@wildo-ai/framework-knowledge 1.1.7 → 1.1.9
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.
- package/dist/claude-marketplace/plugins/wildo/.claude-plugin/plugin.json +1 -1
- package/dist/claude-marketplace/plugins/wildo/references/composites-and-the-loop.md +9 -2
- package/dist/claude-marketplace/plugins/wildo/references/creation-state.md +21 -0
- package/dist/claude-marketplace/plugins/wildo/references/derived-artifacts.md +121 -0
- package/dist/claude-marketplace/plugins/wildo/references/runs-judges-and-questions.md +29 -5
- package/dist/claude-marketplace/plugins/wildo/skills/answer/SKILL.md +29 -2
- package/dist/claude-marketplace/plugins/wildo/skills/build/SKILL.md +69 -24
- package/dist/claude-marketplace/plugins/wildo/skills/doctor/SKILL.md +10 -0
- package/dist/claude-marketplace/plugins/wildo/skills/run/SKILL.md +21 -5
- package/dist/claude-marketplace/plugins/wildo/skills/start/SKILL.md +31 -5
- package/dist/claude-marketplace/plugins/wildo/skills/status/SKILL.md +2 -0
- package/dist/claude-marketplace/plugins/wildo/skills/why/SKILL.md +11 -1
- package/dist/esm/framework-knowledge.definitions.d.ts +1 -1
- package/dist/esm/framework-knowledge.definitions.d.ts.map +1 -1
- package/dist/esm/framework-knowledge.definitions.js +11 -1
- package/dist/esm/framework-knowledge.definitions.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts +2 -2
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js +2 -2
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts +11 -11
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.js +29 -22
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts +3 -3
- package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js +59 -10
- package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js +3 -3
- package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js +1 -1
- package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js +1 -1
- package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts +2 -1
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js +5 -5
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts +8 -0
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js +12 -4
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts +25 -27
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js +85 -43
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.d.ts +40 -0
- package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.js +41 -0
- package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.d.ts +199 -0
- package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.js +201 -0
- package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.d.ts +67 -0
- package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.js +76 -0
- package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts +3 -1
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.js +27 -18
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts +11 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js +11 -11
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts +2 -0
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js +3 -1
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts +2 -0
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js +3 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts +5 -2
- package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.definition/playbook.definition.js +16 -4
- package/dist/esm/playbooks/top_down.definition/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts +7 -3
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js +36 -2
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts +7 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js +4 -2
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts +9 -3
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js +3 -3
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts +35 -2
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js +30 -17
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js.map +1 -1
- package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/authority-basis.json +1 -1
- package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/external-framework-mapping.json +1 -1
- package/dist/knowledge/manifest.json +8 -8
- package/dist/knowledge/playbooks/bottom_up.assemble-verify/method.md +22 -7
- package/dist/knowledge/playbooks/bottom_up.assemble-verify/playbook.json +3 -3
- package/dist/knowledge/playbooks/bottom_up.build/method.md +17 -15
- package/dist/knowledge/playbooks/bottom_up.build/playbook.json +4 -3
- package/dist/knowledge/playbooks/bottom_up.build-decompose/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.build-decompose/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.build-decompose/method.md +117 -28
- package/dist/knowledge/playbooks/bottom_up.build-decompose/playbook.json +4 -4
- package/dist/knowledge/playbooks/bottom_up.build-dispatch/method.md +133 -59
- package/dist/knowledge/playbooks/bottom_up.build-dispatch/playbook.json +2 -2
- package/dist/knowledge/playbooks/bottom_up.build-scale/method.md +169 -276
- package/dist/knowledge/playbooks/bottom_up.build-scale/playbook.json +2 -2
- package/dist/knowledge/playbooks/bottom_up.capability-composition/method.md +8 -1
- package/dist/knowledge/playbooks/bottom_up.capability-composition/playbook.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.conception/method.md +3 -2
- package/dist/knowledge/playbooks/bottom_up.conception/playbook.json +2 -2
- package/dist/knowledge/playbooks/bottom_up.domain-plan/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.domain-plan/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.domain-plan/method.md +22 -6
- package/dist/knowledge/playbooks/bottom_up.domain-plan/playbook.json +4 -3
- package/dist/knowledge/playbooks/bottom_up.foundation/playbook.json +13 -5
- package/dist/knowledge/playbooks/refinement.compliance-document-candidate/method.md +5 -2
- package/dist/knowledge/playbooks/refinement.compliance-document-candidate/playbook.json +1 -1
- package/dist/knowledge/playbooks/top_down.brand-identity/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/top_down.brand-identity/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/top_down.brand-identity/method.md +71 -37
- package/dist/knowledge/playbooks/top_down.brand-identity/playbook.json +35 -38
- package/dist/knowledge/playbooks/top_down.brand-name-research/method.md +105 -0
- package/dist/knowledge/playbooks/top_down.brand-name-research/playbook.json +55 -0
- package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-protocol.json +1 -0
- package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-treatment.json +1 -0
- package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/method.md +78 -0
- package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/playbook.json +63 -0
- package/dist/knowledge/playbooks/top_down.brand-naming/method.md +56 -0
- package/dist/knowledge/playbooks/top_down.brand-naming/playbook.json +65 -0
- package/dist/knowledge/playbooks/top_down.business-model/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/top_down.business-model/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/top_down.business-model/method.md +60 -6
- package/dist/knowledge/playbooks/top_down.business-model/playbook.json +15 -10
- package/dist/knowledge/playbooks/top_down.compliance-analysis/playbook.json +30 -10
- package/dist/knowledge/playbooks/top_down.compliance-conception/playbook.json +3 -1
- package/dist/knowledge/playbooks/top_down.compliance-posture/playbook.json +4 -1
- package/dist/knowledge/playbooks/top_down.definition/method.md +8 -3
- package/dist/knowledge/playbooks/top_down.definition/playbook.json +6 -4
- package/dist/knowledge/playbooks/top_down.phase-gate/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/top_down.phase-gate/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/top_down.phase-gate/playbook.json +11 -1
- package/dist/knowledge/playbooks/top_down.risk-register/method.md +21 -0
- package/dist/knowledge/playbooks/top_down.risk-register/playbook.json +8 -2
- package/dist/knowledge/playbooks/top_down.scope-roadmap/playbook.json +4 -2
- package/dist/knowledge/playbooks/top_down.vision-elicitation/method.md +10 -0
- package/dist/knowledge/playbooks/top_down.vision-elicitation/playbook.json +40 -17
- package/dist/knowledge/references/brand.name-choice.config.md +127 -0
- package/dist/knowledge/references/brand.name-screening.config.md +253 -0
- package/dist/knowledge/references/build-plan.task-graph.config.md +64 -11
- package/dist/knowledge/references/business-model.pricing-plan.config.md +16 -0
- package/dist/knowledge/references/business-model.snapshot.config.md +64 -0
- package/dist/knowledge/references/business-model.snapshot.validation.md +68 -4
- package/dist/knowledge/references/capability-composition.config.md +67 -4
- package/dist/knowledge/references/example.data-seeding.minimal.md +29 -1
- package/dist/knowledge/references/market.snapshot.validation.md +1 -1
- package/dist/knowledge/references/saas.data-seeding.bootstrap-wiring.md +7 -1
- package/dist/knowledge/references/saas.data-seeding.definition-input.md +6 -0
- package/dist/knowledge/references/saas.models.queue.scheduled-recovery.md +81 -2
- package/dist/knowledge/references/saas.specifications.companion-exports.contract.md +10 -0
- package/dist/knowledge/references/saas.website.astro.label-loader.md +9 -0
- package/dist/knowledge/references/saas.website.factories.define-section.md +4 -0
- package/dist/knowledge/references/saas.website.page-manifest.schema.md +12 -3
- package/dist/knowledge/references/saas.website.page-sections.component.md +72 -0
- package/dist/knowledge/references/saas.website.sections.definition-schema.md +11 -0
- package/dist/knowledge/registries/assurance-authority-bases.json +1 -1
- package/dist/knowledge/registries/framework-topics.json +38 -1
- package/dist/knowledge/registries/playbooks.json +68 -20
- package/dist/knowledge/registries/source-tags.json +748 -695
- package/dist/knowledge/rules/live-context-door.md +5 -2
- package/dist/knowledge/skills/INDEX.md +2 -1
- package/dist/knowledge/skills/application-database-migrations/SKILL.md +1 -1
- package/dist/knowledge/skills/brand-name-screening/SKILL.md +154 -0
- package/dist/knowledge/skills/brand-name-screening/references/framework-brand-name-screening-api.md +394 -0
- package/dist/knowledge/skills/brand-name-screening/references/screening-procedure.md +65 -0
- package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-privacy-notice.md +5 -2
- package/dist/knowledge/skills/config-saas/SKILL.md +31 -4
- package/dist/knowledge/skills/config-saas/references/compliance-declarations.md +14 -1
- package/dist/knowledge/skills/config-saas/references/framework-background-work-api.md +81 -2
- package/dist/knowledge/skills/email-add-template/SKILL.md +1 -1
- package/dist/knowledge/skills/i18n-rerun-pipeline/SKILL.md +1 -1
- package/dist/knowledge/skills/inbound-channels/SKILL.md +2 -2
- package/dist/knowledge/skills/local-environment-bootstrap/SKILL.md +11 -1
- package/dist/knowledge/skills/local-environment-bootstrap/references/derived-artifact-currency.md +122 -0
- package/dist/knowledge/skills/local-environment-bootstrap/references/framework-upgrade-and-dependency-alignment.md +11 -0
- package/dist/knowledge/skills/local-environment-bootstrap/references/wildo-cli-bootstrap-commands.md +9 -2
- package/dist/knowledge/skills/market-companion-prompt-enrichment/SKILL.md +11 -1
- package/dist/knowledge/skills/market-companion-prompt-enrichment/references/framework-companion-behavior-api.md +11 -1
- package/dist/knowledge/skills/market-message-templates-authoring/references/framework-message-template-api.md +1 -1
- package/dist/knowledge/skills/market-snapshot-validation/SKILL.md +1 -1
- package/dist/knowledge/skills/market-snapshot-validation/references/framework-snapshot-validation-api.md +1 -1
- package/dist/knowledge/skills/module-companion-exports/references/companion-exports-by-package.md +10 -0
- package/dist/knowledge/skills/module-relationships/SKILL.md +6 -4
- package/dist/knowledge/skills/seeding-authoring/SKILL.md +51 -3
- package/dist/knowledge/skills/seeding-authoring/references/framework-data-seeding-api.md +6 -0
- package/dist/knowledge/skills/seeding-operations/references/framework-data-seeding-operations-api.md +7 -1
- package/dist/knowledge/skills/spec-companion-exports/references/framework-companion-exports-contract-api.md +10 -0
- package/dist/knowledge/skills/website-factory-advanced/SKILL.md +4 -0
- package/dist/knowledge/skills/website-page-authoring/SKILL.md +84 -3
- package/dist/knowledge/skills/website-section-contact/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-contact/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-cta/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-cta/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-faq/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-faq/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-feature-benefit-summary/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-feature-benefit-summary/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-feature-detail/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-feature-detail/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-footer-cta/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-footer-cta/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-hero/SKILL.md +27 -9
- package/dist/knowledge/skills/website-section-hero/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-pricing/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-pricing/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-social-proof/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-social-proof/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-seo-aeo-geo/SKILL.md +1 -1
- package/dist/knowledge/skills/website-seo-aeo-geo/references/aeo-api.md +11 -0
- package/dist/knowledge/topic-index.json +169 -43
- package/dist/tsconfig.build.tsbuildinfo +1 -1
- package/dist/tsconfig.tsbuildinfo +1 -1
- package/package.json +4 -4
|
@@ -1,19 +1,30 @@
|
|
|
1
1
|
{
|
|
2
2
|
"ref": "top_down.brand-identity",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.3.0",
|
|
4
4
|
"phase": "top_down",
|
|
5
|
-
"intent": "Brand-identity elicitation: draw the product's VISUAL identity out of the creator — the brand name, the logo creative direction (mark type, motifs, symbolism, imagery don'ts, background), and the visual tone (style keywords, mood, color story) — and capture it as a single validated BrandSnapshot (the `brand-brief` artifact family). The visual counterpart to the vision (intent) and market (verbal voice) briefs: it derives symbolism from the VisionSnapshot's idea/mission and, when a MarketSnapshot exists, translates its verbal `tonesOfVoice` into a visual register. The emitted brand-brief is the INPUT the companion logo step generates the master logo + derived assets from, and via `BrandSnapshot.resolvedAssets` the single source of truth every logo/favicon/brand-image consumer resolves against. Progressive: may persist a partially-directed brand (logoDirection/visualTone optional) and resume. v1 scaffold methodology — iterate the interview.",
|
|
5
|
+
"intent": "Brand-identity elicitation: draw the product's VISUAL identity out of the creator — the brand name (CHOSEN by the creator from the screened candidates `top_down.brand-naming` landed), the logo creative direction (mark type, motifs, symbolism, imagery don'ts, background), and the visual tone (style keywords, mood, color story) — and capture it as a single validated BrandSnapshot (the `brand-brief` artifact family). The visual counterpart to the vision (intent) and market (verbal voice) briefs: it derives symbolism from the VisionSnapshot's idea/mission and, when a MarketSnapshot exists, translates its verbal `tonesOfVoice` into a visual register. The emitted brand-brief is the INPUT the companion logo step generates the master logo + derived assets from, and via `BrandSnapshot.resolvedAssets` the single source of truth every logo/favicon/brand-image consumer resolves against. Progressive: may persist a partially-directed brand (logoDirection/visualTone optional) and resume. v1 scaffold methodology — iterate the interview.",
|
|
6
6
|
"preconditions": [
|
|
7
7
|
{
|
|
8
8
|
"kind": "artifact_exists",
|
|
9
9
|
"selector": {
|
|
10
10
|
"family": "vision-brief"
|
|
11
11
|
}
|
|
12
|
+
},
|
|
13
|
+
{
|
|
14
|
+
"kind": "artifact_valid",
|
|
15
|
+
"selector": {
|
|
16
|
+
"family": "brand-name-screening"
|
|
17
|
+
}
|
|
12
18
|
}
|
|
13
19
|
],
|
|
14
20
|
"inputs": [
|
|
15
21
|
{
|
|
16
|
-
"family": "vision-brief"
|
|
22
|
+
"family": "vision-brief",
|
|
23
|
+
"aspects": [
|
|
24
|
+
"vision.idea",
|
|
25
|
+
"vision.problem",
|
|
26
|
+
"vision.mission"
|
|
27
|
+
]
|
|
17
28
|
},
|
|
18
29
|
{
|
|
19
30
|
"family": "market-snapshot",
|
|
@@ -21,6 +32,9 @@
|
|
|
21
32
|
},
|
|
22
33
|
{
|
|
23
34
|
"family": "brand-brief"
|
|
35
|
+
},
|
|
36
|
+
{
|
|
37
|
+
"family": "brand-name-screening"
|
|
24
38
|
}
|
|
25
39
|
],
|
|
26
40
|
"outputs": [
|
|
@@ -32,7 +46,7 @@
|
|
|
32
46
|
],
|
|
33
47
|
"stepOutputs": [],
|
|
34
48
|
"method": {
|
|
35
|
-
"guidance": "# Brand Identity — Interview 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\n> be iterated. The question set, the interviewing depth, and the \"when is it\n> done enough\" bar below are deliberately explicit so they can be tuned\n> against real elicitation runs — treat them as a starting rubric, not a\n> frozen contract.\n\n## What this playbook does\n\nYou are the **brand-identity interviewer**. Your job is to draw the product's\nVISUAL identity out of the creator and capture it as a single typed\n**`BrandSnapshot`** — the `brand-brief` artifact. This is the visual\ncounterpart to the vision brief (which captured *intent*) and the market brief\n(which captured the *verbal* voice): here you capture what the product should\n**look like** and, specifically, the brief a logo is generated from.\n\nThe brand-brief you emit is not the logo itself — it is the *direction*. The\ncompanion logo step reads it to generate the master logo and every derived\nasset (favicon, apple-touch, maskable, OG, email, monochrome, dark/light), and\nthose become the single source of truth every surface resolves against. So an\nhonest, well-framed brief is the whole task. You do **not** generate pixels,\nset design-system color tokens, or restate the verbal brand voice — each is a\ndistinct concern with its own home.\n\n## Where the brief comes from\n\nYou do not invent a brand from nothing. Ground it in what the journey already\nknows:\n\n- **The vision brief is your source of meaning.** Read the `VisionSnapshot` and\n derive the mark's **symbolism** from the product's idea and mission — the\n mark should evoke what the product is *for*, not a decorative motif you liked.\n- **The market brief sharpens the register, when present.** If a\n `MarketSnapshot` exists, translate its verbal `tonesOfVoice` (the Nielsen\n Norman 4-axis voice) into a **visual** tone: a serious / formal voice reads as\n restrained geometry and a muted palette; a funny / casual voice reads as\n rounder forms and a warmer accent. The market brief is an *input*, not a\n precondition — if there is no market snapshot yet, derive the visual tone from\n the vision alone and note it as provisional.\n\n## The elicitation posture\n\n- **Interview, do not fill a form.** The typed questions on this playbook\n (`method.elicitation`) are your backbone, not your ceiling. Ask them in a\n natural order, reflect each answer back in one line, and let the creator\n correct you before moving on.\n- **Progressive is fine.** A `BrandSnapshot` requires only the **name**; the\n logo direction and visual tone are OPTIONAL and elicited progressively. If the\n creator can only name the brand today, capture it, note what is still open,\n and stop — the snapshot persists as partially-directed and this playbook can\n resume. Never invent a mark direction the creator did not give you.\n- **One product, one brand.** The snapshot is a single aggregate — one name,\n one logo direction, one visual tone. If the creator describes two brands,\n stop and ask which one this journey is for.\n\n## What you elicit — one aggregate\n\n- **Name** (REQUIRED). The anchor lexical identity: the exact, case-sensitive\n `brandName` the logo renders and every surface prints, plus an optional\n `tagline` to lock up with combination marks / OG imagery. Nothing visual\n here — the mark and the palette come next. A brand without a name has nothing\n for a mark to render; do not proceed until you have it.\n- **Logo direction** (optional, WARNed when absent). The creative brief the\n image model turns into the master logo:\n - `markType` — pick the archetype. **Default to `COMBINATION_MARK`** (symbol +\n wordmark) — it is the only archetype that natively yields BOTH a header\n lockup and a square symbol for favicons/app-icons. Reach for `WORDMARK`\n (text-only) only when the brand is genuinely wordmark-only; warn the creator\n that a wordmark cannot produce a clean square app icon.\n - `motifs` — concrete visual elements to include (short noun phrases).\n - `symbolism` — the meaning the mark should evoke, **derived from the vision\n mission/idea**.\n - `avoid` — imagery don'ts (the negative-prompt guardrails that keep output\n usable).\n - `backgroundTreatment` — keep `TRANSPARENT_ISOLATED` (the default and the\n only treatment that rasterizes losslessly into every derived asset). A\n solid field or contextual scene is an explicit opt-in the pipeline must\n compensate for — the validator WARNs on it.\n- **Visual tone** (optional, WARNed when absent). The aesthetic register — the\n VISUAL counterpart to the market voice: 3–7 concrete `styleKeywords`\n (\"geometric\", \"minimal\", \"warm\"), a one-line `mood`, a prose `colorIntent`\n (the color STORY, not hex values), and optional hex `colorSeeds` pinned only\n when the brand has already committed to anchors that must agree with the\n design system.\n- **Audience** (optional). WHO the brand is for: `targetIcpRefs`, the refs of\n the market ICPs its name and tone are chosen to speak to, copied exactly from\n the market's `icps`, plus a one-line `rationale`. Derive it from what the brief\n already says: the ICP whose preferred voice the visual tone translates, the\n segment the mission and tagline address. Never name a segment the market does\n not hold, and never list an anti-target. Downstream agents are given the\n brand's ICPs, and through them their personas and positionings, from this one\n declaration.\n\n## What you emit\n\nA single `BrandSnapshot`:\n\n- `version` — the snapshot format version (leave at its default unless told otherwise).\n- `name` — the required anchor (`brandName`, optional `tagline`).\n- `logoDirection` / `visualTone` / `audience` — the optional singletons, present only if elicited.\n- `resolvedAssets` — **leave empty.** This is the companion logo step's output,\n not something you author. Hand-authoring it fabricates asset references the\n pipeline will overwrite or the validator will flag.\n\nAuthor every entity in English. Follow the `brand-logo-authoring` skill for the\nexact field contracts and the mark-type / background / visual-tone decision\naids — its full text is in your brief, under \"The skills this method tells you\nto FOLLOW\". Read it there; you cannot open files.\n\n## Quality gate\n\nYour emitted snapshot is checked by the deterministic `brand-snapshot-valid`\ngate (`validateBrandSnapshot`) before it commits. A directed-but-ungenerated\nbrand (a `logoDirection` present, `resolvedAssets` still empty) is expected and\nonly WARNs — it is exactly the state you hand off to the companion logo step. A\nmissing logo direction and a missing visual tone are also warnings, reflecting a\nnot-yet-complete brief. Emit a clean brief and let the warnings stand honestly\nwhen the brand genuinely is not fully directed yet, rather than inventing a\nmark to silence them.\n\nAfter landing, the advisory judge reads the brief against two criteria — grounding in\nthe interview and the vision, and the audience-and-assets hand-off — and its verdicts\nreach the creator's review as notes. A verdict never refuses a landing.\n\n## Approval\n\nThe drafted `BrandSnapshot` is presented to the creator for approval before it\nbecomes the committed `brand-brief`. Show the brief back in plain prose — the\nname, the mark direction, the visual tone — and let the creator confirm or\ncorrect it. The brand-brief is what the logo is generated from and what\npropagates everywhere; it is worth one explicit human sign-off before the mark\nis made.\n\n## Runtime context\n\nBefore you start, read the current journey state, the vision brief that grounds\nthe brand's meaning, and any brand brief that already exists so you refine it\nrather than re-eliciting it from scratch.\n\n(The vision and any previously landed brand brief arrive in your brief as the `vision-brief` and\n`brand-brief` input sections.)\n\n## References\n\nThese are skill FOLDERS installed in the application, and this step has no tools,\nso it does not open them. What reaches you is stated per skill below.\n\n- `brand-logo-authoring` — the field contracts for the `BrandSnapshot` (name /\n logoDirection / visualTone), the mark-type selection table, background\n derivation-safety, and deriving the visual tone from the market voice. Its\n FULL TEXT is in your brief; follow it exactly.\n",
|
|
49
|
+
"guidance": "# Brand Identity — 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\n> be iterated. The question set, the interviewing depth, and the \"when is it\n> done enough\" bar below are deliberately explicit so they can be tuned\n> against real elicitation runs — treat them as a starting rubric, not a\n> frozen contract.\n\n## What this playbook does\n\nYou are the **brand-identity author**. Your job is to capture the product's VISUAL\nidentity, from the creator's few decisions plus what the vision and the market already\nsay, as a single typed\n**`BrandSnapshot`** — the `brand-brief` artifact. This is the visual\ncounterpart to the vision brief (which captured *intent*) and the market brief\n(which captured the *verbal* voice): here you capture what the product should\n**look like** and, specifically, the brief a logo is generated from.\n\nThe brand-brief you emit is not the logo itself — it is the *direction*. The\ncompanion logo step reads it to generate the master logo and every derived\nasset (favicon, apple-touch, maskable, OG, email, monochrome, dark/light), and\nthose become the single source of truth every surface resolves against. So an\nhonest, well-framed brief is the whole task. You do **not** generate pixels,\nset design-system color tokens, or restate the verbal brand voice — each is a\ndistinct concern with its own home.\n\n## Where the brief comes from\n\nYou do not invent a brand from nothing. Ground it in what the journey already\nknows:\n\n- **The vision brief is your source of meaning.** Read the `VisionSnapshot` and\n derive the mark's **symbolism** from the product's idea and mission — the\n mark should evoke what the product is *for*, not a decorative motif you liked.\n- **The market brief sharpens the register, when present.** If a\n `MarketSnapshot` exists, translate its verbal `tonesOfVoice` (the Nielsen\n Norman 4-axis voice) into a **visual** tone: a serious / formal voice reads as\n restrained geometry and a muted palette; a funny / casual voice reads as\n rounder forms and a warmer accent. The market brief is an *input*, not a\n precondition — if there is no market snapshot yet, derive the visual tone from\n the vision alone and note it as provisional.\n\n## What the creator decided, and what you derive\n\nThe interview asks only what the creator alone can decide. Everything else you derive,\nand you say where it came from.\n\n| Decided by the creator (interview answer) | Derived by you |\n|---|---|\n| `brand-name`: chosen from the screened names | `symbolism`, from the vision's idea and mission |\n| `brand-tagline`, or \"none\" | `motifs`: concrete elements that carry that symbolism |\n| `logo-mark-type` | `avoid`: the guardrails that keep the mark usable (no gradients, no literal clip-art, no text inside a symbol meant to stand alone) |\n| `logo-background` | `visualTone` (style keywords, mood, colour story), translated from the market's verbal voice |\n| `visual-color-seeds`, or \"none\" | |\n| `visual-direction`, or \"none\" | |\n\n- **`visual-direction` outranks the derivation.** When it is not \"none\", whatever it asks\n the mark to evoke, include or avoid is honoured, and the derived parts are shaped around it.\n- **Derived is not invented.** Every symbol, motif and tone keyword must trace to the\n vision or the market voice. A decorative choice of your own is the one thing to avoid.\n- **Progressive is fine.** A `BrandSnapshot` requires only the **name**. If the vision or\n the market is too thin to derive a direction honestly, leave `logoDirection` or\n `visualTone` out and say what is missing. The snapshot persists partially directed, and\n this playbook can resume.\n- **One product, one brand.** The snapshot is a single aggregate: one name, one logo\n direction, one visual tone.\n\n## What the brief holds — one aggregate\n\n- **Name** (REQUIRED). The anchor lexical identity: the exact, case-sensitive\n `brandName` the logo renders and every surface prints, plus an optional\n `tagline` to lock up with combination marks / OG imagery. Nothing visual\n here — the mark and the palette come next.\n\n **You do not invent the name, and you do not choose it.** `top_down.brand-naming`\n proposed names and ran a minimal trademark screening of each; the creator CHOSE\n one in this playbook's `brand-name` question, from options computed from that\n screening. The `brandName` is exactly the chosen option's name. An option may end\n with a bracketed qualifier — `[screening-incomplete]` or `[keep-despite-conflict]`\n — which records how the creator chose; it is NEVER part of the name, so drop it.\n\n The brand-name screening is in your brief. Never describe the name as\n \"available\", \"registered\", \"protected\" or \"cleared\": a screening is not a legal\n clearance opinion. Where the creator kept a name despite a conflict, or chose one\n whose screening is incomplete, do not hide or soften that anywhere in the brief.\n- **Logo direction** (optional, WARNed when absent). The creative brief the\n image model turns into the master logo:\n - `markType` — the creator's `logo-mark-type` answer. The question suggests\n `COMBINATION_MARK` (symbol + wordmark) because it is the only archetype that\n natively yields BOTH a header lockup and a square symbol for favicons and app\n icons. When the creator chose `WORDMARK` (text only), note in the brief that a\n wordmark cannot produce a clean square app icon.\n - `motifs` — concrete visual elements to include (short noun phrases), DERIVED\n from the symbolism and the creator's `visual-direction`.\n - `symbolism` — the meaning the mark should evoke, **derived from the vision\n mission/idea** (and the creator's `visual-direction`, when they gave one).\n - `avoid` — imagery don'ts (the negative-prompt guardrails that keep output\n usable), DERIVED, plus anything the creator's `visual-direction` rules out.\n - `backgroundTreatment` — the creator's `logo-background` answer.\n `TRANSPARENT_ISOLATED` is the default and the only treatment that rasterizes\n losslessly into every derived asset. A\n solid field or contextual scene is an explicit opt-in the pipeline must\n compensate for — the validator WARNs on it.\n- **Visual tone** (optional, WARNed when absent). The aesthetic register — the\n VISUAL counterpart to the market voice, DERIVED from it (and shaped by the\n creator's `visual-direction`): 3–7 concrete `styleKeywords`\n (\"geometric\", \"minimal\", \"warm\"), a one-line `mood`, a prose `colorIntent`\n (the color STORY, not hex values), and the hex `colorSeeds` the creator gave in\n `visual-color-seeds`, only when they named any.\n- **Audience** (optional). WHO the brand is for: `targetIcpRefs`, the refs of\n the market ICPs its name and tone are chosen to speak to, copied exactly from\n the market's `icps`, plus a one-line `rationale`. Derive it from what the brief\n already says: the ICP whose preferred voice the visual tone translates, the\n segment the mission and tagline address. Never name a segment the market does\n not hold, and never list an anti-target. Downstream agents are given the\n brand's ICPs, and through them their personas and positionings, from this one\n declaration.\n\n## Answers the creator did not give\n\nIn a quick interview the creator is asked only for `brand-name`. Every other answer may\nreach your brief marked ASSUMED: the companion proposed it from the vision and the market,\nand it was kept without the creator deciding it — on their review, or by an unattended round. Use an assumed answer as a working\ndefault, not as the creator's choice. Where the brief explains a choice that rests on one\n(a tagline, a mark type, a background, a colour seed), say it was proposed rather than\nchosen, and never let an assumed answer outrank what the vision and the market voice imply\nthe way the creator's own answer would. `brand-name` is never assumed: the creator chooses it.\n\n## What you emit\n\nA single `BrandSnapshot`:\n\n- `version` — the snapshot format version (leave at its default unless told otherwise).\n- `name` — the required anchor (`brandName`, optional `tagline`).\n- `logoDirection` / `visualTone` / `audience` — the optional singletons, present when they could be decided or honestly derived.\n- `resolvedAssets` — **leave empty.** This is the companion logo step's output,\n not something you author. Hand-authoring it fabricates asset references the\n pipeline will overwrite or the validator will flag.\n\nAuthor every entity in English. Follow the `brand-logo-authoring` skill for the\nexact field contracts and the mark-type / background / visual-tone decision\naids — its full text is in your brief, under \"The skills this method tells you\nto FOLLOW\". Read it there; you cannot open files.\n\n## Quality gate\n\nYour emitted snapshot is checked by the deterministic `brand-snapshot-valid`\ngate (`validateBrandSnapshot`) before it commits. A directed-but-ungenerated\nbrand (a `logoDirection` present, `resolvedAssets` still empty) is expected and\nonly WARNs — it is exactly the state you hand off to the companion logo step. A\nmissing logo direction and a missing visual tone are also warnings, reflecting a\nnot-yet-complete brief. Emit a clean brief and let the warnings stand honestly\nwhen the brand genuinely is not fully directed yet, rather than inventing a\nmark to silence them.\n\nAfter landing, the advisory judge reads the brief against two criteria — grounding in\nthe interview and the vision, and the audience-and-assets hand-off — and its verdicts\nreach the creator's review as notes. A verdict never refuses a landing.\n\n## Approval\n\nThe drafted `BrandSnapshot` is presented to the creator for approval before it\nbecomes the committed `brand-brief`. Show the brief back in plain prose — the\nname, the mark direction, the visual tone — and let the creator confirm or\ncorrect it. The brand-brief is what the logo is generated from and what\npropagates everywhere; it is worth one explicit human sign-off before the mark\nis made.\n\n## Runtime context\n\nBefore you start, read the current journey state, the vision brief that grounds\nthe brand's meaning, and any brand brief that already exists so you refine it\nrather than re-deriving it from scratch.\n\n(The vision and any previously landed brand brief arrive in your brief as the `vision-brief` and\n`brand-brief` input sections.)\n\n## References\n\nThese are skill FOLDERS installed in the application, and this step has no tools,\nso it does not open them. What reaches you is stated per skill below.\n\n- `brand-logo-authoring` — the field contracts for the `BrandSnapshot` (name /\n logoDirection / visualTone), the mark-type selection table, background\n derivation-safety, and deriving the visual tone from the market voice. Its\n FULL TEXT is in your brief; follow it exactly.\n",
|
|
36
50
|
"skillRefs": [
|
|
37
51
|
"brand-logo-authoring"
|
|
38
52
|
],
|
|
@@ -43,13 +57,17 @@
|
|
|
43
57
|
"questions": [
|
|
44
58
|
{
|
|
45
59
|
"ref": "brand-name",
|
|
46
|
-
"question": "
|
|
47
|
-
"kind": "
|
|
60
|
+
"question": "Which screened name should the brand carry? This exact string is what the logo renders and every surface prints. A name marked [screening-incomplete] could not be checked in every register; [keep-despite-conflict] keeps your own name although the screening found a conflicting mark or competitor. This is a minimal trademark screening, not a legal clearance — consult an IP professional before filing or launching.",
|
|
61
|
+
"kind": "choice",
|
|
62
|
+
"optionsFrom": "brand_name_screening_candidates",
|
|
63
|
+
"depth": "essential",
|
|
64
|
+
"whenUnknown": "ask"
|
|
48
65
|
},
|
|
49
66
|
{
|
|
50
67
|
"ref": "brand-tagline",
|
|
51
68
|
"question": "Is there a tagline / supporting line to lock up with the name (e.g. \"Ship the week, not the meeting.\")? Answer \"none\" if not.",
|
|
52
|
-
"kind": "free_text"
|
|
69
|
+
"kind": "free_text",
|
|
70
|
+
"depth": "detail"
|
|
53
71
|
},
|
|
54
72
|
{
|
|
55
73
|
"ref": "logo-mark-type",
|
|
@@ -63,22 +81,8 @@
|
|
|
63
81
|
"abstract_mark",
|
|
64
82
|
"emblem",
|
|
65
83
|
"mascot"
|
|
66
|
-
]
|
|
67
|
-
|
|
68
|
-
{
|
|
69
|
-
"ref": "logo-motifs",
|
|
70
|
-
"question": "What concrete visual elements should the mark include (short noun phrases, e.g. \"a rising checkmark\", \"concentric rings\")? Answer \"none\" to leave it open.",
|
|
71
|
-
"kind": "free_text"
|
|
72
|
-
},
|
|
73
|
-
{
|
|
74
|
-
"ref": "logo-symbolism",
|
|
75
|
-
"question": "What meaning should the mark evoke (e.g. \"momentum\", \"clarity\", \"trust\")? Derive this from the product's mission / idea rather than inventing it.",
|
|
76
|
-
"kind": "free_text"
|
|
77
|
-
},
|
|
78
|
-
{
|
|
79
|
-
"ref": "logo-avoid",
|
|
80
|
-
"question": "What imagery should the mark AVOID (e.g. \"no gradients\", \"no literal robots\", \"no clip-art gears\")? These are the negative-prompt guardrails that keep the output usable.",
|
|
81
|
-
"kind": "free_text"
|
|
84
|
+
],
|
|
85
|
+
"depth": "detail"
|
|
82
86
|
},
|
|
83
87
|
{
|
|
84
88
|
"ref": "logo-background",
|
|
@@ -88,27 +92,20 @@
|
|
|
88
92
|
"transparent_isolated",
|
|
89
93
|
"solid_field",
|
|
90
94
|
"contextual_scene"
|
|
91
|
-
]
|
|
92
|
-
|
|
93
|
-
{
|
|
94
|
-
"ref": "visual-style-keywords",
|
|
95
|
-
"question": "In 3–7 concrete adjectives, what should the brand LOOK like (e.g. \"geometric\", \"minimal\", \"warm\", \"editorial\")?",
|
|
96
|
-
"kind": "free_text"
|
|
97
|
-
},
|
|
98
|
-
{
|
|
99
|
-
"ref": "visual-mood",
|
|
100
|
-
"question": "In one sentence, what feeling should the imagery leave (e.g. \"calm, precise, quietly confident\")?",
|
|
101
|
-
"kind": "free_text"
|
|
95
|
+
],
|
|
96
|
+
"depth": "detail"
|
|
102
97
|
},
|
|
103
98
|
{
|
|
104
|
-
"ref": "visual-
|
|
105
|
-
"question": "
|
|
106
|
-
"kind": "free_text"
|
|
99
|
+
"ref": "visual-direction",
|
|
100
|
+
"question": "Is there anything the logo or the look should evoke, include or avoid that the vision and the market's voice would not suggest on their own (e.g. \"no literal buildings\", \"a nod to craftsmanship\", \"warm, not corporate\")? Answer \"none\" and the symbolism, imagery and visual tone are derived from the vision and the market voice.",
|
|
101
|
+
"kind": "free_text",
|
|
102
|
+
"depth": "detail"
|
|
107
103
|
},
|
|
108
104
|
{
|
|
109
105
|
"ref": "visual-color-seeds",
|
|
110
106
|
"question": "Has the brand already committed to specific hex colors that the mark must agree with? If so, list them; otherwise answer \"none\" and let the design system own the palette.",
|
|
111
|
-
"kind": "free_text"
|
|
107
|
+
"kind": "free_text",
|
|
108
|
+
"depth": "detail"
|
|
112
109
|
}
|
|
113
110
|
]
|
|
114
111
|
},
|
|
@@ -0,0 +1,105 @@
|
|
|
1
|
+
# Brand Name Research — propose, then screen
|
|
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 **naming researcher**. You do two things: propose names for this product,
|
|
16
|
+
and run a **minimal trademark screening** of every candidate. You do not choose the name
|
|
17
|
+
— the creator does, from what you bring back — and you author no file.
|
|
18
|
+
|
|
19
|
+
## 1. Propose (at least five)
|
|
20
|
+
|
|
21
|
+
Ground every proposal in what the application already decided:
|
|
22
|
+
|
|
23
|
+
- the vision's **idea and mission** — what the product is FOR;
|
|
24
|
+
- the market snapshot's **category language** (the words buyers and competitors use) and
|
|
25
|
+
its **tones of voice** (a serious, formal voice wants a different name from a casual one);
|
|
26
|
+
- the **target geographies and languages** — a name must be pronounceable and inoffensive
|
|
27
|
+
in the target countries' main languages. Check that it carries no unfortunate meaning.
|
|
28
|
+
|
|
29
|
+
Prefer distinctive names (invented or arbitrary) over descriptive ones. A purely
|
|
30
|
+
descriptive name ("Building CRM") is weak as a mark and usually refused registration.
|
|
31
|
+
|
|
32
|
+
**A proposal must not be identical or close to any competitor or alternative the market
|
|
33
|
+
snapshot names**, nor to any name you find trading in the same category. Drop such a name
|
|
34
|
+
before screening it; if one slips through, report the collision so it is never offered.
|
|
35
|
+
|
|
36
|
+
Propose at least five, so at least three survive screening. One line per proposal on
|
|
37
|
+
why it fits. That line is what the creator reads first.
|
|
38
|
+
|
|
39
|
+
## 2. Screen every candidate
|
|
40
|
+
|
|
41
|
+
Screen each proposal, **and every name the creator listed in the interview**
|
|
42
|
+
(`names-to-screen`, unless it says "none"), the same way. Mark the creator's names as theirs.
|
|
43
|
+
|
|
44
|
+
### Jurisdictions — derive, never assume the EU
|
|
45
|
+
|
|
46
|
+
From the market snapshot's ICP geographies, the vision's compliance detail, and the
|
|
47
|
+
operating jurisdictions the application declares. A region tag ("EMEA") is not a
|
|
48
|
+
jurisdiction: name the countries it implies for this product. If any EU member state is
|
|
49
|
+
targeted, the **EU trade mark** (`EU`) applies too, because an EUTM has effect in every
|
|
50
|
+
member state. International registrations (`WO`) are always in scope.
|
|
51
|
+
|
|
52
|
+
### Registers
|
|
53
|
+
|
|
54
|
+
- **EUIPO eSearch plus** (https://euipo.europa.eu/eSearch/) — EU trade marks, and
|
|
55
|
+
international registrations designating the EU.
|
|
56
|
+
- **TMview** (https://www.tmdn.org/tmview/) — the EU office and participating national
|
|
57
|
+
offices in one search.
|
|
58
|
+
- **WIPO Global Brand Database** (https://branddb.wipo.int/) — international (Madrid)
|
|
59
|
+
registrations and many national collections.
|
|
60
|
+
- **The national office of each targeted country** that TMview or WIPO does not already
|
|
61
|
+
cover for you (for example the USPTO for the United States, UKIPO for the United Kingdom).
|
|
62
|
+
|
|
63
|
+
### Classes
|
|
64
|
+
|
|
65
|
+
The Nice classes the product lives in: **9** (software) and **42** (software as a service)
|
|
66
|
+
for every software product, **35** where it is a business-management or CRM tool, and any
|
|
67
|
+
other class the product category implies, each with a one-line reason.
|
|
68
|
+
|
|
69
|
+
### Match types and status
|
|
70
|
+
|
|
71
|
+
Search **identical** marks (ignoring case and spacing) and **near-identical** ones
|
|
72
|
+
(plurals, hyphenation, transposed or substituted letters, common phonetic variants).
|
|
73
|
+
Record only **live** marks: registered, or filed and pending (including under opposition).
|
|
74
|
+
An expired, withdrawn or refused mark is not a conflict.
|
|
75
|
+
|
|
76
|
+
### What to report per query
|
|
77
|
+
|
|
78
|
+
The register, the jurisdictions it covers, the classes and match types searched, the
|
|
79
|
+
result, every live conflicting mark (mark, owner, number, classes, status, the record's
|
|
80
|
+
URL), the search URL, and today's date.
|
|
81
|
+
|
|
82
|
+
## 3. A failure is not an answer
|
|
83
|
+
|
|
84
|
+
Some registers will not answer you: TMview renders in the browser, and WIPO's database is
|
|
85
|
+
behind a CAPTCHA. **When you cannot run a search, or cannot read its result, report that
|
|
86
|
+
register as NOT CHECKED, and say why.** Never infer "no conflict" from a search engine,
|
|
87
|
+
from silence, or from your own memory of which marks exist. A candidate with a register
|
|
88
|
+
not checked is "screening incomplete" — still offered to the creator, never as clear.
|
|
89
|
+
|
|
90
|
+
## 4. Signals beside the registers (recorded, never blocking)
|
|
91
|
+
|
|
92
|
+
- the exact-match `.com` and the main country-code domains of the target countries,
|
|
93
|
+
registered or available;
|
|
94
|
+
- any company or product already trading under the name in this category, with its URL.
|
|
95
|
+
|
|
96
|
+
## What you must never say
|
|
97
|
+
|
|
98
|
+
Never write that a name is "available", "free to use", "safe" or "cleared". This is a
|
|
99
|
+
**minimal trademark screening, not a legal clearance opinion**. The creator should consult an
|
|
100
|
+
IP professional before filing or launching. You report what each register said, with its source.
|
|
101
|
+
|
|
102
|
+
## Condensation
|
|
103
|
+
|
|
104
|
+
Return a brief, not a transcript: candidates, per-register results with URLs and dates,
|
|
105
|
+
collisions, signals, and an explicit list of what could not be checked.
|
|
@@ -0,0 +1,55 @@
|
|
|
1
|
+
{
|
|
2
|
+
"ref": "top_down.brand-name-research",
|
|
3
|
+
"version": "0.1.0",
|
|
4
|
+
"phase": "top_down",
|
|
5
|
+
"intent": "Propose candidate names for the product, grounded in the vision and the market snapshot, and run a minimal trademark screening of every candidate — proposed or supplied by the creator — against the public registers of the jurisdictions the product targets, in the Nice classes it lives in, for identical and near-identical live marks, with domain and same-category signals beside them. Returns a condensed, source-attributed brief and authors nothing. Never a legal clearance opinion: a register it could not query is reported as not checked, never as clear.",
|
|
6
|
+
"preconditions": [
|
|
7
|
+
{
|
|
8
|
+
"kind": "artifact_valid",
|
|
9
|
+
"selector": {
|
|
10
|
+
"family": "vision-brief"
|
|
11
|
+
}
|
|
12
|
+
},
|
|
13
|
+
{
|
|
14
|
+
"kind": "artifact_valid",
|
|
15
|
+
"selector": {
|
|
16
|
+
"family": "market-snapshot"
|
|
17
|
+
}
|
|
18
|
+
}
|
|
19
|
+
],
|
|
20
|
+
"inputs": [
|
|
21
|
+
{
|
|
22
|
+
"family": "vision-brief"
|
|
23
|
+
},
|
|
24
|
+
{
|
|
25
|
+
"family": "market-snapshot"
|
|
26
|
+
},
|
|
27
|
+
{
|
|
28
|
+
"family": "brand-name-screening"
|
|
29
|
+
}
|
|
30
|
+
],
|
|
31
|
+
"outputs": [],
|
|
32
|
+
"stepOutputs": [
|
|
33
|
+
{
|
|
34
|
+
"ref": "brand-name-evidence",
|
|
35
|
+
"condensation": "A brief of at most ~2500 words. First the jurisdictions (each with what declared it) and the Nice classes searched (each with why). Then, per candidate: the exact name, who put it on the list (the companion or the creator), one line on why it fits (proposals only), and for EVERY register query — the register, the jurisdictions it covers, the classes searched, the match types searched (identical, near-identical), the result (no conflict found / conflict / not checked), each live conflicting mark with its owner, number, classes, status and record URL, the search URL and the date. Then any competitor or alternative the market snapshot names that the candidate is identical or close to, the domains checked with their status, and any company already trading under the name in this category. End with what could NOT be checked, and why. Every claim carries the URL it came from; raw page text is never returned.",
|
|
36
|
+
"description": "Screened brand-name candidates with per-register results and sources, condensed for the produce sibling."
|
|
37
|
+
}
|
|
38
|
+
],
|
|
39
|
+
"method": {
|
|
40
|
+
"guidance": "# Brand Name Research — propose, then screen\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 **naming researcher**. You do two things: propose names for this product,\nand run a **minimal trademark screening** of every candidate. You do not choose the name\n— the creator does, from what you bring back — and you author no file.\n\n## 1. Propose (at least five)\n\nGround every proposal in what the application already decided:\n\n- the vision's **idea and mission** — what the product is FOR;\n- the market snapshot's **category language** (the words buyers and competitors use) and\n its **tones of voice** (a serious, formal voice wants a different name from a casual one);\n- the **target geographies and languages** — a name must be pronounceable and inoffensive\n in the target countries' main languages. Check that it carries no unfortunate meaning.\n\nPrefer distinctive names (invented or arbitrary) over descriptive ones. A purely\ndescriptive name (\"Building CRM\") is weak as a mark and usually refused registration.\n\n**A proposal must not be identical or close to any competitor or alternative the market\nsnapshot names**, nor to any name you find trading in the same category. Drop such a name\nbefore screening it; if one slips through, report the collision so it is never offered.\n\nPropose at least five, so at least three survive screening. One line per proposal on\nwhy it fits. That line is what the creator reads first.\n\n## 2. Screen every candidate\n\nScreen each proposal, **and every name the creator listed in the interview**\n(`names-to-screen`, unless it says \"none\"), the same way. Mark the creator's names as theirs.\n\n### Jurisdictions — derive, never assume the EU\n\nFrom the market snapshot's ICP geographies, the vision's compliance detail, and the\noperating jurisdictions the application declares. A region tag (\"EMEA\") is not a\njurisdiction: name the countries it implies for this product. If any EU member state is\ntargeted, the **EU trade mark** (`EU`) applies too, because an EUTM has effect in every\nmember state. International registrations (`WO`) are always in scope.\n\n### Registers\n\n- **EUIPO eSearch plus** (https://euipo.europa.eu/eSearch/) — EU trade marks, and\n international registrations designating the EU.\n- **TMview** (https://www.tmdn.org/tmview/) — the EU office and participating national\n offices in one search.\n- **WIPO Global Brand Database** (https://branddb.wipo.int/) — international (Madrid)\n registrations and many national collections.\n- **The national office of each targeted country** that TMview or WIPO does not already\n cover for you (for example the USPTO for the United States, UKIPO for the United Kingdom).\n\n### Classes\n\nThe Nice classes the product lives in: **9** (software) and **42** (software as a service)\nfor every software product, **35** where it is a business-management or CRM tool, and any\nother class the product category implies, each with a one-line reason.\n\n### Match types and status\n\nSearch **identical** marks (ignoring case and spacing) and **near-identical** ones\n(plurals, hyphenation, transposed or substituted letters, common phonetic variants).\nRecord only **live** marks: registered, or filed and pending (including under opposition).\nAn expired, withdrawn or refused mark is not a conflict.\n\n### What to report per query\n\nThe register, the jurisdictions it covers, the classes and match types searched, the\nresult, every live conflicting mark (mark, owner, number, classes, status, the record's\nURL), the search URL, and today's date.\n\n## 3. A failure is not an answer\n\nSome registers will not answer you: TMview renders in the browser, and WIPO's database is\nbehind a CAPTCHA. **When you cannot run a search, or cannot read its result, report that\nregister as NOT CHECKED, and say why.** Never infer \"no conflict\" from a search engine,\nfrom silence, or from your own memory of which marks exist. A candidate with a register\nnot checked is \"screening incomplete\" — still offered to the creator, never as clear.\n\n## 4. Signals beside the registers (recorded, never blocking)\n\n- the exact-match `.com` and the main country-code domains of the target countries,\n registered or available;\n- any company or product already trading under the name in this category, with its URL.\n\n## What you must never say\n\nNever write that a name is \"available\", \"free to use\", \"safe\" or \"cleared\". This is a\n**minimal trademark screening, not a legal clearance opinion**. The creator should consult an\nIP professional before filing or launching. You report what each register said, with its source.\n\n## Condensation\n\nReturn a brief, not a transcript: candidates, per-register results with URLs and dates,\ncollisions, signals, and an explicit list of what could not be checked.\n",
|
|
41
|
+
"skillRefs": [
|
|
42
|
+
"brand-name-screening"
|
|
43
|
+
],
|
|
44
|
+
"skillBodyRefs": [],
|
|
45
|
+
"contextSources": [],
|
|
46
|
+
"draftableDocumentDefinitionRefs": [],
|
|
47
|
+
"suspendsForClarification": false,
|
|
48
|
+
"briefAdequacyGate": false,
|
|
49
|
+
"briefAdequacyExcludedSources": []
|
|
50
|
+
},
|
|
51
|
+
"executor": "research_agent",
|
|
52
|
+
"approval": "auto",
|
|
53
|
+
"budget": {},
|
|
54
|
+
"onFailure": "keep_and_flag"
|
|
55
|
+
}
|
package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-protocol.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"aggregationPolicyRef":"application-creation:aggregation/worst-brand-name-screening-verdict","aggregationStrategy":"WORST_VERDICT_PRECEDENCE_V1","criteria":[{"assessesAspects":["brand-name-screening.candidate","vision.idea","vision.mission","market.category","market.alternative","market.tone-of-voice"],"criterionRef":"application-creation:criterion/brand-name-proposals-grounded-and-distinct","criterionVersion":1,"evidenceRequirements":[{"requirementRef":"application-creation:evidence-requirement/brand-name-proposals-grounded-and-distinct","requirementVersion":1}],"instruction":"Determine whether the PROPOSALS are worth choosing from: each companion-proposed name carries a rationale traceable to the vision's idea or mission and to the market's category language or tone of voice; no proposal is identical or close to a competitor or alternative the market snapshot names, or to a company the evidence found trading in the same category (a creator-supplied name may collide — it is offered only as an explicit keep-despite-conflict, so it is not a finding here); and every name the creator listed in the interview is on the list, marked as theirs. Nothing in the screening may assert that a name is available, free to use or legally cleared.","schemaVersion":1,"verdictGuidance":{"CONCERN":"Grounded overall, with a generic rationale, a weakly distinctive or purely descriptive proposal, or fewer than three proposals surviving the screening.","GAP":"A proposal collides with a named competitor, a creator-listed name is missing, or the screening claims a name is available or legally cleared.","INDETERMINATE":"The vision, the market snapshot or the creator's interview answer is not in evidence.","PASS":"Every proposal is grounded and distinct from the named competitors, the creator's names are all present, and nothing claims availability or clearance."}},{"assessesAspects":["brand-name-screening.candidate","brand-name-screening.jurisdiction","brand-name-screening.nice-class","market.icp"],"criterionRef":"application-creation:criterion/brand-name-screening-coverage-and-honesty","criterionVersion":1,"evidenceRequirements":[{"requirementRef":"application-creation:evidence-requirement/brand-name-screening-coverage-and-honesty","requirementVersion":1}],"instruction":"Determine whether the screening COVERS what it declares and reports it HONESTLY: the declared jurisdictions follow from the market's ICP geographies and the vision (an EU member state target brings the EU trade mark with it; a region tag is resolved to countries), the Nice classes include 9 and 42 and any class the product category implies, every candidate has a query reaching each declared jurisdiction in those classes for identical and near-identical marks, every query cites a source URL and a date, and no register the evidence reports as unreachable or unread appears with a clear result. A register that could not be checked and is recorded as not checked is a legitimate, honest state, not a finding.","schemaVersion":1,"verdictGuidance":{"CONCERN":"Coverage is honest but thin: a class the category implies is missing, or several registers could not be checked and are correctly recorded as such.","GAP":"A query the evidence reports as unreachable or unread is recorded as clear, a declared jurisdiction is never queried while the candidate reads as cleared, or a query has no source.","INDETERMINATE":"The research evidence or the market snapshot is not in evidence, so coverage and honesty cannot be established.","PASS":"Jurisdictions and classes follow from the product, every candidate is queried across them with sources and dates, and nothing unchecked is shown as clear."}}],"promptAssemblyStrategy":"CANONICAL_PROTOCOL_EVIDENCE_V1","protocolRef":"application-creation:evaluation-protocol/brand-name-screening","protocolVersion":1,"provenance":{"compilerRef":"meta-workflow:compiler/evaluation-treatment","compilerVersion":1,"sourcePlaybookRef":"playbook:top_down.brand-name-screening-produce"},"schemaVersion":1,"verdictPrecedence":["GAP","INDETERMINATE","CONCERN","PASS"]}
|
package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-treatment.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"authorityRequirement":{"admittedChannels":["INTERFACE_RELAY"],"assurancePolicyRef":"application-creation:authority-policy/local-single-operator","channelPolicyRef":"application-creation:authority-policy/interface-relay","consequenceClassRef":"application-creation:authority-consequence/accept-brand-name-screening","decisionModePolicyRef":"application-creation:authority-policy/explicit-operator-confirmation","expiryPolicyRef":"application-creation:authority-expiry/current-interface-session","hardFloorOverrideAllowed":false,"hardFloorPosture":"NON_WAIVABLE","minimumAssurance":"LOCAL_OS_SESSION","noncePolicyRef":"application-creation:authority-nonce/random-per-request","principalPolicyRef":null,"requiredDecisionMode":"EXPLICIT_OPERATOR_CONFIRMATION","requiredEvidenceRequirementRefs":["application-creation:evidence-requirement/brand-name-screening-coverage-and-honesty"],"requirementRef":"application-creation:authority-requirement/brand-name-screening-result","requirementVersion":1,"riskClassRef":"application-creation:risk/brand-name-screening-accepted-family-mutation","schemaVersion":1},"continuationPolicy":{"fallbackAction":"BLOCK","mappings":[{"action":"CONTINUE","decisionConsequence":"CONTINUE"},{"action":"REVISE","decisionConsequence":"REVISE"},{"action":"REQUEST_EVIDENCE","decisionConsequence":"REQUEST_EVIDENCE"},{"action":"REQUEST_AUTHORITY","decisionConsequence":"REQUEST_AUTHORITY"},{"action":"BLOCK","decisionConsequence":"BLOCK"}],"maximumAuthorityReviews":1,"maximumEvidenceRequests":2,"maximumRevisionAttempts":3,"policyRef":"application-creation:continuation-policy/brand-name-screening","policyVersion":1,"schemaVersion":1},"decisionPointDefinition":{"authorityRequirement":{"requirementRef":"application-creation:authority-requirement/brand-name-screening-result","requirementVersion":1},"continuationPolicy":{"policyRef":"application-creation:continuation-policy/brand-name-screening","policyVersion":1},"decisionPointRef":"application-creation:decision-point/brand-name-screening-result","decisionPointVersion":1,"decisionRule":{"ruleRef":"application-creation:decision-rule/brand-name-screening-result","ruleVersion":1},"evaluatorBindingPolicy":{"policyRef":"application-creation:evaluator-binding-policy/brand-name-screening","policyVersion":1},"evidenceRequirements":[{"requirementRef":"application-creation:evidence-requirement/brand-name-proposals-grounded-and-distinct","requirementVersion":1},{"requirementRef":"application-creation:evidence-requirement/brand-name-screening-coverage-and-honesty","requirementVersion":1}],"hardFloorRefs":["application-creation:hard-floor/brand-name-screening-valid"],"riskPolicyRef":"application-creation:risk-policy/scoped-application-and-execution-context","schemaVersion":1,"significancePolicyRef":"application-creation:significance-policy/current-horizon-brand-name-screening-change","triggerRefs":["application-creation:trigger/brand-name-screening-staged-and-valid"]},"decisionRule":{"boundaryClass":"QUALITY_INTERPRETATION","evaluatorFailureConsequence":"BLOCK","evidenceAggregationRef":"application-creation:aggregation/worst-brand-name-screening-verdict","hardFloorBindings":[{"evidenceRequirementRefs":["application-creation:evidence-requirement/brand-name-screening-coverage-and-honesty"],"hardFloorRef":"application-creation:hard-floor/brand-name-screening-valid"}],"hardFloorFailureConsequence":"BLOCK","hardFloorShortcutAllowed":false,"resultMappings":[{"consequence":"REQUEST_AUTHORITY","verdict":"PASS"},{"consequence":"REVISE","verdict":"CONCERN"},{"consequence":"REVISE","verdict":"GAP"},{"consequence":"REQUEST_EVIDENCE","verdict":"INDETERMINATE"}],"ruleRef":"application-creation:decision-rule/brand-name-screening-result","ruleVersion":1,"schemaVersion":1,"unresolvedConsequence":"REQUEST_EVIDENCE"},"definitionRef":"application-creation:evaluation-treatment/brand-name-screening","definitionVersion":1,"evaluationProtocol":{"aggregationPolicyRef":"application-creation:aggregation/worst-brand-name-screening-verdict","aggregationStrategy":"WORST_VERDICT_PRECEDENCE_V1","criteria":[{"assessesAspects":["brand-name-screening.candidate","vision.idea","vision.mission","market.category","market.alternative","market.tone-of-voice"],"criterionRef":"application-creation:criterion/brand-name-proposals-grounded-and-distinct","criterionVersion":1,"evidenceRequirements":[{"requirementRef":"application-creation:evidence-requirement/brand-name-proposals-grounded-and-distinct","requirementVersion":1}],"instruction":"Determine whether the PROPOSALS are worth choosing from: each companion-proposed name carries a rationale traceable to the vision's idea or mission and to the market's category language or tone of voice; no proposal is identical or close to a competitor or alternative the market snapshot names, or to a company the evidence found trading in the same category (a creator-supplied name may collide — it is offered only as an explicit keep-despite-conflict, so it is not a finding here); and every name the creator listed in the interview is on the list, marked as theirs. Nothing in the screening may assert that a name is available, free to use or legally cleared.","schemaVersion":1,"verdictGuidance":{"CONCERN":"Grounded overall, with a generic rationale, a weakly distinctive or purely descriptive proposal, or fewer than three proposals surviving the screening.","GAP":"A proposal collides with a named competitor, a creator-listed name is missing, or the screening claims a name is available or legally cleared.","INDETERMINATE":"The vision, the market snapshot or the creator's interview answer is not in evidence.","PASS":"Every proposal is grounded and distinct from the named competitors, the creator's names are all present, and nothing claims availability or clearance."}},{"assessesAspects":["brand-name-screening.candidate","brand-name-screening.jurisdiction","brand-name-screening.nice-class","market.icp"],"criterionRef":"application-creation:criterion/brand-name-screening-coverage-and-honesty","criterionVersion":1,"evidenceRequirements":[{"requirementRef":"application-creation:evidence-requirement/brand-name-screening-coverage-and-honesty","requirementVersion":1}],"instruction":"Determine whether the screening COVERS what it declares and reports it HONESTLY: the declared jurisdictions follow from the market's ICP geographies and the vision (an EU member state target brings the EU trade mark with it; a region tag is resolved to countries), the Nice classes include 9 and 42 and any class the product category implies, every candidate has a query reaching each declared jurisdiction in those classes for identical and near-identical marks, every query cites a source URL and a date, and no register the evidence reports as unreachable or unread appears with a clear result. A register that could not be checked and is recorded as not checked is a legitimate, honest state, not a finding.","schemaVersion":1,"verdictGuidance":{"CONCERN":"Coverage is honest but thin: a class the category implies is missing, or several registers could not be checked and are correctly recorded as such.","GAP":"A query the evidence reports as unreachable or unread is recorded as clear, a declared jurisdiction is never queried while the candidate reads as cleared, or a query has no source.","INDETERMINATE":"The research evidence or the market snapshot is not in evidence, so coverage and honesty cannot be established.","PASS":"Jurisdictions and classes follow from the product, every candidate is queried across them with sources and dates, and nothing unchecked is shown as clear."}}],"promptAssemblyStrategy":"CANONICAL_PROTOCOL_EVIDENCE_V1","protocolRef":"application-creation:evaluation-protocol/brand-name-screening","protocolVersion":1,"provenance":{"compilerRef":"meta-workflow:compiler/evaluation-treatment","compilerVersion":1,"sourcePlaybookRef":"playbook:top_down.brand-name-screening-produce"},"schemaVersion":1,"verdictPrecedence":["GAP","INDETERMINATE","CONCERN","PASS"]},"evaluatorBindingPolicy":{"admissibleEvaluatorDescriptors":[{"descriptorRef":"meta-workflow:evaluator/structured-semantic-coherence","descriptorVersion":1}],"budgetPolicyRef":"application-creation:evaluator-policy/current-work-cycle-budget","defaultEvaluatorDescriptor":{"descriptorRef":"meta-workflow:evaluator/structured-semantic-coherence","descriptorVersion":1},"escalationPolicyRef":"application-creation:evaluator-policy/request-explicit-review","fallbackPolicyRef":"application-creation:evaluator-policy/fail-closed","maximumAttempts":2,"outputSchemaRef":"meta-workflow:schema/structured-semantic-evaluation-candidate","policyRef":"application-creation:evaluator-binding-policy/brand-name-screening","policyVersion":1,"schemaVersion":1,"selectionPolicyRef":"application-creation:evaluator-policy/scoped-risk-and-evidence","timeoutPolicyRef":"application-creation:evaluator-policy/bounded-semantic-evaluation"},"evidenceRequirements":[{"aggregationPolicyRef":null,"conditionRef":null,"coveragePolicyRef":"application-creation:evidence-policy/exact-brand-name-inputs-and-candidate","criterionRef":"application-creation:criterion/brand-name-proposals-grounded-and-distinct","diversityPolicyRef":null,"freshnessPolicyRef":"application-creation:evidence-policy/current-action-binding","independencePolicyRef":null,"kind":"MANDATORY","maxCount":4,"minCount":2,"requirementRef":"application-creation:evidence-requirement/brand-name-proposals-grounded-and-distinct","requirementVersion":1,"schemaVersion":1,"subjectRef":"application-creation:definition-set/market-research-and-brand-name-screening-candidate"},{"aggregationPolicyRef":null,"conditionRef":null,"coveragePolicyRef":"application-creation:evidence-policy/exact-brand-name-inputs-and-candidate","criterionRef":"application-creation:criterion/brand-name-screening-coverage-and-honesty","diversityPolicyRef":null,"freshnessPolicyRef":"application-creation:evidence-policy/current-action-binding","independencePolicyRef":null,"kind":"MANDATORY","maxCount":4,"minCount":2,"requirementRef":"application-creation:evidence-requirement/brand-name-screening-coverage-and-honesty","requirementVersion":1,"schemaVersion":1,"subjectRef":"application-creation:definition-set/market-research-and-brand-name-screening-candidate"}],"schemaVersion":1}
|
|
@@ -0,0 +1,78 @@
|
|
|
1
|
+
# Brand Name Screening — land what the research found
|
|
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 turn the evidence a sibling research step gathered into the validated
|
|
16
|
+
**`BrandNameScreening`** — the `brand-name-screening` family. The creator chooses the
|
|
17
|
+
brand name from what you land, so the record must say exactly what was checked and
|
|
18
|
+
what each register returned, and nothing more.
|
|
19
|
+
|
|
20
|
+
You are a **transcriber, not a judge.** There is no field for "this name is clear":
|
|
21
|
+
a candidate's standing is computed from its register queries. Your job is to record
|
|
22
|
+
every query faithfully.
|
|
23
|
+
|
|
24
|
+
## Where your inputs are
|
|
25
|
+
|
|
26
|
+
- The research brief is in your brief under "Evidence gathered for this run".
|
|
27
|
+
- The vision and the market snapshot are in your brief as input sections.
|
|
28
|
+
- A screening already on record, if any, is in your brief too. Keep its candidates and
|
|
29
|
+
their slugs, and re-record them with the new evidence. A re-run adds to the list; it
|
|
30
|
+
does not forget it.
|
|
31
|
+
- The creator's own names are in the interview answers of `top_down.brand-naming`
|
|
32
|
+
(`names-to-screen`). Every one of them is a candidate with origin `CREATOR_SUPPLIED`.
|
|
33
|
+
|
|
34
|
+
## What you emit
|
|
35
|
+
|
|
36
|
+
- `screenedOn` — today's date.
|
|
37
|
+
- `jurisdictions` — each code the research searched (`EU` for the EU trade mark, `WO` for
|
|
38
|
+
international registrations, ISO country codes otherwise), with what declared it.
|
|
39
|
+
- `niceClasses` — each class searched, with why this product lives in it.
|
|
40
|
+
- `candidates` — one per name, with a kebab-case `slug`, the exact `name`, its `origin`,
|
|
41
|
+
a one-line `rationale` for proposals, and:
|
|
42
|
+
- `trademarkQueries` — one per register search the evidence reports: register,
|
|
43
|
+
jurisdictions covered, classes and match types searched, outcome, conflicting marks,
|
|
44
|
+
source URL, date, and a note for anything a reader needs.
|
|
45
|
+
- `competitorCollisions` — any market competitor or alternative the name is identical
|
|
46
|
+
or close to.
|
|
47
|
+
- `domainSignals` and `sameCategoryUses` — as the evidence reports them.
|
|
48
|
+
|
|
49
|
+
## The rules that keep it true
|
|
50
|
+
|
|
51
|
+
- **A register the evidence could not query or read is `UNKNOWN`, with a note saying
|
|
52
|
+
why.** Never `CLEAR`. Never omit it either: an unrecorded register is an uncovered
|
|
53
|
+
jurisdiction, and the candidate reads as not cleared anyway.
|
|
54
|
+
- **`CONFLICT` exactly when the query found a live identical or near-identical mark**,
|
|
55
|
+
and then every such mark is listed with its source. A conflict with no mark, or a
|
|
56
|
+
mark beside a `CLEAR`, is refused at landing.
|
|
57
|
+
- **Only what the evidence says.** No mark, URL, date or result from memory. A claim
|
|
58
|
+
without a source in the evidence is left out and named in a query note.
|
|
59
|
+
- **Keep conflicting proposals on record.** A proposal that conflicts is never offered
|
|
60
|
+
to the creator, and the record of why it was dropped is still worth keeping.
|
|
61
|
+
- **Never write "available", "free to use" or "cleared".** This is a minimal trademark
|
|
62
|
+
screening, not a legal clearance opinion.
|
|
63
|
+
|
|
64
|
+
Follow the `brand-name-screening` skill for the field contracts. Its full text is in
|
|
65
|
+
your brief under "The skills this method tells you to FOLLOW". Read it there; you cannot
|
|
66
|
+
open files.
|
|
67
|
+
|
|
68
|
+
## Quality gate
|
|
69
|
+
|
|
70
|
+
The deterministic `validateBrandNameScreening` runs before anything lands. It refuses a
|
|
71
|
+
contradictory record and REPORTS the rest for the creator's review: an incomplete
|
|
72
|
+
screening, a conflicting proposal kept for the record, fewer than three offerable
|
|
73
|
+
proposals, a missing EU trade mark for an EU target, or a missing class 9 or 42. Let
|
|
74
|
+
those findings stand honestly rather than inventing results to silence them.
|
|
75
|
+
|
|
76
|
+
After landing, an advisory judge reads the screening for coverage and honesty, and checks
|
|
77
|
+
that the proposals are grounded and distinct from the competitors. Its verdict is a note
|
|
78
|
+
for the creator's review.
|
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
{
|
|
2
|
+
"ref": "top_down.brand-name-screening-produce",
|
|
3
|
+
"version": "0.1.0",
|
|
4
|
+
"phase": "top_down",
|
|
5
|
+
"intent": "Derive the validated brand-name screening from the vision, the market snapshot and the evidence a sibling research step gathered: the jurisdictions and Nice classes searched, and per candidate its origin, why it fits, every register query with its result, conflicting marks, source and date, the competitor collisions, and the domain and same-category signals. Transcribes, never concludes: a candidate's standing is derived from its queries. A minimal trademark screening, never a legal clearance opinion.",
|
|
6
|
+
"preconditions": [
|
|
7
|
+
{
|
|
8
|
+
"kind": "artifact_valid",
|
|
9
|
+
"selector": {
|
|
10
|
+
"family": "vision-brief"
|
|
11
|
+
}
|
|
12
|
+
},
|
|
13
|
+
{
|
|
14
|
+
"kind": "artifact_valid",
|
|
15
|
+
"selector": {
|
|
16
|
+
"family": "market-snapshot"
|
|
17
|
+
}
|
|
18
|
+
},
|
|
19
|
+
{
|
|
20
|
+
"kind": "step_available",
|
|
21
|
+
"ref": "brand-name-evidence"
|
|
22
|
+
}
|
|
23
|
+
],
|
|
24
|
+
"inputs": [
|
|
25
|
+
{
|
|
26
|
+
"family": "vision-brief"
|
|
27
|
+
},
|
|
28
|
+
{
|
|
29
|
+
"family": "market-snapshot"
|
|
30
|
+
},
|
|
31
|
+
{
|
|
32
|
+
"family": "brand-name-screening"
|
|
33
|
+
}
|
|
34
|
+
],
|
|
35
|
+
"outputs": [
|
|
36
|
+
{
|
|
37
|
+
"family": "brand-name-screening",
|
|
38
|
+
"schemaRef": "saas-specifications:BrandNameScreening",
|
|
39
|
+
"description": "The screened brand-name candidates — jurisdictions and classes searched, per-register results with sources and dates, competitor collisions and domain signals — validated by validateBrandNameScreening. The brand-identity interview offers its `brand-name` CHOICE from it."
|
|
40
|
+
}
|
|
41
|
+
],
|
|
42
|
+
"stepOutputs": [],
|
|
43
|
+
"method": {
|
|
44
|
+
"guidance": "# Brand Name Screening — land what the research found\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 turn the evidence a sibling research step gathered into the validated\n**`BrandNameScreening`** — the `brand-name-screening` family. The creator chooses the\nbrand name from what you land, so the record must say exactly what was checked and\nwhat each register returned, and nothing more.\n\nYou are a **transcriber, not a judge.** There is no field for \"this name is clear\":\na candidate's standing is computed from its register queries. Your job is to record\nevery query faithfully.\n\n## Where your inputs are\n\n- The research brief is in your brief under \"Evidence gathered for this run\".\n- The vision and the market snapshot are in your brief as input sections.\n- A screening already on record, if any, is in your brief too. Keep its candidates and\n their slugs, and re-record them with the new evidence. A re-run adds to the list; it\n does not forget it.\n- The creator's own names are in the interview answers of `top_down.brand-naming`\n (`names-to-screen`). Every one of them is a candidate with origin `CREATOR_SUPPLIED`.\n\n## What you emit\n\n- `screenedOn` — today's date.\n- `jurisdictions` — each code the research searched (`EU` for the EU trade mark, `WO` for\n international registrations, ISO country codes otherwise), with what declared it.\n- `niceClasses` — each class searched, with why this product lives in it.\n- `candidates` — one per name, with a kebab-case `slug`, the exact `name`, its `origin`,\n a one-line `rationale` for proposals, and:\n - `trademarkQueries` — one per register search the evidence reports: register,\n jurisdictions covered, classes and match types searched, outcome, conflicting marks,\n source URL, date, and a note for anything a reader needs.\n - `competitorCollisions` — any market competitor or alternative the name is identical\n or close to.\n - `domainSignals` and `sameCategoryUses` — as the evidence reports them.\n\n## The rules that keep it true\n\n- **A register the evidence could not query or read is `UNKNOWN`, with a note saying\n why.** Never `CLEAR`. Never omit it either: an unrecorded register is an uncovered\n jurisdiction, and the candidate reads as not cleared anyway.\n- **`CONFLICT` exactly when the query found a live identical or near-identical mark**,\n and then every such mark is listed with its source. A conflict with no mark, or a\n mark beside a `CLEAR`, is refused at landing.\n- **Only what the evidence says.** No mark, URL, date or result from memory. A claim\n without a source in the evidence is left out and named in a query note.\n- **Keep conflicting proposals on record.** A proposal that conflicts is never offered\n to the creator, and the record of why it was dropped is still worth keeping.\n- **Never write \"available\", \"free to use\" or \"cleared\".** This is a minimal trademark\n screening, not a legal clearance opinion.\n\nFollow the `brand-name-screening` skill for the field contracts. Its full text is in\nyour brief under \"The skills this method tells you to FOLLOW\". Read it there; you cannot\nopen files.\n\n## Quality gate\n\nThe deterministic `validateBrandNameScreening` runs before anything lands. It refuses a\ncontradictory record and REPORTS the rest for the creator's review: an incomplete\nscreening, a conflicting proposal kept for the record, fewer than three offerable\nproposals, a missing EU trade mark for an EU target, or a missing class 9 or 42. Let\nthose findings stand honestly rather than inventing results to silence them.\n\nAfter landing, an advisory judge reads the screening for coverage and honesty, and checks\nthat the proposals are grounded and distinct from the competitors. Its verdict is a note\nfor the creator's review.\n",
|
|
45
|
+
"skillRefs": [
|
|
46
|
+
"brand-name-screening"
|
|
47
|
+
],
|
|
48
|
+
"skillBodyRefs": [
|
|
49
|
+
"brand-name-screening"
|
|
50
|
+
],
|
|
51
|
+
"contextSources": [],
|
|
52
|
+
"draftableDocumentDefinitionRefs": [],
|
|
53
|
+
"suspendsForClarification": false,
|
|
54
|
+
"briefAdequacyGate": false,
|
|
55
|
+
"briefAdequacyExcludedSources": []
|
|
56
|
+
},
|
|
57
|
+
"executor": "companion_agent",
|
|
58
|
+
"approval": "approve_result",
|
|
59
|
+
"budget": {
|
|
60
|
+
"maxRuns": 3
|
|
61
|
+
},
|
|
62
|
+
"onFailure": "keep_and_flag"
|
|
63
|
+
}
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
# Brand Naming — the umbrella
|
|
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 playbook produces nothing itself. It coordinates two children, and the
|
|
16
|
+
`brand-name-screening` is landed by one of them. What lands is the list the creator
|
|
17
|
+
CHOOSES the brand name from, in the `brand-name` question of `top_down.brand-identity`.
|
|
18
|
+
|
|
19
|
+
**The companion proposes; the creator chooses.** Nothing here picks the name.
|
|
20
|
+
|
|
21
|
+
## The children, and why the order is not written here
|
|
22
|
+
|
|
23
|
+
- **`top_down.brand-name-research`** proposes candidate names and screens every
|
|
24
|
+
candidate — proposed or the creator's own — against the public trademark registers,
|
|
25
|
+
with web access. Read-only: it returns a condensed, source-attributed brief.
|
|
26
|
+
- **`top_down.brand-name-screening-produce`** turns that brief into the validated
|
|
27
|
+
`brand-name-screening` family. It becomes eligible once research has returned.
|
|
28
|
+
|
|
29
|
+
Nothing above is a sequence: produce needs research's evidence (`step_available`),
|
|
30
|
+
and that precondition is the whole order.
|
|
31
|
+
|
|
32
|
+
## Composing an objective for research
|
|
33
|
+
|
|
34
|
+
- The **first** round proposes and screens. Name the vision's idea and mission, the
|
|
35
|
+
market's category language and tones of voice, the competitors and alternatives the
|
|
36
|
+
market snapshot names (no candidate may collide with one), and the jurisdictions
|
|
37
|
+
the application targets (from the market's ICP geographies and the vision's
|
|
38
|
+
compliance detail). Ask for at least five proposals, so three survive screening.
|
|
39
|
+
- Include **every name the creator listed** in this playbook's interview (`names-to-screen`,
|
|
40
|
+
unless it says "none"). They are screened exactly like proposals, and marked as theirs.
|
|
41
|
+
- A **second** round is warranted only when the first could not reach a register
|
|
42
|
+
(a CAPTCHA, an outage) or fewer than three proposals survived. Name precisely which
|
|
43
|
+
register, jurisdiction or class was not reached, or ask for new proposals — never
|
|
44
|
+
repeat the first objective.
|
|
45
|
+
|
|
46
|
+
## When to stop
|
|
47
|
+
|
|
48
|
+
Once the screening has landed with at least three offerable proposals, or once a second
|
|
49
|
+
research round could not improve on the first. An UNKNOWN register result is an honest
|
|
50
|
+
answer: it is offered to the creator as "screening incomplete", never as clear.
|
|
51
|
+
|
|
52
|
+
## What this is not
|
|
53
|
+
|
|
54
|
+
A **minimal trademark screening — not a legal clearance opinion.** Nothing in this lane
|
|
55
|
+
may say a name is "available", "free to use" or "cleared". The creator is told to
|
|
56
|
+
consult an IP professional before filing or launching under any name.
|