Marketing & Growth Workflows

Designs technical blueprints — tech stack selection, database schema, API design, file structure, and deployment plan for a defined product or feature. Produces architecture/system-architecture.md. Not for unclear requirements (use discover) or task decomposition (use breakdown-tasks). For user journey mapping, see map-user-flow. For code quality after building, see review-work.

Decomposes a spec or architecture into buildable tasks with acceptance criteria, dependencies, and risk-first implementation order, for AI agents or human engineers. Produces docs/forsvn/artifacts/meta/tasks.md. Use once requirements are clear and you need an execution plan. Not for clarifying unclear requirements (use discover) or designing architecture (use architect-system). For code review after building, see review-work.

Produces production-ready briefs for app onboarding, App Store preview, and feature-demo videos from supplied UI screenshots. Defines the feature promise, cropped UI beats, interaction choreography, captions, motion rules, platform specs, and asset manifest. Use when screenshots exist and the goal is to show a product feature in action. Not for generic short-form social videos (use brief-shortform) or rendering the video (use produce-video).

Produce a graphic-design brief for a single visual asset — social posts, thumbnails, banners, OOH, OG cards, hero illustrations. Pulls brand tokens, generates concepts, writes platform-aware specs + image-gen prompt or designer-handoff spec. Does NOT render — rendering is downstream. Not for brand identity (use create-brand), whole-page redesigns (use brief-landing-page), or the copy that goes IN the asset (use write-copy).

Generates a campaign-grade brief for a conversion landing page or redesign — hypothesis, surface rhythm, section-by-section spec, asset slots, copy candidates, hand-off prompts, conversion + brand-voice critics. Output ready for Claude Design, Figma, a human designer, or a coding agent. Not for post-launch CRO from analytics (use evaluate-landing-page inside an eval-loop), non-conversion pages (blogs, docs), or a single visual asset (use brief-graphic).

Designs the in-product interface from a validated map-user-flow — screen inventory, a reusable component system, DESIGN-token application, per-state visual treatments, accessibility floor, and a buildable handoff. Emits a portable SPEC, never rendered UI. Use after a user flow exists and before architect-system. Not for brand identity (create-brand), conversion landing pages (brief-landing-page), or technical architecture (architect-system).

Production-ready brief for short-form video — hook, shot list, on-screen text, audio plan, caption, CTA, aspect, length. Covers live-action + motion-graphic. 1 hero + 2 variants per run. Reads the per-platform research-shortform catalog. Not for static visual assets (use brief-graphic), organic social copy (use write-social), paid ad creative (use write-ad), or rendering (use produce-video).

Build, sign, install, and publish iOS apps using the Vibecode signing service. Use when the user wants to build an iOS app from source, sign an iOS app, install on their iPhone, register a device, set up Apple Developer auth, publish to the App Store or TestFlight, submit for review, or work with the iOS build/sign/distribute/publish pipeline. Also triggers for "test on device", "put this on my phone", "ship it to my iPhone", "publish to App Store", "submit my app", "push to TestFlight", "send for review", or any request to get a Swift/iOS app running on a real device or shipped to App Store Connect.

Audit + groom docs/forsvn/artifacts/ — classify every file (KEEP/STALE/ORPHAN/LEGACY/EPHEMERAL), surface references + risk. On --apply archives candidates behind per-category confirmation (moves to dated archive, never deletes). Not for cleaning code (use clean-code) or machine state (use clean-machine).

Audit + clean a developer's machine — dotfolders, caches, language toolchains, package globals — with per-target classification, risk surfacing (auth, processes, side effects), and explicit confirmation. Produces docs/forsvn/artifacts/meta/records/machine-cleanup-.md. Not for cleaning code (use clean-code) or for triaging user files (those need human review).

Builds a brand identity system as up to five artifacts — BRAND.md (story, voice, archetype), DESIGN.md (design tokens), CREATIVE-DIRECTION.md (art direction), FRAME.md (frame direction for the camera), ASSETS.md (per-platform inventory). Runs Quick Brand (Route A) or full brand-system (Route B). Use to define or rebrand a product's identity. Not for marketing copy (use write-copy), user flows (use map-user-flow), campaign planning (use plan-campaign), or audience research (use research-icp).

Runs a problem through multiple expert perspectives via debate (agents argue in rounds and converge) or poll (agents analyze independently, then aggregate by consensus). Use to pressure-test a decision or trade-off with no clear winner. Standalone, or invoked by another skill as a sub-routine. Not for implementation (use architect-system) or code verification (use review-work).

Designs lifecycle / email-automation flows — onboarding, activation, winback, churn-save — as multi-step trigger, message, timing, and branch maps anchored to an activation metric, with suppression rules and a quantitative critic gate. Use for retention email/notification automation against a real list + product. Not for one-off broadcast copy (use write-copy), cold outreach (use write-outreach), organic social (use write-social), or paid-ad creative (use write-ad).

Design a marketing mini-game / interactive — spin-the-wheel, quiz, scratch-card, playable ad, advent-calendar — for engagement, lead capture, or virality. Produces a game-design spec: the mechanic + win condition, the reward economics, the data-capture value exchange, and the conversion funnel. Honest by construction (no fake-win dark patterns). Not for building the game's code (that's an engineering task), nor a static ad/asset (use write-ad / brief-graphic / produce-asset).

Designs referral / viral loops — loop mechanics, K-factor + cycle-time math, incentive economics (CAC-bounded), and a falsifiable trigger — with a quantitative critic gate. Use when a product with retention wants a referral or word-of-mouth loop. Not for paid-ad creative (use write-ad), channel-mix strategy (use plan-campaign), lifecycle email flows (use design-lifecycle), or affiliate/partnership outreach (use write-outreach).

Score a launched paid ad (Meta, Google, TikTok, LinkedIn) from real metrics — network-specific primary metric + diagnosis + fatigue/auction signals — inside an existing eval loop. One cycle per network. Not for loop setup (use run-pipeline), writing new creative (use write-ad), channel-mix retrospectives (use plan-campaign), or campaign-level scoring (use evaluate-campaign).

Score a produced visual asset (image / graphic / carousel frame) against its brief — render fidelity + brand-fit — inside an existing eval loop, using the re-ingested asset (the return-leg). One asset (or picked variant) per cycle, verdict + brief-fidelity diagnosis. Not for video (use evaluate-shortform), a landing page (use evaluate-landing-page), live-post engagement (use evaluate-content / evaluate-ad), generating the asset (use produce-asset), or scaffolding the loop (use run-pipeline).

Score a launched multi-channel campaign from real metrics inside an existing eval loop — verdict, per-channel breakdown, unit economics. Aggregate-only: one cycle = whole campaign, all channels. Requires an eval-loop workspace. Not for loop setup (use run-pipeline), re-planning (use plan-campaign), or per-asset eval — single ad uses evaluate-ad, post evaluate-content, page evaluate-landing-page, short-form evaluate-shortform.

Score a published organic post (text / image / carousel) from real metrics inside an existing eval loop — one primary platform per cycle, verdict + engagement-quality diagnosis. Not for short-form video (use evaluate-shortform), paid-ad performance (use evaluate-ad), writing next-cycle copy (use write-social), or scaffolding the loop (use run-pipeline).

Scores a launched landing page from real performance evidence inside an existing eval loop — writes a cycle eval snapshot and appends the loop results ledger. Use for post-launch CRO cycles backed by analytics, experiment results, recordings, form-funnel data, or qualified manual metric notes. Not for designing the next page brief or a redesign (use brief-landing-page), channel strategy (use plan-campaign), best-practice audits without evidence, or scaffolding the loop (use run-pipeline).

Score a sent outreach cycle (cold email / LinkedIn DM / sequence) from real reply data inside an existing eval loop — one channel + segment per cycle, verdict + reply-quality diagnosis with a deliverability + compliance gate. Not for writing the outreach (use write-outreach), organic-post performance (use evaluate-content), paid-ad performance (use evaluate-ad), or scaffolding the loop (use run-pipeline).

Score an SEO / AEO cycle from real ranking + visibility data inside an existing eval loop — one keyword cluster + surface (organic SERP or AI answers) per cycle, verdict + visibility-delta diagnosis with a lag-and-volatility gate that refuses short-window noise. Not for running the audit/fixes (use optimize-seo), tracking AI citations (use monitor-aeo), organic-post performance (use evaluate-content), or scaffolding the loop (use run-pipeline).

Closes the feedback loop for short-form video — scores a published post against its original brief and the matching short-form platform-intelligence catalog on a 4-dimension rubric, then logs a falsifiable pattern entry to the eval loop. Use to review a post after publishing or run an eval cycle in an existing loop. Not for pre-publish brief authoring (use brief-shortform) or catalog discovery (use research-shortform); needs a loop workspace (see run-pipeline).

Produce a minute-by-minute run-of-show (cue sheet) for a live marketing event — webinar, launch event, AMA, demo day, product reveal, conference talk. Segments + timing + owners + technical cues + contingencies. Not for the campaign around the event (use plan-campaign), the launch-day social sequence (use the launch chain / publish-social), or a recorded video (use brief-shortform/produce-video).