b2c-app-builder 0.221.39

package/agents/skills/b2c-plan-implementation/references/task.md

@@ -0,0 +1,41 @@
+# Engineering orchestration (CE + production readiness)
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+Canonical workflow: `workflow.engineering.engineering-orchestration-ce-production-readiness`. This is a reference contract, not an executable plan. Managed eligibility, ordering, authority, and acceptance remain with the installed business runtime.
+
+## Inputs and outputs
+
+For advisory work, use the evidence supplied and return findings. Do not create runtime state, prerequisite artifacts, or a whole business to satisfy these managed-workspace paths. Missing evidence remains explicit.
+
+Managed inputs: `engineering/TECH_SPEC.md`, `state/LAUNCH_TRACE.md`, `DESIGN.md`, `state/business-state.json`
+
+Consult when relevant: None declared.
+
+Managed outputs: `engineering/ENGINEERING_PLAN.md`, `operations/ORCHESTRATION.md`, `engineering/PRODUCTION_READINESS.md`
+
+## Verification and authority
+
+Declared checks: `check:compound-engineering`, `check:orchestration`
+
+Additional founder decisions: None specific to this workflow; host permission boundaries still apply.
+
+Run applicable checks with the installed builder's documented target arguments. Report unavailable or unrun checks honestly. A review report, generated file, or successful command does not by itself establish accepted runtime or provider evidence. Do not mark reducer state by hand.
+
+## Select supporting knowledge
+
+Load only the sections needed for the current task. Broad load-when wording does not override accepted scope or an explicit provider binding. Provider procedures are current only at the corresponding selected-provider action. Stop and report an unresolved required source rather than treating its title as delivered guidance.
+
+| Reference | Load when | Stable identity |
+| --- | --- | --- |
+| [Design Acceptance Evidence](../../../../knowledge/design/design-acceptance.md) | accepting complete native and landing design or repairing missing, stale, producer-unbound, incomplete, or independently rejected visual evidence | `reference.design.design-acceptance` |
+| [Premium Mobile Craft](../../../../knowledge/design/premium-mobile-craft.md) | building or polishing in-app UI; wiring press states, animation, haptics, keyboard, loading/empty states; any "premium feel" request | `reference.design.premium-mobile-craft` |
+| [Quality Lens](../../../../knowledge/design/quality-lens.md) | judging whether a design-room output is actually good, not just present — the 11-star taste filter, anti-generic checks, and inspiration sources applied during a design-room mutation (distinct from design-room.md's protocol and surfaces-b2c.md's schemas) | `reference.design.quality-lens` |
+| [Engineering Orchestration](../../../../knowledge/engineering/engineering-orchestration.md) | before app implementation, backend/frontend work, or production-readiness claims — mobile quality bars, engineering/ENGINEERING_PLAN.md, engineering/PRODUCTION_READINESS.md, and device-proof expectations | `reference.engineering.engineering-orchestration` |
+| [Recommended Agent Skills](../../../../knowledge/engineering/recommended-agent-skills.md) | before Expo or SwiftUI implementation when choosing recommended external agent skill packs for craft, motion, store work, optional recency research, or optional design-research provider guidance without vendor lock-in | `reference.engineering.recommended-agent-skills` |
+| [Eleven-Star Experience](../../../../knowledge/experience/eleven-star-experience.md) | before PRODUCT.md, DESIGN.md, onboarding, ads, store screenshots, content assets, or engineering plans are treated as ready; on "11-star run"/"11-star pass" — follow the reference's 11-Star Run Protocol before any other output | `reference.experience.eleven-star-experience` |
+| [Compound Engineering Routing](../../../../knowledge/orchestration/compound-engineering-routing.md) | choosing which compound-engineering (CE) skill to invoke for a build stage — the freshness/plan/work/review/ test/proof loop, generated builder prompts, parallel agents, and worktrees | `reference.orchestration.compound-engineering-routing` |
+| [Isolated Review](../../../../knowledge/orchestration/isolated-review.md) | before dispatching any producer whose surface a second agent must accept, before dispatching an auditor node, when writing or checking the review ledger in operations/ORCHESTRATION.md, and when a review, rubric, or fix loop is contested | `reference.orchestration.isolated-review` |
+| [Parallel Agent Orchestration](../../../../knowledge/orchestration/parallel-agent-orchestration.md) | dispatching or coordinating subagents — lane ownership, worktree isolation, budgets, quarantine, reconciliation, and reconciling durable state; before provider/store mutations or handoff in multi-lane work | `reference.orchestration.parallel-agent-orchestration` |
+| [Project State](../../../../knowledge/orchestration/project-state.md) | reading state/business-state.json to resume runtime work, or changing runtime state through the reducer — the durable state schema, reducer contract, and continuation rules; author product scope and decisions in product.yaml and render PRODUCT.md; load together with parallel-agent-orchestration.md when dispatching subagents | `reference.orchestration.project-state` |
+| [Engineering And Agent Orchestration](../../../../knowledge/process/tool-recipes/engineering-and-agent-orchestration.md) | routing engineering work through CE skills, parallel-agent rules, the three engineering record contracts, and choosing MCP, CLI, or skill-pack shape for a new third-party tool — routed from tool-recipes.md | `reference.process.tool-recipes.engineering-and-agent-orchestration` |

package/agents/skills/b2c-plan-launch/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: b2c-plan-launch
+description: "Plan a scoped launch narrative, channels, assets, measurement, and follow-up from current evidence. Drafting does not publish, connect accounts, enable campaigns, or spend money."
+compatibility: Markdown and supplied evidence. Provider-backed work needs the corresponding authorized tools. The B2C runtime is optional for focused advisory work.
+metadata:
+  source-workflow: "workflow.growth.launch-narrative-and-cadence"
+  generated-by: b2c-catalog
+---
+
+# Plan a launch
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+## Choose the scope
+
+Use this task directly for focused advice, review, or an authorized change. Do not require setup, install software, create a workspace, or activate a full launch graph merely to use this expertise. A review is read-only unless the user also requests changes.
+
+For an existing managed business, read business-status then business-plan and use its current brief. This skill cannot choose executable next work, bypass prerequisites, change provider bindings, or replace runtime acceptance. Do not inspect raw reducer files merely to start a focused task.
+
+## Method
+
+For a review, assess the existing evidence against this method and return findings; do not execute its authoring or mutation instructions. For requested creation or implementation, follow the method only within the accepted scope and authority.
+
+## Continuous experience principle
+
+Carry the accepted user's intended outcome through the work: make the result meaningfully better for that user, preserve relevant identity, hierarchy, accessibility, and recovery constraints, and verify behavior as well as presence. Apply this only where relevant; a narrow fix stays narrow. This principle does not require an 11-star exercise or a numeric taste score.
+
+The fastest-growing consumer-AI companies treat **every release as an event** and run a
+**deliberate cadence**, so they are always in the conversation. That is a system, not luck —
+each beat is planned weeks out, down to post order and who replies to what. This reference
+encodes that system so a launch package ships with a real narrative and cadence instead of a
+pretty 30-second animation and a blog post written the day before.
+
+The core reframe: **a launch is not the end of building a product; it is the reason to build it
+a certain way.** Use rare big moments to earn a standing audience, then feed that audience so it
+never goes cold.
+
+## Load only what the task needs
+
+[Task inputs, outputs, checks, and knowledge selectors](references/task.md) supplies the canonical details when they are needed. Open the specific referenced sections, not the whole library. In connected knowledge retrieval, follow exact section selectors, revision hashes, and continuation calls. Unresolved guidance remains unresolved.
+
+## Tools and evidence
+
+Keep the method independent of the agent host and business provider. Honor explicit selections. Use already available, authorized tools that implement the required operation; do not infer availability from the agent's name or silently substitute a provider. Load a provider's procedure only when its action is current. Record missing capabilities without inventing provider proof.
+
+Pause for access or secrets, spend, pricing or legal decisions, destructive changes, hosted deployment, store submission, or production release. Guidance is not permission. A proposed price is not an approved price, and a mock is not live evidence.
+
+## Return
+
+Report findings or changes, the evidence inspected, applicable checks actually run, unresolved requirements, and the next decision. Label advisory findings separately from accepted business evidence. Do not record business completion or modify reducer-owned state outside the supported runtime.

package/agents/skills/b2c-plan-launch/references/task.md

@@ -0,0 +1,37 @@
+# Launch narrative & cadence
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+Canonical workflow: `workflow.growth.launch-narrative-and-cadence`. This is a reference contract, not an executable plan. Managed eligibility, ordering, authority, and acceptance remain with the installed business runtime.
+
+## Inputs and outputs
+
+For advisory work, use the evidence supplied and return findings. Do not create runtime state, prerequisite artifacts, or a whole business to satisfy these managed-workspace paths. Missing evidence remains explicit.
+
+Managed inputs: `DESIGN.md`, `growth/VIRAL_GROWTH.md`, `product/experience/11-star-experience/11_STAR_EXPERIENCE.md`, `strategy/RESEARCH.md`, `strategy/SIGNAL_CORPUS.md`
+
+Consult when relevant: `growth/content-assets/CONTENT_ASSETS.md`
+
+Managed outputs: `growth/LAUNCH_NARRATIVE.md`, `growth/content-intelligence.csv`
+
+## Verification and authority
+
+Declared checks: None declared.
+
+Additional founder decisions: approve public launch posting
+
+Run applicable checks with the installed builder's documented target arguments. Report unavailable or unrun checks honestly. A review report, generated file, or successful command does not by itself establish accepted runtime or provider evidence. Do not mark reducer state by hand.
+
+## Select supporting knowledge
+
+Load only the sections needed for the current task. Broad load-when wording does not override accepted scope or an explicit provider binding. Provider procedures are current only at the corresponding selected-provider action. Stop and report an unresolved required source rather than treating its title as delivered guidance.
+
+| Reference | Load when | Stable identity |
+| --- | --- | --- |
+| [Ethics Guardrail](../../../../knowledge/experience/ethics-guardrail.md) | a HIGH-risk Experience Card (variable reward, streak, scarcity, urgency, social proof) is in play, or before any regulatory/platform-compliance claim about an engagement mechanic — Bright-Line/Dark-Line test, FTC/EU DSA/Apple/Google Play/COPPA landscape, the guardrail attestation-block contract consumed by check:emotional-design | `reference.experience.ethics-guardrail` |
+| [Launch Narrative Cadence](../../../../knowledge/growth/launch-narrative-cadence.md) | before drafting the announcement, the launch-day sequence, the tentpole-vs-weekly-cadence plan, or launch post copy | `reference.growth.launch-narrative-cadence` |
+| [Viral Growth Loops](../../../../knowledge/growth/viral-growth-loops.md) | before referral unlocks, share-to-unlock, invite systems, social/comment loops, viral onboarding or paywall flows, creator CTAs, content format labs, or features meant to spread on TikTok/Reels/Shorts | `reference.growth.viral-growth-loops` |
+| [Distribution-First Niche](../../../../knowledge/research/distribution-first-niche.md) | before Phase 2 build; when research must name a paying audience, one reachable channel, and purchases as validation | `reference.research.distribution-first-niche` |
+| [Distribution, Offer, And Signal Validation](../../../../knowledge/research/distribution-offer-signal.md) | before a Go, Pivot, or Kill decision; when founder posts, transcripts, reviews, interviews, support records, or prior launch material can inform the business; before automating a value-producing business loop | `reference.research.distribution-offer-signal` |
+| [Consumer Copy Benchmarks](../../../../knowledge/words/consumer-copy-benchmarks.md) | when any surface a user reads is authored or reviewed — landing, store listing, screenshot captions, paywall, onboarding, lifecycle email, share text — and when a new app's voice is established in COPY_BRIEF.md / BRAND.md (the Voice benchmarks section writes from this file's method) | `reference.words.consumer-copy-benchmarks` |
+| [No-Slop Writing](../../../../knowledge/words/no-slop-writing.md) | always for dispatched business workers — the voice and writing-quality bar applied to whatever other lanes produce, covering onboarding, store listing, landing, paywall, email, ads, launch-post wording, UGC scripts, GEO/SEO | `reference.words.no-slop-writing` |

package/agents/skills/b2c-research-opportunity/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: b2c-research-opportunity
+description: "Research whether a consumer-app idea is worth building. Compare demand, competitors, distribution, offer evidence, and product scope; recommend Go, Pivot, or Kill. Use for opportunity validation or delegated idea selection, not a narrow code fix or execution of an entire launch."
+compatibility: Markdown and supplied evidence. Provider-backed work needs the corresponding authorized tools. The B2C runtime is optional for focused advisory work.
+metadata:
+  source-workflow: "workflow.research.research-backed-spec"
+  generated-by: b2c-catalog
+---
+
+# Research an opportunity
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+## Choose the scope
+
+Use this task directly for focused advice, review, or an authorized change. Do not require setup, install software, create a workspace, or activate a full launch graph merely to use this expertise. A review is read-only unless the user also requests changes.
+
+For an existing managed business, read business-status then business-plan and use its current brief. This skill cannot choose executable next work, bypass prerequisites, change provider bindings, or replace runtime acceptance. Do not inspect raw reducer files merely to start a focused task.
+
+## Method
+
+For a review, assess the existing evidence against this method and return findings; do not execute its authoring or mutation instructions. For requested creation or implementation, follow the method only within the accepted scope and authority.
+
+## Continuous experience principle
+
+Carry the accepted user's intended outcome through the work: make the result meaningfully better for that user, preserve relevant identity, hierarchy, accessibility, and recovery constraints, and verify behavior as well as presence. Apply this only where relevant; a narrow fix stays narrow. This principle does not require an 11-star exercise or a numeric taste score.
+
+Before the spec hardens, ask the question a good idea and a good business both answer
+differently: **is this market big enough to be worth building in at all?** Pull top-competitor
+revenue estimates (AppKittie, sorted by revenue) and judge them against a stated bar.
+
+Default bar: the top 10 apps in the target category gross at least **$5M/year combined**, with
+at least **two independent apps each clearing $1M/year**. A category whose leaders gross too
+little cannot become a real business however well the launch executes — no amount of good
+onboarding, ASO, or paid UA fixes a market that is not there. Adjust the bar with the founder
+for a deliberate niche play, and record why the adjustment is legitimate rather than a way to
+pass a category that would otherwise fail.
+
+`check:research` reads the `## Category Revenue Reality` section's table, not the phrase in
+prose, and requires:
+
+- at least one competitor row with a real dollar estimate in the revenue column AND a dated
+  (`YYYY-MM-DD`), non-placeholder source in the source column — collecting the AppKittie data
+  is not the gate, the sourced number judged against the bar is
+- a "stated bar" line carrying an actual number, not a blank or placeholder
+- an explicit `pass or fail:` judgment line against that bar
+
+A pass verdict over no stated threshold, or a table with rows but no judgment line, is data
+collection wearing a gate's clothes.
+
+## Load only what the task needs
+
+[Task inputs, outputs, checks, and knowledge selectors](references/task.md) supplies the canonical details when they are needed. Open the specific referenced sections, not the whole library. In connected knowledge retrieval, follow exact section selectors, revision hashes, and continuation calls. Unresolved guidance remains unresolved.
+
+## Tools and evidence
+
+Keep the method independent of the agent host and business provider. Honor explicit selections. Use already available, authorized tools that implement the required operation; do not infer availability from the agent's name or silently substitute a provider. Load a provider's procedure only when its action is current. Record missing capabilities without inventing provider proof.
+
+Pause for access or secrets, spend, pricing or legal decisions, destructive changes, hosted deployment, store submission, or production release. Guidance is not permission. A proposed price is not an approved price, and a mock is not live evidence.
+
+## Return
+
+Report findings or changes, the evidence inspected, applicable checks actually run, unresolved requirements, and the next decision. Label advisory findings separately from accepted business evidence. Do not record business completion or modify reducer-owned state outside the supported runtime.

package/agents/skills/b2c-research-opportunity/references/task.md

@@ -0,0 +1,42 @@
+# Consumer app opportunity and product research
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+Canonical workflow: `workflow.research.research-backed-spec`. This is a reference contract, not an executable plan. Managed eligibility, ordering, authority, and acceptance remain with the installed business runtime.
+
+## Inputs and outputs
+
+For advisory work, use the evidence supplied and return findings. Do not create runtime state, prerequisite artifacts, or a whole business to satisfy these managed-workspace paths. Missing evidence remains explicit.
+
+Managed inputs: `product.yaml`
+
+Consult when relevant: None declared.
+
+Managed outputs: `strategy/RESEARCH.md`, `strategy/SIGNAL_CORPUS.md`, `strategy/OFFER_TEST.md`, `product.yaml`, `PRODUCT.md`
+
+## Verification and authority
+
+Declared checks: `check:research-workflow-output`
+
+Additional founder decisions: None specific to this workflow; host permission boundaries still apply.
+
+Run applicable checks with the installed builder's documented target arguments. Report unavailable or unrun checks honestly. A review report, generated file, or successful command does not by itself establish accepted runtime or provider evidence. Do not mark reducer state by hand.
+
+## Select supporting knowledge
+
+Load only the sections needed for the current task. Broad load-when wording does not override accepted scope or an explicit provider binding. Provider procedures are current only at the corresponding selected-provider action. Stop and report an unresolved required source rather than treating its title as delivered guidance.
+
+| Reference | Load when | Stable identity |
+| --- | --- | --- |
+| [Consumer Craft Benchmarks](../../../../knowledge/design/consumer-craft-benchmarks.md) | calibrating complete consumer-business mobile and landing craft against primary-source product examples before production and independent review | `reference.design.consumer-craft-benchmarks` |
+| [Design Worthiness](../../../../knowledge/design/design-worthiness.md) | when DESIGN.md authoring or its generated Design Room review needs the mechanical worthiness floor or its independent audit must record the delegated taste decision before engineering harden, including native flow semantics and mechanical anti-generic consistency, with no beauty score | `reference.design.design-worthiness` |
+| [iOS Consumer Playbook Intake](../../../../knowledge/growth/ios-consumer-playbook-intake.md) | before encoding an external iOS consumer-app playbook into paywall, onboarding, or paid-UA gates, including ToS-risky spend and social-proof tactics | `reference.growth.ios-consumer-playbook-intake` |
+| [Offer And Pricing Decisions](../../../../knowledge/money/offer-and-pricing-decisions.md) | research proposes an offer or monetization locks a production price; separate hypotheses, offer evidence, and exact founder authority | `reference.money.offer-and-pricing-decisions` |
+| [Artifact Contracts](../../../../knowledge/process/artifact-contracts.md) | writing docs, handoff bundles, or acceptance criteria | `reference.process.artifact-contracts` |
+| [Research Intelligence](../../../../knowledge/process/tool-recipes/research-intelligence.md) | delegating AppKittie store intelligence, XPOZ social-language, last30days recency briefs, Firecrawl web intelligence, Refero UX pattern research, or name/keyword collision checks — routed from tool-recipes.md; complements the Market research rows | `reference.process.tool-recipes.research-intelligence` |
+| [Core Loop And Complete Product Scope](../../../../knowledge/product/core-loop-and-complete-scope.md) | the product does not match one of the four shipped app archetypes (habit tracker, photo/AI media, social network, AI chat companion) — before naming the core loop, defining every required system in the accepted product, or specing schema for any other product shape | `reference.product.core-loop-and-complete-scope` |
+| [Product Moat](../../../../knowledge/product/product-moat.md) | before the spec or launch surfaces harden — the moat and defensibility test for what makes this app hard to copy; see eleven-star-experience.md for the 11-Star Run Protocol itself | `reference.product.product-moat` |
+| [Distribution-First Niche](../../../../knowledge/research/distribution-first-niche.md) | before Phase 2 build; when research must name a paying audience, one reachable channel, and purchases as validation | `reference.research.distribution-first-niche` |
+| [Distribution, Offer, And Signal Validation](../../../../knowledge/research/distribution-offer-signal.md) | before a Go, Pivot, or Kill decision; when founder posts, transcripts, reviews, interviews, support records, or prior launch material can inform the business; before automating a value-producing business loop | `reference.research.distribution-offer-signal` |
+| [Go, Pivot, Or Kill: The Pre-Build Research Verdict](../../../../knowledge/research/go-pivot-or-kill.md) | writing or updating strategy/RESEARCH.md's Category Revenue Reality or Go, Pivot, Or Kill sections; deciding whether a category and wedge earn a build before Phase 2 design/build spend | `reference.research.go-pivot-or-kill` |
+| [Transformation Demo](../../../../knowledge/research/transformation-demo.md) | before a consumer app Go verdict; when strategy/RESEARCH.md needs a one-screenshot 15s transformation demo that is not a vitamin feature | `reference.research.transformation-demo` |

package/agents/skills/b2c-review-business-performance/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: b2c-review-business-performance
+description: "Review supplied business performance evidence with honest period, cohort, denominator, and source limits. Recommend investigations without changing prices, spending money, or shipping an intervention."
+compatibility: Markdown and supplied evidence. Provider-backed work needs the corresponding authorized tools. The B2C runtime is optional for focused advisory work.
+metadata:
+  source-workflow: "workflow.operations.post-launch-operations"
+  generated-by: b2c-catalog
+---
+
+# Review business performance
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+## Choose the scope
+
+Use this task directly for focused advice, review, or an authorized change. Do not require setup, install software, create a workspace, or activate a full launch graph merely to use this expertise. A review is read-only unless the user also requests changes.
+
+For an existing managed business, read business-status then business-plan and use its current brief. This skill cannot choose executable next work, bypass prerequisites, change provider bindings, or replace runtime acceptance. Do not inspect raw reducer files merely to start a focused task.
+
+## Method
+
+For a review, assess the existing evidence against this method and return findings; do not execute its authoring or mutation instructions. For requested creation or implementation, follow the method only within the accepted scope and authority.
+
+## Continuous experience principle
+
+Carry the accepted user's intended outcome through the work: make the result meaningfully better for that user, preserve relevant identity, hierarchy, accessibility, and recovery constraints, and verify behavior as well as presence. Apply this only where relevant; a narrow fix stays narrow. This principle does not require an 11-star exercise or a numeric taste score.
+
+Load this reference when any of the following is true:
+
+- The project enters phase_6/phase_6b (post-launch growth and operations) or the first store approval lands on either store.
+- The founder asks "what now", "the app is live, what do I do", or any variant of "how do I run this".
+- A weekly ops session is due (the rhythm in §2 — the default standing session once live).
+- An incident is in progress: crash spike, review-bombing, billing outage, store policy notice, or a bad release.
+- An agent resumes work on an app that is already live (continuity review shows a shipped app but no `operations/POST_LAUNCH_OPS.md` — create it before doing anything else).
+
+If the app is live and `lanes.post_launch_ops` is still not_started, that is the highest-priority gap: a live business with no operating rhythm is the launch-and-vanish failure mode in progress.
+
+## Load only what the task needs
+
+[Task inputs, outputs, checks, and knowledge selectors](references/task.md) supplies the canonical details when they are needed. Open the specific referenced sections, not the whole library. In connected knowledge retrieval, follow exact section selectors, revision hashes, and continuation calls. Unresolved guidance remains unresolved.
+
+## Tools and evidence
+
+Keep the method independent of the agent host and business provider. Honor explicit selections. Use already available, authorized tools that implement the required operation; do not infer availability from the agent's name or silently substitute a provider. Load a provider's procedure only when its action is current. Record missing capabilities without inventing provider proof.
+
+Pause for access or secrets, spend, pricing or legal decisions, destructive changes, hosted deployment, store submission, or production release. Guidance is not permission. A proposed price is not an approved price, and a mock is not live evidence.
+
+## Return
+
+Report findings or changes, the evidence inspected, applicable checks actually run, unresolved requirements, and the next decision. Label advisory findings separately from accepted business evidence. Do not record business completion or modify reducer-owned state outside the supported runtime.

package/agents/skills/b2c-review-business-performance/references/task.md

@@ -0,0 +1,37 @@
+# Post-launch operations
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+Canonical workflow: `workflow.operations.post-launch-operations`. This is a reference contract, not an executable plan. Managed eligibility, ordering, authority, and acceptance remain with the installed business runtime.
+
+## Inputs and outputs
+
+For advisory work, use the evidence supplied and return findings. Do not create runtime state, prerequisite artifacts, or a whole business to satisfy these managed-workspace paths. Missing evidence remains explicit.
+
+Managed inputs: `state/business-state.json`, `operations/SUPPORT_OPS.md`, `operations/RETENTION_OPS.md`, `operations/FINANCE_OPS.md`
+
+Consult when relevant: `operations/POST_LAUNCH_OPS.md`, `operations/LAUNCH_RETRO.md`, `growth/PAID_UA.md`
+
+Managed outputs: `operations/POST_LAUNCH_OPS.md`, `operations/LAUNCH_RETRO.md`
+
+## Verification and authority
+
+Declared checks: `check:post-launch`
+
+Additional founder decisions: decide Kill, Hold, Fix, or Scale
+
+Run applicable checks with the installed builder's documented target arguments. Report unavailable or unrun checks honestly. A review report, generated file, or successful command does not by itself establish accepted runtime or provider evidence. Do not mark reducer state by hand.
+
+## Select supporting knowledge
+
+Load only the sections needed for the current task. Broad load-when wording does not override accepted scope or an explicit provider binding. Provider procedures are current only at the corresponding selected-provider action. Stop and report an unresolved required source rather than treating its title as delivered guidance.
+
+| Reference | Load when | Stable identity |
+| --- | --- | --- |
+| [Paid User Acquisition](../../../../knowledge/growth/paid-user-acquisition.md) | before paid ads, Apple Search Ads, Meta/TikTok/Google campaigns, custom product page campaign routing, MMP/ad-network SDK choices, paid creative tests, or spend-readiness claims | `reference.growth.paid-user-acquisition` |
+| [Billing Health And Reactivation](../../../../knowledge/money/billing-health-and-reactivation.md) | the purchase-events backend/analytics contract, involuntary billing-failure recovery, or reactivation and win-back after a purchase already happened — routed from revenue-monetization.md | `reference.money.billing-health-and-reactivation` |
+| [Post-Launch Operations](../../../../knowledge/operations/post-launch-operations.md) | once the app is live (phase_6/phase_6b); after first store approval; on "what now"; for weekly ops, incidents, review responses, retention and kill-or-scale reviews, or resuming a live app; when a second business exists | `reference.operations.post-launch-operations` |
+| [Change Cascade](../../../../knowledge/process/change-cascade.md) | after any change to a launched or near-launch app's features, copy, brand vocabulary, pricing, products, design, or data behavior | `reference.process.change-cascade` |
+| [Distribution, Offer, And Signal Validation](../../../../knowledge/research/distribution-offer-signal.md) | before a Go, Pivot, or Kill decision; when founder posts, transcripts, reviews, interviews, support records, or prior launch material can inform the business; before automating a value-producing business loop | `reference.research.distribution-offer-signal` |
+| [ASO Apple Keyword Evidence](../../../../knowledge/store/aso-apple-keyword-evidence.md) | before initial listing keywords and weekly post-launch ASO; when STORE_OPS.md needs official Apple rank, discover, and score evidence | `reference.store.aso-apple-keyword-evidence` |
+| [ASO Store Ops](../../../../knowledge/store/aso-store-ops.md) | before App Store/Play metadata, screenshot planning, ASO audits, keyword research, Apple Search Ads, release/rejection handling, ratings/reviews, or post-launch monitoring | `reference.store.aso-store-ops` |

package/agents/skills/b2c-review-experience/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: b2c-review-experience
+description: "Review an app experience against supplied product, interaction, accessibility, and evidence requirements. Return findings without fabricating device proof or accepting implementation."
+compatibility: Markdown and supplied evidence. Provider-backed work needs the corresponding authorized tools. The B2C runtime is optional for focused advisory work.
+metadata:
+  source-workflow: "workflow.experience.emotional-experience-design-producer"
+  generated-by: b2c-catalog
+---
+
+# Review the app experience
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+## Choose the scope
+
+Use this task directly for focused advice, review, or an authorized change. Do not require setup, install software, create a workspace, or activate a full launch graph merely to use this expertise. A review is read-only unless the user also requests changes.
+
+For an existing managed business, read business-status then business-plan and use its current brief. This skill cannot choose executable next work, bypass prerequisites, change provider bindings, or replace runtime acceptance. Do not inspect raw reducer files merely to start a focused task.
+
+## Method
+
+For a review, assess the existing evidence against this method and return findings; do not execute its authoring or mutation instructions. For requested creation or implementation, follow the method only within the accepted scope and authority.
+
+## Continuous experience principle
+
+Carry the accepted user's intended outcome through the work: make the result meaningfully better for that user, preserve relevant identity, hierarchy, accessibility, and recovery constraints, and verify behavior as well as presence. Apply this only where relevant; a narrow fix stays narrow. This principle does not require an 11-star exercise or a numeric taste score.
+
+Run this review per feature or per journey before build handoff. Each lens has an exact question, evidence to capture on a real device, and a sub-score (0–2). Total score: 0–12. The total is a discussion aid. It cannot establish readiness or override a material defect.
+
+These bands are canonical in [`emotional-design-system.md`](../../../knowledge/experience/emotional-design-system.md) §Emotional Review Framework. This file must not restate them differently.
+
+Use this framework as the operative tool for any UX or onboarding audit subagent. Each finding must reference its lens, its score change, and its star-ladder level per the UX And Onboarding Audit Output Contract in `eleven-star-experience.md`.
+
+---
+
+## Load only what the task needs
+
+[Task inputs, outputs, checks, and knowledge selectors](references/task.md) supplies the canonical details when they are needed. Open the specific referenced sections, not the whole library. In connected knowledge retrieval, follow exact section selectors, revision hashes, and continuation calls. Unresolved guidance remains unresolved.
+
+## Tools and evidence
+
+Keep the method independent of the agent host and business provider. Honor explicit selections. Use already available, authorized tools that implement the required operation; do not infer availability from the agent's name or silently substitute a provider. Load a provider's procedure only when its action is current. Record missing capabilities without inventing provider proof.
+
+Pause for access or secrets, spend, pricing or legal decisions, destructive changes, hosted deployment, store submission, or production release. Guidance is not permission. A proposed price is not an approved price, and a mock is not live evidence.
+
+## Return
+
+Report findings or changes, the evidence inspected, applicable checks actually run, unresolved requirements, and the next decision. Label advisory findings separately from accepted business evidence. Do not record business completion or modify reducer-owned state outside the supported runtime.

package/agents/skills/b2c-review-experience/references/task.md

@@ -0,0 +1,36 @@
+# Emotional experience design (producer)
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+Canonical workflow: `workflow.experience.emotional-experience-design-producer`. This is a reference contract, not an executable plan. Managed eligibility, ordering, authority, and acceptance remain with the installed business runtime.
+
+## Inputs and outputs
+
+For advisory work, use the evidence supplied and return findings. Do not create runtime state, prerequisite artifacts, or a whole business to satisfy these managed-workspace paths. Missing evidence remains explicit.
+
+Managed inputs: `product/experience/11-star-experience/11_STAR_EXPERIENCE.md`, `analytics/ANALYTICS.md`
+
+Consult when relevant: None declared.
+
+Managed outputs: `product/experience/emotional-design/EMOTIONAL_DESIGN.md`
+
+## Verification and authority
+
+Declared checks: `check:emotional-design`
+
+Additional founder decisions: None specific to this workflow; host permission boundaries still apply.
+
+Run applicable checks with the installed builder's documented target arguments. Report unavailable or unrun checks honestly. A review report, generated file, or successful command does not by itself establish accepted runtime or provider evidence. Do not mark reducer state by hand.
+
+## Select supporting knowledge
+
+Load only the sections needed for the current task. Broad load-when wording does not override accepted scope or an explicit provider binding. Provider procedures are current only at the corresponding selected-provider action. Stop and report an unresolved required source rather than treating its title as delivered guidance.
+
+| Reference | Load when | Stable identity |
+| --- | --- | --- |
+| [Design Evidence Stack](../../../../knowledge/design/design-evidence-stack.md) | before planning, creating, revising, auditing, or implementing any user-facing surface, component, interaction, onboarding flow, paywall, store frame, or marketing design; use it to classify the decision, select evidence sources, and record the evidence pass before mutation | `reference.design.design-evidence-stack` |
+| [Experience Cards](../../../../knowledge/experience/experience-cards.md) | selecting or auditing an engagement mechanic — the 12-card deck index: card shape contract, live-MCP access model, Card Routing table to every card in experience-cards/, and the Ethics Ladder attestation-block contract | `reference.experience.experience-cards` |
+| [Emotional Design System](../../../../knowledge/experience/emotional-design-system.md) | any product, onboarding, core-loop, paywall, or return-session work targeting 6-star ("better than expected") or higher; "charge this feature with emotion", "apply the <name> card", "emotional UX audit" — the methodology hub | `reference.experience.emotional-design-system` |
+| [Emotional Experience Design](../../../../knowledge/experience/emotional-experience-design.md) | implementing one of the four foundational Experience Cards (Commitment, Variable Reward, Perceived Effort Delay, Intent Mirroring) — full psychological basis, trigger timing, deterministic guardrail tests, named PostHog events, and the Six-Lens Design Review Framework in full | `reference.experience.emotional-experience-design` |
+| [Emotional Experience Measurement](../../../../knowledge/experience/emotional-experience-measurement.md) | instrumenting an emotional-design or Experience Card feature — system-level events/metrics, per-card PostHog events, leading behavioral metrics, dark-pattern counter-metrics, and A/B experiment design (measurement only; see emotional-design-system.md for the psychology) | `reference.experience.emotional-experience-measurement` |
+| [Ethics Guardrail](../../../../knowledge/experience/ethics-guardrail.md) | a HIGH-risk Experience Card (variable reward, streak, scarcity, urgency, social proof) is in play, or before any regulatory/platform-compliance claim about an engagement mechanic — Bright-Line/Dark-Line test, FTC/EU DSA/Apple/Google Play/COPPA landscape, the guardrail attestation-block contract consumed by check:emotional-design | `reference.experience.ethics-guardrail` |

package/agents/skills/b2c-review-monetization/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: b2c-review-monetization
+description: "Review a consumer app's offer, pricing proposal, paywall, purchases, entitlements, restore behavior, and billing evidence. Use for a monetization audit or explicitly requested implementation. A review does not authorize live product changes, pricing changes, payments, or provider selection."
+compatibility: Markdown and supplied evidence. Provider-backed work needs the corresponding authorized tools. The B2C runtime is optional for focused advisory work.
+metadata:
+  source-workflow: "workflow.money.revenue-monetization"
+  generated-by: b2c-catalog
+---
+
+# Review monetization
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+## Choose the scope
+
+Use this task directly for focused advice, review, or an authorized change. Do not require setup, install software, create a workspace, or activate a full launch graph merely to use this expertise. A review is read-only unless the user also requests changes.
+
+For an existing managed business, read business-status then business-plan and use its current brief. This skill cannot choose executable next work, bypass prerequisites, change provider bindings, or replace runtime acceptance. Do not inspect raw reducer files merely to start a focused task.
+
+## Method
+
+For a review, assess the existing evidence against this method and return findings; do not execute its authoring or mutation instructions. For requested creation or implementation, follow the method only within the accepted scope and authority.
+
+## Continuous experience principle
+
+Carry the accepted user's intended outcome through the work: make the result meaningfully better for that user, preserve relevant identity, hierarchy, accessibility, and recovery constraints, and verify behavior as well as presence. Apply this only where relevant; a narrow fix stays narrow. This principle does not require an 11-star exercise or a numeric taste score.
+
+Choose the smallest reliable monetization path for the current phase:
+
+- **Pre-build validation**: waitlist, pricing page, preorder interest, or non-charging web funnel. Do not imply paid access is active.
+- **Mobile-only app subscription**: App Store/Google Play products, RevenueCat products/entitlements/offerings, in-app paywall, restore purchases, sandbox testing, store submission.
+- **Web-to-app acquisition**: RevenueCat Web Billing or Stripe Billing through RevenueCat Web, Web Purchase Links or Web Funnels, Redemption Links, deep-link redemption, app entitlement validation.
+- **Existing Stripe web business**: Stripe Billing remains billing engine, RevenueCat imports/syncs entitlements, Stripe webhooks and customer portal stay authoritative for billing management.
+- **Direct Stripe without RevenueCat**: only use when the app does not need mobile store entitlements or cross-platform entitlement sync. For digital goods unlocked inside iOS/Android apps, review Apple/Google rules first.
+
+Default for B2C mobile subscriptions: RevenueCat owns entitlements and cross-platform subscription state. Stripe may be the web payment rail or billing engine, but a successful Stripe payment is not launch-ready until it unlocks the correct RevenueCat entitlement in the app.
+
+## Load only what the task needs
+
+[Task inputs, outputs, checks, and knowledge selectors](references/task.md) supplies the canonical details when they are needed. Open the specific referenced sections, not the whole library. In connected knowledge retrieval, follow exact section selectors, revision hashes, and continuation calls. Unresolved guidance remains unresolved.
+
+## Tools and evidence
+
+Keep the method independent of the agent host and business provider. Honor explicit selections. Use already available, authorized tools that implement the required operation; do not infer availability from the agent's name or silently substitute a provider. Load a provider's procedure only when its action is current. Record missing capabilities without inventing provider proof.
+
+Pause for access or secrets, spend, pricing or legal decisions, destructive changes, hosted deployment, store submission, or production release. Guidance is not permission. A proposed price is not an approved price, and a mock is not live evidence.
+
+## Return
+
+Report findings or changes, the evidence inspected, applicable checks actually run, unresolved requirements, and the next decision. Label advisory findings separately from accepted business evidence. Do not record business completion or modify reducer-owned state outside the supported runtime.

package/agents/skills/b2c-review-monetization/references/task.md

@@ -0,0 +1,40 @@
+# Revenue monetization
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+Canonical workflow: `workflow.money.revenue-monetization`. This is a reference contract, not an executable plan. Managed eligibility, ordering, authority, and acceptance remain with the installed business runtime.
+
+## Inputs and outputs
+
+For advisory work, use the evidence supplied and return findings. Do not create runtime state, prerequisite artifacts, or a whole business to satisfy these managed-workspace paths. Missing evidence remains explicit.
+
+Managed inputs: `state/LAUNCH_TRACE.md`, `strategy/RESEARCH.md`, `strategy/OFFER_TEST.md`, `state/business-state.json`
+
+Consult when relevant: None declared.
+
+Managed outputs: `revenue/REVENUE_OPS.md`
+
+## Verification and authority
+
+Declared checks: `check:revenue`, `check:price-derivation`
+
+Additional founder decisions: approve pricing and product catalog
+
+Run applicable checks with the installed builder's documented target arguments. Report unavailable or unrun checks honestly. A review report, generated file, or successful command does not by itself establish accepted runtime or provider evidence. Do not mark reducer state by hand.
+
+## Select supporting knowledge
+
+Load only the sections needed for the current task. Broad load-when wording does not override accepted scope or an explicit provider binding. Provider procedures are current only at the corresponding selected-provider action. Stop and report an unresolved required source rather than treating its title as delivered guidance.
+
+| Reference | Load when | Stable identity |
+| --- | --- | --- |
+| [Billing Health And Reactivation](../../../../knowledge/money/billing-health-and-reactivation.md) | the purchase-events backend/analytics contract, involuntary billing-failure recovery, or reactivation and win-back after a purchase already happened — routed from revenue-monetization.md | `reference.money.billing-health-and-reactivation` |
+| [Offer And Pricing Decisions](../../../../knowledge/money/offer-and-pricing-decisions.md) | research proposes an offer or monetization locks a production price; separate hypotheses, offer evidence, and exact founder authority | `reference.money.offer-and-pricing-decisions` |
+| [Paywall, Pricing, And Experiments](../../../../knowledge/money/paywall-pricing-and-experiments.md) | paywall timing/placement/trials/offers, pricing disclosure, price-point procedure, standing experiment cadence, or RevenueCat Experiments vs bandit vs PostHog engine choice — routed from revenue-monetization.md | `reference.money.paywall-pricing-and-experiments` |
+| [Revenue Monetization](../../../../knowledge/money/revenue-monetization.md) | before RevenueCat, Stripe, app-store products, web billing, web purchase links, funnels, paywalls, subscriptions, webhooks, taxes, pricing, restore purchases, or entitlements — the Decision Matrix, Founder-Only Gates, and anti-pattern digest hub; see revenuecat-and-store-products.md, stripe-and-web-billing.md, paywall-pricing-and-experiments.md, and billing-health-and-reactivation.md for setup and procedure detail | `reference.money.revenue-monetization` |
+| [RevenueCat Agent Tooling](../../../../knowledge/money/revenuecat-agent-tooling.md) | when the selected RevenueCat operation needs official agent setup, identity, instrumentation, or verification procedures | `reference.money.revenuecat-agent-tooling` |
+| [RevenueCat And Store Products](../../../../knowledge/money/revenuecat-and-store-products.md) | RevenueCat project/product/entitlement/offering setup, App Store or Play product gates, MISSING_METADATA or RevenueCat product-type reconciliation, paywall smoke proof, or promotional IAP/subscription art — routed from revenue-monetization.md | `reference.money.revenuecat-and-store-products` |
+| [Stripe And Web Billing](../../../../knowledge/money/stripe-and-web-billing.md) | Stripe account/checkout/webhook/customer-portal setup, or RevenueCat Web Billing, Web Purchase Links, Web Funnels, Web SDK, or Redemption Links — routed from revenue-monetization.md | `reference.money.stripe-and-web-billing` |
+| [Subscription Price Derivation](../../../../knowledge/money/subscription-price-derivation.md) | before deriving subscription territory prices from another plan; when PRICE_DERIVATION.md needs dry-run, founder apply, and provider readback | `reference.money.subscription-price-derivation` |
+| [Consumer Copy Benchmarks](../../../../knowledge/words/consumer-copy-benchmarks.md) | when any surface a user reads is authored or reviewed — landing, store listing, screenshot captions, paywall, onboarding, lifecycle email, share text — and when a new app's voice is established in COPY_BRIEF.md / BRAND.md (the Voice benchmarks section writes from this file's method) | `reference.words.consumer-copy-benchmarks` |
+| [Conversion Copy](../../../../knowledge/words/conversion-copy.md) | before writing any words a user reads: conversion copy (hero/CTA, store, paywall) and every in-app string (buttons, empty states, errors, settings); and l10n readiness | `reference.words.conversion-copy` |

package/agents/skills/b2c-verify-release-readiness/SKILL.md

@@ -0,0 +1,47 @@
+---
+name: b2c-verify-release-readiness
+description: "Inspect target-specific release evidence and report supported, missing, stale, blocked, or inapplicable requirements. Inspection cannot certify acceptance or perform a release."
+compatibility: Markdown and supplied evidence. Provider-backed work needs the corresponding authorized tools. The B2C runtime is optional for focused advisory work.
+metadata:
+  source-workflow: "workflow.orchestration.full-launch-closeout"
+  generated-by: b2c-catalog
+---
+
+# Verify release readiness
+
+<!-- Generated task skill. Edit catalog owners, then run render:task-skills. -->
+
+## Choose the scope
+
+Use this task directly for focused advice, review, or an authorized change. Do not require setup, install software, create a workspace, or activate a full launch graph merely to use this expertise. A review is read-only unless the user also requests changes.
+
+For an existing managed business, read business-status then business-plan and use its current brief. This skill cannot choose executable next work, bypass prerequisites, change provider bindings, or replace runtime acceptance. Do not inspect raw reducer files merely to start a focused task.
+
+## Method
+
+For a review, assess the existing evidence against this method and return findings; do not execute its authoring or mutation instructions. For requested creation or implementation, follow the method only within the accepted scope and authority.
+
+## Continuous experience principle
+
+Carry the accepted user's intended outcome through the work: make the result meaningfully better for that user, preserve relevant identity, hierarchy, accessibility, and recovery constraints, and verify behavior as well as presence. Apply this only where relevant; a narrow fix stays narrow. This principle does not require an 11-star exercise or a numeric taste score.
+
+- Coverage Matrix
+- Must-Have For Any Real Launch
+- Optional But High-Leverage
+- Common Missing Pieces
+- Handoff Completeness Checklist
+- Audit Output
+
+## Load only what the task needs
+
+[Task inputs, outputs, checks, and knowledge selectors](references/task.md) supplies the canonical details when they are needed. Open the specific referenced sections, not the whole library. In connected knowledge retrieval, follow exact section selectors, revision hashes, and continuation calls. Unresolved guidance remains unresolved.
+
+## Tools and evidence
+
+Keep the method independent of the agent host and business provider. Honor explicit selections. Use already available, authorized tools that implement the required operation; do not infer availability from the agent's name or silently substitute a provider. Load a provider's procedure only when its action is current. Record missing capabilities without inventing provider proof.
+
+Pause for access or secrets, spend, pricing or legal decisions, destructive changes, hosted deployment, store submission, or production release. Guidance is not permission. A proposed price is not an approved price, and a mock is not live evidence.
+
+## Return
+
+Report findings or changes, the evidence inspected, applicable checks actually run, unresolved requirements, and the next decision. Label advisory findings separately from accepted business evidence. Do not record business completion or modify reducer-owned state outside the supported runtime.