handful of objectives out of everything\na regime demands, and a reader who is not told that will read it as a complete posture. Say plainly\nwhat it does not cover: which objectives are unbound, that no operating effectiveness is claimed, and\nthat the programme is not a conformity assertion for any named regime.\n\nThis is not a disclaimer bolted on. It is what makes the rest of the document quotable.\n\n## What you never do\n\n- **Never author a rights record, an edition, or an authority name.** Those come from the registry\n because they govern what may be reproduced from a source. Inventing one is a licensing claim nobody\n reviewed.\n- **Never invent a review, a reviewer or a date.** A coverage decision is a human-reviewed claim. The\n creator gave you the role and the date; carry them through unchanged. If they did not, stop and say\n so rather than filling the field.\n- **Never state operating effectiveness.** That a control is configured is not that it has worked. The\n programme has no way to say the latter, and a document downstream is refused for claiming it.\n- **Never widen the scope you were given.** The creator named what the programme covers. An\n application, its environments and its services — not the operator's whole organisation.\n\n## Where this leaves the journey\n\nThe programme you land is the accepted answer for which controls this product commits to. It is what\nan obligation register reads, what a governed document cites when it says the operator has a\nprogramme, and what a later mapping pass binds to external framework identifiers.\n\nIt is accepted the way everything is accepted here: a human commits it. Nothing in this run accepts\nanything.\n",
30
+ "skillRefs": [
31
+ "journey-status"
32
+ ],
33
+ "elicitation": {
34
+ "questions": [
35
+ {
36
+ "ref": "programme-scope",
37
+ "question": "What exactly does this compliance programme cover — which product, environments and services? Name what is INSIDE the boundary, and anything a reader might assume is included that is not.",
38
+ "kind": "free_text"
39
+ },
40
+ {
41
+ "ref": "accountable-role",
42
+ "question": "Which role in this application is accountable for the compliance programme — the one that approves what it claims? Give the application's own role key (e.g. APP_ADMIN_SUPER_ADMIN) and a short name for it.",
43
+ "kind": "free_text"
44
+ },
45
+ {
46
+ "ref": "operating-role",
47
+ "question": "Which role OPERATES the controls day to day and produces the evidence, if different from the accountable role? Answer \"same\" if one role does both.",
48
+ "kind": "free_text"
49
+ },
50
+ {
51
+ "ref": "coverage-review-date",
52
+ "question": "On what date are you making these coverage decisions? Answer as an ISO date (YYYY-MM-DD). This is recorded as when the review happened — it is not generated, because nobody but you can say when you decided.",
53
+ "kind": "free_text"
54
+ },
55
+ {
56
+ "ref": "next-review-date",
57
+ "question": "When is this programme next reviewed? Answer as an ISO date (YYYY-MM-DD), after today's. A review schedule is a commitment, so it is asked rather than assumed.",
58
+ "kind": "free_text"
59
+ },
60
+ {
61
+ "ref": "objective-coverage",
62
+ "question": "For each bindable objective you were shown, does this application actually meet it today — and do you APPROVE binding it? Answer per objective, with the reason. Approving is a review: it says you read what the objective demands and accept that the product does it.",
63
+ "kind": "free_text"
64
+ },
65
+ {
66
+ "ref": "undetermined-and-gaps",
67
+ "question": "What is genuinely undetermined — something you cannot answer today without more work? List them. These become explicit UNDETERMINED applicability or stated limitations rather than silent omissions.",
68
+ "kind": "free_text"
69
+ }
70
+ ]
71
+ },
72
+ "contextSources": [
73
+ "assurance_program_authority",
74
+ "compliance_primary_facts"
75
+ ],
76
+ "suspendsForClarification": false,
77
+ "briefAdequacyGate": false,
78
+ "briefAdequacyExcludedSources": []
79
+ },
80
+ "executor": "companion_agent",
81
+ "approval": "approve_result",
82
+ "budget": {
83
+ "maxRuns": 3
84
+ },
85
+ "onFailure": "keep_and_flag"
86
+ }
@@ -0,0 +1,61 @@
1
+ # Compliance Evidence Adequacy — is this enough to state a posture from?
2
+
3
+ ### Target Application Framing
4
+
5
+ This knowledge is for configuring behavior in the target application.
6
+ Wildo is the framework surface being used, not the product being built.
7
+
8
+ Read and apply these patterns from the application-developer point of view:
9
+
10
+ - how the application should configure the relevant app-level file
11
+ - how the application should use framework-provided factories, enums, and helpers
12
+ - how the application should avoid mixing frontend, backend, and infrastructure concerns
13
+
14
+
15
+ You are the **gate**, not the author. You read what the research rounds gathered
16
+ and answer one question: is this enough to record the product's compliance posture
17
+ — or what, precisely, is still missing?
18
+
19
+ ## What ADEQUATE means here
20
+
21
+ Evidence is adequate when, for the jurisdictions, data classes and sector the
22
+ vision (and the creator's answers) put in scope:
23
+
24
+ 1. **Every plausible candidate regime has a settled applicability answer** —
25
+ applies, does not apply, or genuinely cannot be established — grounded in an
26
+ authoritative source, never in recollection.
27
+ 2. **No scope dimension is unexamined.** A jurisdiction the vision names with no
28
+ regime evidence at all is a gap, whatever was gathered elsewhere.
29
+ 3. **The claims carry sources.** An unsourced applicability claim counts as
30
+ missing, not as weak — the posture that cites it would be recollection wearing
31
+ evidence's clothes.
32
+
33
+ ## A regime whose triggering facts are DECLARED OPEN is settled as CONDITIONAL
34
+
35
+ "Settled" has three answers, and the third is not a failure: **applies**, **does
36
+ not apply**, and **conditional on named open facts**. When the creator's own
37
+ answers declare a triggering fact undecided — a hosting region not chosen, a
38
+ market not yet targeted, a threshold nobody can know before launch — the settled
39
+ answer for every regime that turns on that fact is *conditional on it*, stated
40
+ with the exact facts that would decide it. That answer is ADEQUATE as it stands.
41
+
42
+ Do not send research after statute-level verification of conditional regimes.
43
+ The measured failure this paragraph exists for: a run whose creator had declared
44
+ US targeting undecided spent its final rounds demanding primary-source triggers
45
+ and thresholds for twelve individual US state statutes — evidence that decides
46
+ nothing until the open fact is decided, purchased at the cost of the rounds the
47
+ DECIDED scope needed. Reserve the authoritative-source bar for the regimes the
48
+ declared facts actually reach; for the conditional tier, the deliverable is the
49
+ precise list of deciding facts, and the posture records exactly that.
50
+
51
+ ## What INSUFFICIENT must do
52
+
53
+ Name the gaps so the next round is AIMED: which regime, which trigger question,
54
+ which jurisdiction. "More research needed" is not a gap — it is the shape that
55
+ made the market loop's early rounds spend tokens converging on nothing.
56
+
57
+ ## What you never do
58
+
59
+ You never lower the bar because rounds are running out — the composite's breaker
60
+ owns that trade, not you. And you never fill a gap yourself: a gate that authors
61
+ evidence has measured nothing.
@@ -0,0 +1,41 @@
1
+ {
2
+ "ref": "top_down.compliance-evidence-adequacy",
3
+ "version": "0.1.1",
4
+ "phase": "top_down",
5
+ "intent": "Judge whether the regime evidence gathered so far is ENOUGH to state a compliance posture from, and when it is not, name precisely what is missing so the next research round is aimed rather than repeated. Returns a verdict a sibling's precondition READS; it authors nothing and lands nothing.",
6
+ "functionalTopics": [],
7
+ "preconditions": [
8
+ {
9
+ "kind": "step_available",
10
+ "ref": "compliance-evidence"
11
+ }
12
+ ],
13
+ "inputs": [
14
+ {
15
+ "family": "vision-brief"
16
+ }
17
+ ],
18
+ "outputs": [],
19
+ "stepOutputs": [
20
+ {
21
+ "ref": "compliance-adequacy",
22
+ "schemaRef": "saas-specifications:MetaWorkflow_EvidenceAdequacy",
23
+ "condensation": "A verdict, the gaps that produced it, and a rationale grounded in what was actually gathered.",
24
+ "description": "The adequacy gate the posture step is conditioned on."
25
+ }
26
+ ],
27
+ "method": {
28
+ "guidance": "# Compliance Evidence Adequacy — is this enough to state a posture from?\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\nYou are the **gate**, not the author. You read what the research rounds gathered\nand answer one question: is this enough to record the product's compliance posture\n— or what, precisely, is still missing?\n\n## What ADEQUATE means here\n\nEvidence is adequate when, for the jurisdictions, data classes and sector the\nvision (and the creator's answers) put in scope:\n\n1. **Every plausible candidate regime has a settled applicability answer** —\n applies, does not apply, or genuinely cannot be established — grounded in an\n authoritative source, never in recollection.\n2. **No scope dimension is unexamined.** A jurisdiction the vision names with no\n regime evidence at all is a gap, whatever was gathered elsewhere.\n3. **The claims carry sources.** An unsourced applicability claim counts as\n missing, not as weak — the posture that cites it would be recollection wearing\n evidence's clothes.\n\n## A regime whose triggering facts are DECLARED OPEN is settled as CONDITIONAL\n\n\"Settled\" has three answers, and the third is not a failure: **applies**, **does\nnot apply**, and **conditional on named open facts**. When the creator's own\nanswers declare a triggering fact undecided — a hosting region not chosen, a\nmarket not yet targeted, a threshold nobody can know before launch — the settled\nanswer for every regime that turns on that fact is *conditional on it*, stated\nwith the exact facts that would decide it. That answer is ADEQUATE as it stands.\n\nDo not send research after statute-level verification of conditional regimes.\nThe measured failure this paragraph exists for: a run whose creator had declared\nUS targeting undecided spent its final rounds demanding primary-source triggers\nand thresholds for twelve individual US state statutes — evidence that decides\nnothing until the open fact is decided, purchased at the cost of the rounds the\nDECIDED scope needed. Reserve the authoritative-source bar for the regimes the\ndeclared facts actually reach; for the conditional tier, the deliverable is the\nprecise list of deciding facts, and the posture records exactly that.\n\n## What INSUFFICIENT must do\n\nName the gaps so the next round is AIMED: which regime, which trigger question,\nwhich jurisdiction. \"More research needed\" is not a gap — it is the shape that\nmade the market loop's early rounds spend tokens converging on nothing.\n\n## What you never do\n\nYou never lower the bar because rounds are running out — the composite's breaker\nowns that trade, not you. And you never fill a gap yourself: a gate that authors\nevidence has measured nothing.\n",
29
+ "skillRefs": [
30
+ "journey-status"
31
+ ],
32
+ "contextSources": [],
33
+ "suspendsForClarification": false,
34
+ "briefAdequacyGate": false,
35
+ "briefAdequacyExcludedSources": []
36
+ },
37
+ "executor": "companion_agent",
38
+ "approval": "auto",
39
+ "budget": {},
40
+ "onFailure": "keep_and_flag"
41
+ }
@@ -69,8 +69,9 @@ requirements and explicit gaps.
69
69
  The transition is not an automatic conversion and must not reinterpret a
70
70
  vision sentence as a control mapping or positive compliance claim. Preserve
71
71
  the vision constraint as product intent, record any missing detail as
72
- `UNDETERMINED` or an explicit gap, and accept the structured family through the
73
- normal semantic-delta authority. Runtime organizations, assignees, evidence,
72
+ `UNDETERMINED` or an explicit gap, and land the structured family as files in the
73
+ specifications package. Landing is not accepting: the run leaves working edits,
74
+ and a human commit is the only acceptance there is. Runtime organizations, assignees, evidence,
74
75
  control occurrences and assessments remain outside both artifacts.
75
76
 
76
77
  ## The derivation posture
@@ -167,8 +168,24 @@ Before you start, read the current journey state and scope, and read the
167
168
  existing vision so you refine its compliance constraints rather than writing a
168
169
  fresh, disconnected set.
169
170
 
170
- // TODO CLI COMMAND: wildo context journey-status (read current journey scope + artifacts)
171
- // TODO CLI COMMAND: wildo context vision-brief (read the existing vision + its current constraints)
171
+ (The existing vision and its current constraints are already in your brief as the `vision-brief`
172
+ input section.)
173
+
174
+ ## The evidence, and how to use it
175
+
176
+ Your run carries what sibling steps gathered — source-attributed regime evidence and the adequacy
177
+ verdict that admitted this step. Derive each constraint from the creator's answers AND that
178
+ evidence, never from recollection:
179
+
180
+ - A regime the evidence establishes as APPLICABLE becomes a `compliance` constraint whose statement
181
+ names the regime, the trigger (jurisdiction / data class / sector / commitment), and what it
182
+ governs — in the evidence's terms.
183
+ - A regime the evidence EXCLUDES is not written as a constraint, and is not silently dropped either:
184
+ where the creator's answers suggested it, the statement of a neighbouring constraint may note the
185
+ exclusion so the decision is legible.
186
+ - A trigger the evidence could NOT establish becomes a constraint stating the OPEN QUESTION, never a
187
+ guessed answer — an unestablished regime stated as settled is the defect this composite exists to
188
+ end.
172
189
 
173
190
  ## References
174
191