Amazon Market Entry Analyzer

Amazon Market Entry Analyzer — GO / CAUTION / AVOID

One input (keyword/category). Full market viability assessment with sub-market discovery.

Files

• Script: {skill_base_dir}/scripts/zoodata.py — run --help for params
• Reference: {skill_base_dir}/references/reference.md (field names & response structure)

Credential

Required: ZOODATA_API_KEY. Get free key at zoodata.ai/api-keys

Input

• Required: keyword or categoryPath
• Optional: marketplace (default US)
• Optional (seller-side — drives the Small-Seller Entry Risk Gates section below):
• budget — first-6-month capital available (e.g. "$10K", "$50K", "$200K+")
• risk_tolerance — low / medium / high
• ip_concern — known compliance, patent, trademark, or restricted-category concerns; or "none"

If the user hasn't supplied these, ask once at the start of the workflow (a single batched question is fine). If the user declines or skips, omit the Risk Gates section from the final verdict and add a line under Data Provenance: "Risk Gates: skipped — seller-side inputs not provided." Do not guess thresholds — silent gate evaluation with invented inputs produces inconsistent verdicts across runs.

API Pitfalls (shared with zoodata skill — critical!)

• Keyword search is broad → categoryPath is auto-resolved via categories endpoint, with fallback to top search result. If category_source is inferred_from_search, confirm with user
• Brand/price-band queries MUST include --category to avoid cross-category contamination
• Revenue = sampleAvgMonthlyRevenue (NEVER calculate avgPrice × totalSales — overestimates 30-70%)
• Sales = monthlySalesFloor (lower bound). Fallback: 300,000 / BSR^0.65, tag 🔍
• Use sampleOpportunityIndex, sampleTop10BrandSalesRate directly — never reinvent
• reviews/analysis needs 50+ reviews. Fallback chain when sample is insufficient:

1. Lightweight: realtime/product ratingBreakdown — only star distribution, no themes
2. Full 11-dim insights — bypass /reviews/analysis entirely:

a. zoodata.py reviews-raw --asin X → fetch up to 100 raw reviews (10 credits, ~60s) b. For each review: render Map prompt via zoodata.py review-tag-prompt --review '' and have your own LLM produce JSON tags (sentiment + 11 dimensions) c. Collect candidate phrases per dimension; for each dimension render Reduce prompt via zoodata.py review-reduce-prompt --label-type X --candidates '[...]' and have your LLM produce semantic clusters d. zoodata.py review-aggregate --reviews R --tagged T --clusters C → consumerInsights output compatible with /reviews/analysis

1. Fallback caveats (apply to the 4-step chain above — lessons from end-to-end validation):

• Working dir: WORK=/tmp/review__$(date +%s) && mkdir -p $WORK
• Step b CLI behavior: review-tag-prompt RENDERS the prompt only; YOUR LLM produces the JSON. Render once to learn the schema, then produce tags for all N reviews in one in-context pass (don't call the CLI N times).
• Step c candidate extraction (Python one-liner):

candidates = {d: sorted({el.strip().lower() for t in tagged for el in (t.get(d) or [])}) for d in DIMS}

• **Small-sample rule (reviewCount$10M/mo | $5-10M | 60% |

| Price Opportunity | 15% | oppIndex>1.0 | 0.5-1.0 | 15% | 5-15% | 30% | 15-30% | CAUTION > AVOID`. A score-90 GO with one gate at AVOID → final AVOID; a score-90 GO with one gate at CAUTION → final CAUTION.

1. GO requires BOTH a passing viability score AND every gate in PASS (or with a documented mitigation plan in the same workflow turn).
2. CAUTION fits markets with 1–2 uncertain gates that can plausibly be validated inside the Validation Speed window (7–30 days, sampled or lightweight listing).
3. AVOID is mandatory when any of {Compliance/IP, Capital fit, Review barrier} is a hard-block — regardless of viability score. These three categories are non-negotiable for small sellers.
4. Relationship to "User criteria override" above: that rule remains authoritative — if the user sets explicit thresholds (e.g. "min monthly sales 500", "max CR10 50%"), those override even gates. The Gates fire as the default backstop when no user-set thresholds cover the same dimension.
5. Tag each gate conclusion with the required confidence label (📊, 🔍, or 💡) — never treat the gate table itself as data-backed.

Composite Command

python3 {skill_base_dir}/scripts/zoodata.py market-entry --keyword "{kw}" --category "{path}"

Runs all 11 endpoints (~20 calls). Output JSON is large — use targeted extraction, not full read.

Output

Respond in user's language.

Sections: Sub-Market Landscape → Executive Summary → Market Overview → Trend → Brand Landscape → Price Structure → Top 5 Competitors → Consumer Insights → Scoring Breakdown (with "Basis" column) → Entry Strategy → Data Provenance → API Usage → Cross-Market Comparison

If user provides COGS, calculate break-even and profit. If not, prompt for it.

Language (required)

Output language MUST match the user's input language. If the user asks in Chinese, the entire report is in Chinese. If in English, output in English. Exception: API field names (e.g. monthlySalesFloor, categoryPath), endpoint names, technical terms (e.g. ASIN, BSR, CR10, FBA, credits) remain in English.

Disclaimer (required, at the top of every report)

> Data is based on ZooData API sampling as of [date]. Monthly sales (monthlySalesFloor) are lower-bound estimates. This analysis is for reference only and should not be the sole basis for business decisions. Validate with additional sources before acting.

Confidence Labels (required, tag EVERY conclusion)

• 📊 Data-backed — direct API data (e.g. "CR10 = 54.8% 📊")
• 🔍 Inferred — logical reasoning from data (e.g. "brand concentration is moderate 🔍")
• 💡 Directional — suggestions, predictions, strategy (e.g. "consider entering $10-15 band 💡")

Rules: Strategy recommendations are NEVER 📊. Anomalies (>200% growth) are always 💡. User criteria override AI judgment.

Aggregate-label rule (applies to ALL report output, not just fallback): NEVER attach 📊 to ANY element that aggregates or groups underlying content when ANY piece of that content is 🔍 or 💡. "Aggregate/grouping elements" include:

• Section headers at EVERY level (#, ##, ###, ####) — including top-level summary sections like "Overall Score", "Verdict", "Executive Summary"
• Summary/score lines anywhere in the report (e.g. ## Overall Score — 27/100 · Grade F 📊 is WRONG if any Basis row inside is 🔍)
• Table column headers in comparison tables (e.g. **Target ASIN** 📊 as a column label is WRONG if any cell in that column contains 🔍)
• Table row headers or row-aggregation labels (when the row aggregates multiple cells of mixed confidence)
• Any other visual grouping label — bullet-list group titles, callout box titles, etc.

A group-level 📊 implies the whole block/column/row is data-backed, which smuggles inferred/directional content into the 📊 tier via visual grouping. Either (a) omit the group-level label entirely (preferred when content mixes tiers), or (b) use the LOWEST confidence present inside (🔍 if any underlying content is 🔍; 💡 if any is 💡). This is a universal output-quality rule — it applies regardless of which fallback path (if any) was triggered.

Emoji reservation rule (closely related): The three confidence symbols 📊 🔍 💡 are RESERVED for confidence labeling. NEVER use them as decorative prefixes on section headers, table headers, or any aggregate element — even when you also include a correct confidence suffix on the same line. Example:

• ❌ WRONG: ## 📊 Overall Score — 27/100 · Grade F 🔍 (the leading 📊 reads as a data-backed claim even though the trailing 🔍 is correct)
• ✅ RIGHT: ## Overall Score — 27/100 · Grade F 🔍 (no decorative emoji, just the proper confidence suffix)
• ✅ RIGHT: ## 🎯 Overall Score — 27/100 · Grade F 🔍 (use non-reserved decorative icons like 🎯 🧭 📋 📝 📂 🏁 🚨 🏆 🔔 when a visual prefix is desired)

Decorative emoji ≠ confidence label — but from a reader's perspective, a leading 📊/🔍/💡 is indistinguishable from a confidence claim. Reserve these three symbols EXCLUSIVELY for confidence annotation to avoid ambiguity.

Data Provenance (required)

Include a table at the end of every report:

| Data | Endpoint | Key Params | Notes | |------|----------|------------|-------| | (e.g. Market Overview) | markets/search | categoryPath, topN=10 | 📊 Top N sampling, sales are lower-bound | | ... | ... | ... | ... |

Extract endpoint and params from _query in JSON output. Add notes: sampling method, T+1 delay, realtime vs DB, minimum review threshold, etc.

API Usage (required)

| Endpoint | Calls | Credits | |----------|-------|---------| | (each endpoint used) | N | N | | Total | N | N |

Extract from meta.creditsConsumed per response. End with Credits remaining: N.

API Budget: ~20 calls

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: SerendipityOneInc
• Source: SerendipityOneInc/ZooData-Skills
• License: MIT
• Homepage: https://apiclaw.io/

Install and usage instructions live in the source repository linked above.