ln-51-opportunity-evaluator

# Opportunity Evaluator

**Goal:** Evaluate product opportunities before implementation commitment. Start from observable demand and a reachable acquisition path, eliminate weak candidates early, and recommend one low-cost validation step without manufacturing market precision.

**Execution contract:** Treat the ordered checkbox workflow below as this skill's Definition of Done. Track every checkbox as `PENDING`, then resolve it to `PROVEN` with concrete evidence, `CLEARED` with evidence that its conditional trigger is absent, or `UNPROVEN`; reading, mentioning, delegating, skipping, or tool failure is not proof.
Before returning, resolve every `PENDING`, count only `PROVEN` and `CLEARED` items as complete, apply this skill's verdict, decision, and approval rules to every `UNPROVEN`, and prepend **Checklist: X/Y complete**<br>**Incomplete: None | section/item — reason; outcome impact; exact next action**; list every `UNPROVEN` item.

## Tool Routing

| Need | Preferred tool | Use it when | Fallback |
|---|---|---|---|
| Product and constraints | User context plus existing product, analytics, customer, and strategy documents | Establishing audience, assets, channels, economics, and non-goals | State assumptions and request only consequential missing intent |
| Current demand and acquisition | Web research, trend or marketplace data, communities, reviews, ads, directories, and primary customer evidence | Every external market claim that affects elimination or recommendation | Mark the signal unavailable; never infer a number from search-result count |
| Competition and pricing | Competitor product pages, pricing, release history, distribution channels, reviews, and public filings where relevant | Establishing substitutes, willingness-to-pay signals, and credible differentiation | Use qualitative evidence with explicit confidence |
| Feasibility and validation cost | Existing capabilities, public APIs, regulations, platform rules, and current official documentation | Comparing the cheapest credible experiment and major blockers | Label estimates and name the evidence still required |

Keep the evaluation read-only. Do not create project files, roadmaps, Epics, Stories, implementation plans, campaigns, listings, advertisements, or customer outreach.

## Evidence Classes

| Class | Meaning |
|---|---|
| `MEASURED` | Direct analytics, transactions, experiments, or instrumented observations with known method and date |
| `REPORTED` | A primary source reports a value or behavior, but the underlying measurement is not independently available |
| `ESTIMATED` | A stated model based on explicit inputs and assumptions |
| `INFERRED` | A qualitative conclusion from observable proxies |
| `UNKNOWN` | Evidence is unavailable, stale, incomparable, or too weak to support a decision |

Do not turn `REPORTED`, `ESTIMATED`, or `INFERRED` evidence into a measured market size, search volume, conversion rate, revenue, or willingness-to-pay claim. Date every external source and distinguish the event date from the publication date when they differ.
Treat the creator thesis, intended experience, taste, and conviction as owner preferences and strategic-fit inputs, never as demand, acquisition, or willingness-to-pay evidence.

## Checklist

### 1. Frame the Decision

- [ ] Resolve the existing product or capability, target users, creator thesis, intended experience, decision horizon, available assets, geographic or regulatory scope, constraints, and explicit non-goals.
- [ ] Accept user-supplied candidates or generate a bounded set of materially distinct opportunities from product context and current signals; do not create cosmetic variants of one idea.
- [ ] Define what would justify deeper validation: identifiable user and problem, observable demand, reachable channel, credible value exchange, differentiating wedge, and affordable experiment.
- [ ] Separate discovery of a new direction from prioritization of already committed work or implementation planning.
- [ ] Record assumptions that can reverse the recommendation, separate researchable facts from owner preference, and ask one concise question only when different interpretations materially change the candidates or experiment.

### 2. Collect One Evidence Bundle per Candidate

- [ ] Identify who experiences the problem, how they solve it today, what triggers active search or purchase, and what evidence shows the pain is recurring or costly.
- [ ] Find a reachable acquisition channel and its mechanism: query, marketplace category, integration ecosystem, community, partner, outbound audience, or another observable path.
- [ ] Inspect direct competitors, substitutes, do-nothing behavior, pricing, positioning, distribution, review complaints, and evidence of continued investment or abandonment.
- [ ] Examine economic signals without inventing unit economics: price anchors, budget owner, purchase frequency, switching cost, delivery cost, platform fees, and support burden.
- [ ] Identify implementation, data, dependency, regulation, trust, distribution, and operational blockers that affect the cost of a validation experiment.
- [ ] Capture source, date, evidence class, scope, confidence, contradiction, and the candidate decision each signal can change.
- [ ] Stop researching a candidate once the evidence is sufficient to eliminate it or additional sources cannot change its status.

### 3. Apply Evidence-First Elimination

- [ ] Eliminate a candidate when no specific user problem, observable demand signal, reachable channel, credible value exchange, or feasible validation path can be established.
- [ ] Treat competition as evidence of demand and constraints, not an automatic rejection; require a concrete wedge against substitutes and the do-nothing option.
- [ ] Do not use universal thresholds for search volume, competitor count, ARPU, market size, or MVP duration.
- [ ] Preserve candidates with weak public data as `UNKNOWN` rather than labeling them invalid when a c