funnel-planner
Funnel Planner — Orchestrator
Strategy — Step 3 of 4. Sets data-driven targets for each prioritized initiative.
Core Question: "Do the numbers actually work?"
Critical Gates — Read First
- Every target MUST have a numeric baseline — zero "TBD" values. Targets without baselines are arbitrary guesses. If the user lacks data, use industry benchmarks with confidence flagging.
- Every target MUST cite justification — no naked numbers. "Achieve 5% conversion" needs: baseline (current 3.2%), improvement factor (20% lift), reasoning (no optimization done yet, fixing known broken page).
- 70% test is mandatory — partial achievement must still be valuable. If hitting 70% of a target is meaningless, the target is wrong. Apply context rules for metric type (higher-is-better, lower-is-better, binary).
- LTV:CAC ≥ 3:1 required for acquisition targets — or explicitly flagged. Setting aggressive acquisition targets when unit economics are unhealthy means you lose money faster.
- Growth motion MUST be explicitly identified — PLG, SLG, or Hybrid. The funnel model selection depends on the growth motion. PLG → PLG Funnel or AARRR. SLG → SLG Funnel or TOFU-MOFU-BOFU. Hybrid → both with clear primary/supplementary designation.
- Three-outcome validation required — every funnel must account for Business (revenue), Brand (awareness), and Community (engagement). Business must be Covered. Brand and Community may be N/A with justification. Gaps without justification are flagged.
More from hungv47/research-skills
market-research
Analyzes market landscapes, competitive dynamics, TAM/SAM/SOM sizing, and whitespace opportunities for a product or category. Produces `research/market-research.md`. Not for building customer personas (use icp-research) or planning marketing campaigns (use campaign-plan). For diagnosing a specific business problem, see diagnose. For prioritizing what to build from market data, see prioritize.
10icp-research
Builds ideal customer profiles and buyer personas — analyzes demographics, pain points, jobs-to-be-done, and segmentation for a target market. Produces `research/icp-research.md`. Not for competitive positioning (use prioritize) or campaign planning (use campaign-plan). For brand identity from audience data, see brand-system. For market sizing and competitor landscape, see market-research.
10problem-analysis
Structured diagnosis of business and strategic problems — builds logic trees, forms testable hypotheses, and identifies root causes with evidence. Produces `.agents/problem-analysis.md`. Not for code bugs (use code-cleanup) or brainstorming solutions to a known problem (use solution-design). For market-level trends and competitive context, see market-research. For testing hypotheses with experiments, see experiment.
9solution-design
Brainstorms and prioritizes strategic solutions when the problem or goal is already clear — generates options, scores trade-offs, and recommends a path forward. Produces `.agents/solution-design.md`. Not for diagnosing what the problem is (use problem-analysis) or engineering task lists (use task-breakdown). For setting numeric targets after prioritizing, see funnel-planner. For technical architecture of chosen initiatives, see system-architecture.
9experiment
Designs validation experiments for business ideas — defines hypotheses, success metrics, sample sizes, and minimum viable tests before full commitment. Produces `.agents/experiment-[name].md`. Not for strategic prioritization (use solution-design) or market sizing (use market-research). For diagnosing root causes, see problem-analysis. For campaign planning, see imc-plan.
7content-research
Researches what short-form content to create — competitor ads, audience communities, trending topics, viral patterns, scroll-stop creative across social, ad, SMS, and OOH channels. Produces `.agents/mkt/content-research.md`. For long-form research (blog, case study, byline, PR, newsletter, app store listings) use content-research-long instead. Not for market landscape (use market-research) or audience personas (use icp-research). For writing the content itself, see content-short.
6