hashgraph-online/awesome-codex-plugins / plugins/BlockchainHB/launchfast_codex_plugin/skills/product-research
product-research
VerifiedDeep Codex-native Amazon FBA product validation using LaunchFast MCP and the LegacyX criteria. Use when the user wants a serious viability review for a keyword, niche, or adjacent niche expansion.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.8 KB |
SKILL.md
View on GitHub---
name: product-research
description: |
Deep Codex-native Amazon FBA product validation using LaunchFast MCP and the
LegacyX criteria. Use when the user wants a serious viability review for a
keyword, niche, or adjacent niche expansion.
---
# Amazon FBA Product Research
This skill is the deeper, criteria-driven version of `launchfast-product-research`.
## Core criteria
Evaluate every market against these baselines:
| Criteria | Threshold |
|---|---|
| Total niche revenue | > $200,000/month |
| Average price | >= $25, ideally >= $40 |
| Average reviews | <= 500 |
| Revenue per seller | >= $5,000/month |
| Top-seller dominance | top 2-3 sellers < 50% of revenue |
| Search volume | must exist |
| Estimated margin | >= 30% before ad costs |
Large-market exception:
- If niche revenue is above $1M, higher review counts can still be acceptable when multiple sellers under 200 reviews are doing strong revenue.
## Workflow
### 1. Initial scan
Run:
```text
research_products(keyword="<keyword>", focus="balanced", product_limit=20)
```
Extract:
- search volume
- average price
- average reviews
- opportunity score
- market grade
- brand concentration
- dominant brand
- total niche revenue
- average revenue per seller
- top-seller share
### 2. Financial trend check
Run:
```text
research_products(keyword="<keyword>", focus="financial", product_limit=20)
```
Look for:
- growing vs stable vs declining products
- average MoM growth
- short-term momentum using 7d trend fields
### 3. Listing quality check
Run:
```text
research_products(keyword="<keyword>", focus="titles", product_limit=10)
```
Look for:
- low listing quality scores with high revenue
- listing quality gaps
- weak copy or obvious differentiation openings
### 4. Keyword validation
Pick 2-3 relevant ASINs and run:
```text
amazon_keyword_research(asins=["ASIN1", "ASIN2", "ASIN3"], limit=20)
```
Evaluate:
- keyword diversity
- CPC and sponsored density
- purchase rate
- obvious ranking gaps
### 5. Profitability estimate
Present a conservative estimate:
```text
Selling Price
- Amazon Fees (~15%)
- Manufacturing
- Shipping
= Estimated Profit per Unit
= Estimated Margin %
```
If manufacturing cost is unknown, say so and state the assumption used.
## Output format
Use a scorecard first:
```markdown
## Market Scorecard: [keyword]
| Criteria | Threshold | Actual | Status |
|---|---|---|---|
```
Then include:
- market grade
- opportunity score
- trend summary
- verdict: VIABLE, MARGINAL, or NOT RECOMMENDED
- concise rationale
## Rabbit-hole expansion
Use adjacent-niche exploration only when it is helpful:
- identify variations from the first result set
- rerun `research_products` on the most promising adjacent keywords
- keep the branching tight; do not explode the scope without user intent
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |