Marketing & Growth Workflows

Use when adversarially reviewing a document that makes formal or technical claims — math derivations, physics papers, statistical analyses, benchmark reports, whitepapers. Inventories every equation and quantitative claim, verifies each AS NAMED in the text (never a paraphrase or a neighboring statement), and classifies VERIFIED / REFUTED / UNVERIFIABLE / VACUOUS. Triggers on "check this paper", "verify these claims", "is this derivation right", "review this proof", "audit this benchmark", "does the math hold up". For source-code review see code-review-and-quality; for skill/agent library audits see skill-library-review; for content quality scoring see content-ops.

Use to draft a blog post from a filled blog-post-shaper brief — opinion, case study, or deep dive — and emit per-task files for the asset bundle (hero image, OG card, social posts, embedded diagrams, code samples, internal-link map, newsletter excerpt) so the calling agent can fan them out to subagents. Triggers on "write the blog post", "draft this post", "expand the blog brief", "author the post", or when handed a filled blog brief from blog-post-shaper. Writes one post against the brief and one file per asset task; does not reopen scope decisions. For intake shaping see blog-post-shaper. For a standalone LinkedIn/X promo post see social-growth; for other non-blog content (threads, decks, newsletters) see marketing-shaper. For courses see course-author.

Use to structure a vague blog-post idea into a well-scoped brief before any drafting begins. Triggers on "blog post on X", "write a blog about", "long-form post", "case study post", "explainer post", "opinion piece", "thought leadership post", or when invoked as the /blog-shape slash command. Produces a filled blog brief (opinion, case-study, or deep-dive) that blog-post-author consumes — the author then writes the post and emits one task file per declared asset (hero image, OG card, social posts, embedded diagrams, code samples, internal-link map, newsletter excerpt) that the parent agent dispatches to subagents. Do not use for short social-format posts (X, LinkedIn) — go to marketing-shaper's content brief or x-longform-post. For engineering intake see prompt-shaper; for course intake see course-shaper; for game-design intake see game-design-shaper.

Cloud platforms (AWS, Cloudflare, GCP, Azure), containerization (Docker), Kubernetes, Infrastructure as Code (Terraform), CI/CD, and observability.

Estimate the full development cost of an existing codebase from lines of code, architectural complexity, and team-composition overhead. Use for 'how much would this cost to build', 'what did this codebase cost', development-cost or build-cost estimates, calendar-time estimates, and Claude/AI ROI on a delivered codebase. Estimates by measured LOC and complexity, not by ticket volume. For financial reporting from accounting exports (CFO briefings, burn rate, runway) see finance-ops.

Design, analyze, and optimize cold outbound email campaigns for Instantly. Handles end-to-end ICP definition, expert panel scoring (recursive to 90+), sequence copywriting, infrastructure audit, capacity planning, and implementation docs. Use when asked to build cold outbound sequences, optimize cold email, analyze outbound campaigns, build sales sequences, build Instantly sequences, create cold outbound strategies, or design email campaigns. Supports both "start from scratch" and "optimize existing" modes.

Auto-assembles a domain-specific expert panel (7–10 experts), scores any content or strategy artifact against a typed rubric, and iterates until the aggregate hits 90+ (max 3 rounds). Use as a quality gate on copy, email sequences, landing-page drafts, strategy docs, charts, titles, or recruiting evaluations — or when another skill needs a final review gate on its output. Triggers on "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "expert score", "evaluate this copy/strategy/page".

AI-powered conversion rate optimization: landing page audits, CRO scoring, survey segmentation, and lead magnet generation. Use when asked to audit a landing page, run a CRO analysis, segment survey responses, or generate lead magnets. For content quality scoring see content-ops.

Use to write lesson content from a filled lesson spec — hook, explanation, worked example with code snippets, exercises, misconception callouts, and formative check. Triggers on "write the lesson", "draft lesson", "author lesson", "expand the spec", "write course content", "add the code snippets", or when handed a filled lesson-spec-template from course-design. Writes one lesson at a time against the spec; does not reopen curriculum decisions. For course outlining see course-design; for intake shaping see course-shaper.

Use to turn a course brief into a concrete outline — modules, lessons, learning objectives, sequencing, and assessment map — before any lesson content is written. Triggers on "design the course", "build the curriculum", "outline the course", "course outline", "module breakdown", "lesson plan", "learning objectives", or when handed a filled course brief from course-shaper. Produces a course outline + per-lesson specs that course-author consumes. For intake shaping see course-shaper; for writing the lessons themselves see course-author.

Use to structure a vague course idea into a well-scoped course brief before any outlining or writing begins. Triggers on "design a course", "course on X", "teach X", "curriculum for", "workshop on", "training material", "learning path", or when invoked as the /course-shape slash command. Produces a filled course brief (full-course, single-module, or workshop) that course-design and course-author consume. Do not use for briefs that are already well-scoped. For engineering task shaping see prompt-shaper; for marketing briefs see marketing-shaper; for game-design intake see game-design-shaper.

Generate professional presentations with AI-generated images. Use when asked to create a deck, presentation, pitch deck, or slides. Supports style presets (whiteboard, corporate, minimalist, etc). Uses Imagen 4.0 API for image generation and Google Slides API for assembly. Produces full decks from markdown content specs in minutes.

Use when authoring or reviewing CI/CD pipelines — GitHub Actions workflows, reusable workflows, composite actions, OIDC federation to AWS/GCP, caching, artifacts, and pipeline security hardening. Triggers on edits to .github/workflows/, action.yml, composite action definitions, or mentions of "CI", "CD", "pipeline", "GitHub Actions", "workflow", "OIDC", "runner", "deploy script", "release", or "build pipeline". For provisioning the cloud resources these pipelines deploy to, see cloud-infrastructure.

Run CFO briefings from QuickBooks/CSV accounting exports: financial reporting, profitability and people-cost breakdowns, burn-rate and runway analysis, and base/bull/bear scenario modeling. Use for an executive financial briefing, expense/vendor review, or cash-runway analysis from accounting data. For estimating the development cost of a codebase (LOC-based build cost) see codebase-cost-estimator.

Use when recording, tallying, or triaging stochastic review findings — the append-only JSONL ledger where Tier 2 (advisory, unevidenced) reviewer output goes instead of blocking language. Triggers on "log this finding", "ledger add", "tally the findings", "triage findings", "is this finding recurring", "retire this noise", or whenever a reviewer produces an unevidenced concern that should be measured for recurrence rather than chased. For the review itself see code-review-and-quality or skill-library-review; for verifying formal claims with deterministic evidence see adversarial-claims-reviewer.

Use when tuning the numbers in a game — economy curves, progression rates, difficulty pacing, drop tables, win/loss probabilities, time-to-X targets, currency velocities, and balance pass plans. Triggers on "balance pass", "tune the economy", "progression curve", "difficulty curve", "drop rate", "XP curve", "TTK", "time-to-content", "balance the economy", "spreadsheet model", "economy sim", or when handed a system spec from game-systems-designer with placeholders. Produces an economy spreadsheet, a balance pass plan, simulation outputs, and per-system balance tables. Stops at the numbers — does not change system rules (that's game-systems-designer) or pricing (that's game-monetization-strategist / iap-manager). For systems design see game-systems-designer; for monetization model see game-monetization-strategist; for store catalog see iap-manager.

Use to generate, evaluate, and refine pitch-quality game concepts — theme × mechanic × audience combinations expressed as one-pagers. Triggers on "game concept", "concept pitch", "ideate a game", "what game should we make", "concept one-pager", "elevator pitch for a game", "remix this concept", or when handed a filled brief from game-design-shaper with the concept still open. Produces a concept one-pager (logline, fantasy, hook, target player, 3 verbs, payment rails, comparable titles, risks) that game-systems-designer consumes. Stops at the pitch — does not design systems, balance, or write design docs. For systems design see game-systems-designer; for intake shaping see game-design-shaper; for generic ideation see idea-refine.

Use to structure a vague game idea into a well-scoped game design brief before any concept, systems, balance, monetization, or marketing work begins. Triggers on "design a game", "game on X", "game idea", "prototype this", "game jam", "live game update", "game design plan", or when invoked as the /game-shape slash command. Produces a filled brief (full game, prototype, jam, or live-game update) that game-concept-creator and game-systems-designer consume. Do not use for briefs that are already well-scoped — go straight to the right execution skill. For engineering intake see prompt-shaper; for marketing intake see marketing-shaper; for course intake see course-shaper.

Use when marketing a game — store-page conversion (App Store / Google Play / Steam), trailers and hooks, soft-launch CPI / ROAS, creator / influencer / community programs, wishlist campaigns, launch and live-ops comms, web3 mint comms. Triggers on "store page", "Steam page", "trailer", "gameplay hook", "soft launch", "wishlist", "Discord community", "TikTok / YouTube Shorts", "creator program", "patch notes", "launch comms", or when handed a brief / strategy / catalog from the game pipeline. Produces store-page specs, trailer briefs, soft-launch creative plans, community programs, comms drafts. For non-game marketing see marketing-shaper; for marketing intake see marketing-shaper; for catalog comms see iap-manager; for KPI floors see game-monetization-strategist.

Use when picking and shaping the monetization model of a game — premium / F2P / subscription / ad-supported / hybrid / web3 — including LTV / ARPDAU / ROAS targets, retention-to-monetization mapping, soft-launch KPI floors, and the macro economy. Triggers on "monetization model", "monetization strategy", "F2P vs premium", "LTV", "ARPDAU", "ROAS", "soft launch KPIs", "battle pass", "subscription model", "web3 token economy", or a design doc with the model still open. Produces a monetization strategy doc, KPI floors, and macro economy spec. Stops at strategy — does not set per-SKU prices (iap-manager) or tune economy numbers (game-balancer). For per-SKU catalog see iap-manager; for economy curves see game-balancer; for CPI see game-marketer.

Use when designing the systems of a game from a locked concept — core loops, meta loops, player verbs, progression, content systems, level structure, and narrative integration. Triggers on "game design doc", "GDD", "system spec", "core loop design", "progression design", "level design", "MDA", "design the systems", or when handed a one-pager from game-concept-creator. Produces a design doc plus per-system specs that game-balancer numbers, game-monetization-strategist prices, iap-manager stocks, and godot-engineer (or another engine team) builds. Stops at the design — does not tune numbers, set prices, or write engine code. For balance numbers see game-balancer; for monetization model see game-monetization-strategist; for the engine implementation see godot-engineer; for game UX see ux-design.

Use when building games or interactive software in Godot 4 with C — designing scenes and nodes, writing gameplay code, handling input, physics, animation, UI, rendering, save systems, performance work, WebSocket-based multiplayer, or exporting to platforms. Triggers on "Godot", "GDScript", "C Godot", "scene tree", Godot node types (Node2D, Node3D, Control, CharacterBody), "Process", "PhysicsProcess", "signal", "autoload", "RPC", "WebSocketMultiplayerPeer", "shader", "export preset", or any Godot 4 project files. For game design see game-systems-designer; for balance see game-balancer; for monetization see game-monetization-strategist; for marketing see game-marketer; for game-specific intake see game-design-shaper. For broader software design principles see software-design.

Use when designing and operating the in-app purchase catalog of a game — SKU design, price-tier ladder, bundles, starter packs, battle pass tiering, A/B price tests, store config (App Store / Google Play / Steam DLC / web / web3), and per-region price localization. Triggers on "IAP catalog", "store SKUs", "pricing tiers", "starter pack", "bundle design", "battle pass tiering", "price test", "price localization", "App Store Connect", "Google Play Console", "Steam DLC", or when handed a monetization strategy with the catalog still open. Produces a catalog spec, per-region price tables, bundle compositions, and a price-test plan. For the macro model and KPI floors see game-monetization-strategist; for in-game economy curves see game-balancer; for store-page conversion and trailers see game-marketer.

Use when deciding and validating WHO the right customer is from market and sales evidence — refining the Ideal Customer Profile (firmographic and behavioral fit), running win-loss analysis on closed deals, validating or invalidating a segment, diagnosing an ICP that is too broad, and turning win-loss findings into sharper targeting and disqualification criteria. Triggers on "ICP", "ideal customer profile", "win-loss analysis", "why we won/lost", "which segment", "who should we sell to", "is this segment real", "disqualification criteria", "segment validation", or "our ICP is too broad". For studying the user's experience, personas, or JTBD see ux-research; for running growth experiments on a known ICP see growth-engine; for mining sales-call transcripts see revenue-intelligence.