By RBraga01
AI growth quality enforcement: 14 skills and 5 agents for growth teams
Use before any AI product messaging ships externally. Audits capability claims for accuracy, quantified claims for evidence, and "AI" labels for specificity. Blocks "10x productivity" without measurement and "AI-powered" without definition.
Use before any campaign moves from strategy to execution. Transforms a growth strategy and offer into an executable brief — campaign objective, audience, offer, message, channel, creative requirements, landing destination, CTA, success metric, review gates, and launch checklist. Blocks "the team knows what we're going for" completions.
Use before building any campaign, content plan, or outbound motion. Scores every candidate growth channel against eight criteria — audience presence, intent, cost to test, feedback speed, trust requirement, sales cycle fit, operational complexity, and measurement feasibility — before one is chosen. Blocks "let's try everything" and "we picked the channel everyone else uses" completions.
Use before any external-facing copy ships. Applies three tests — "so what?", "who cares?", and "why now?" — to every claim in the copy. Blocks "it explains what we do" completions.
Use before running any growth experiment — pricing test, copy variant, onboarding flow, feature gate — that will inform a ship/no-ship decision. All six elements must be defined before the test starts. Blocks "we'll run it for a while and see" completions.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Skills and agents that enforce quality across the full growth lifecycle:
Strategy → Channel Selection → Offer → Campaign → Launch → Metrics → Funnel → Experiment → Retention → Messaging Review
Growth strategy defined before channels are chosen, channels chosen before campaigns are built, offers validated before copy is written, copy that clears the "who cares?" test, launches planned with rollback criteria, metrics named before execution, funnels diagnosed before they are optimised, experiments designed with stopping rules before they run, retention loops defined before launch, pricing and social proof reviewed before they ship, and AI capability claims reviewed for accuracy before they ship.
Works standalone or alongside A Team, builder-ai, builder-design, and builder-product.
Not every skill is required on every project — use the ones that match the work in front of you. See CLAUDE.md for the full trigger sequence.
| Skill | What It Enforces |
|---|---|
growth-strategy-design | Growth stage, segment, goal, constraint, channel hypothesis, offer, north star, and 90-day hypothesis defined before execution |
channel-selection-audit | Every candidate channel scored against 8 criteria before a campaign is built |
offer-quality-gate | Target customer, problem, outcome, mechanism, proof, risk reversal, pricing, CTA, and objections defined before copy is written |
positioning-audit | Clear category, specific audience, and differentiated claim before any copy is written |
campaign-brief-generator | Objective, audience, offer, message, channel, creative specs, and success metric defined before execution |
copy-quality-gate | "So what?", "who cares?", and "why now?" tests before any copy ships |
launch-plan-design | Launch goal, timeline, task ownership, success metrics, and rollback criteria defined before launch day |
growth-metrics-design | North star, input/output metrics, leading/lagging indicators, and metric owners defined before execution |
funnel-analysis | Leak identified and root-caused before any optimisation begins |
experiment-design | Hypothesis, metric, sample size, duration, stopping rule, decision rule before any test runs |
retention-design | Activation moment, habit loop, and reactivation path defined before launch |
social-proof-review | Every testimonial, logo, case study, and quantified result sourced and permissioned before publication |
pricing-page-review | Pricing clarity, tier differentiation, risk reversal, and disclosed limitations before a pricing page ships |
ai-messaging-review | AI capability claims reviewed for source, scope, and accuracy — no unsourced quantified claims |
| Agent | Role |
|---|---|
growth-critic (Sonnet) | Reviews positioning, copy, and experiments against skill gates; PASS / CONDITIONAL / BLOCK |
experiment-designer (Sonnet) | Designs growth experiments with calculated sample sizes and pre-specified stopping rules |
messaging-reviewer (Opus) | Reviews AI product messaging for sourced claims, scoped capabilities, and specific AI labels |
growth-strategist (Sonnet) | Defines growth strategy, validates channel selection and offers, designs launch plans; READY / CONDITIONAL / BLOCKED |
campaign-reviewer (Sonnet) | Builds campaign briefs, defines growth metrics, reviews social proof and pricing pages; PASS / CONDITIONAL / BLOCK |
# bash (macOS / Linux / WSL)
bash <(curl -fsSL https://raw.githubusercontent.com/RBraga01/builder-growth/master/install.sh)
# PowerShell (Windows)
irm https://raw.githubusercontent.com/RBraga01/builder-growth/master/install.ps1 | iex
Or clone directly:
git clone https://github.com/RBraga01/builder-growth
cp -rn builder-growth/skills your-project/
cp -rn builder-growth/.claude your-project/
| Pack | Domain | Skills | Agents |
|---|---|---|---|
| A Team | Engineering baseline | 19 | 26 |
| builder-ai | LLM engineering | 8 | 5 |
| builder-design | AI UI design | 8 | 5 |
| builder-product | Product quality | 7 | 3 |
| builder-growth | Growth & messaging | 14 | 5 |
All packs share the same enforcement model: Completion Statement Formats that require real values, not summaries.
MIT — Ricardo Romão Marques Braga
npx claudepluginhub rbraga01/a-team --plugin builder-growthUniversal multi-agent infrastructure: 26 specialist agents, 20 enforced workflow skills, and a lead orchestrator
AI UI design quality enforcement: 8 skills and 5 agents for UI design teams
AI product quality enforcement: 6 skills and 3 agents for product teams
AI product quality enforcement: 8 skills and 5 agents for LLM product teams
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.