Amazon Market Entry Analyzer

One-click market viability assessment for Amazon sellers. Analyzes market size, competition intensity, brand landscape, pricing structure, and consumer pain...

Security Scan

The skill is internally consistent with its stated purpose: it only requires an APIClaw API key and calls APIClaw endpoints (no unrelated credentials, installs, or system-wide changes).

Purpose & Capability

Name/description, SKILL.md, README, reference, and the included script all consistently describe market analysis via the APIClaw service. The only required credential is APICLAW_API_KEY which is exactly what the skill needs to call api.apiclaw.io endpoints.

Instruction Scope

Runtime instructions direct the agent to run the included CLI script and use APIClaw's 11 endpoints. The SKILL.md specifies which inputs are required, expected fallbacks, output format, language rules, and a required disclaimer. There are no instructions to read unrelated system files, other environment variables, or to transmit data to endpoints outside api.apiclaw.io. Note: the script injects _query metadata into API responses (expected for provenance) and the workflow makes many API calls (~20), so the APICLAW_API_KEY will be transmitted to api.apiclaw.io during normal operation.

Install Mechanism

No install spec; the skill is instruction-only with a provided script. No external downloads, package installs, or archive extraction are requested by the skill metadata. This minimizes installation risk.

Credentials

Only APICLAW_API_KEY is required and declared as the primary credential. The included script also supports reading a local config.json (in the skill directory) as an alternative key source — this is reasonable but users should avoid placing sensitive keys in shared repositories. No unrelated secrets or multiple service credentials are requested.

Persistence & Privilege

always is false; the skill does not request persistent/always-on privilege and does not modify other skills or global agent config. It only reads the API key from the environment or a local config file and performs API calls to api.apiclaw.io as described.

Assessment

This skill appears coherent and does what it claims: it queries api.apiclaw.io using your APICLAW_API_KEY and the included CLI script. Before installing, consider: (1) Trustworthiness of the API provider — the skill will send your API key and query parameters to api.apiclaw.io, so verify the service is legitimate and you trust its data/privacy practices. (2) Do not commit your APICLAW_API_KEY into public repos — the script will also accept a local config.json in the skill directory, which could be accidentally checked in. (3) The workflow makes many API calls (~20) and may consume API credits; check quotas and billing on your APIClaw account. (4) Review the included script if you want to confirm there is no additional network behavior or logging you disagree with — the code is readable and uses urllib to POST to the documented base URL. (5) If you need the agent to not call external services autonomously, adjust invocation policies; although the skill is user-invocable only by default, the agent can still invoke it when asked. If you want, I can highlight specific lines in the script that show how the API key is used and where a config.json would be read.

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

Credential

Required: APICLAW_API_KEY. Get free key at apiclaw.io/api-keys

Input

• Required: keyword or categoryPath
• Optional: marketplace (default US)

API Pitfalls (shared with apiclaw 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 to realtime ratingBreakdown
• Aggregation endpoints without categoryPath produce severely distorted data

Unique Logic

Sub-Market Discovery

Run market --category "{path}" --topn 10 --page-size 20, paginate all pages. Score each sub-market (1-100):

Dimension	Weight	Field	Good→100	Bad→0
Demand	25%	sampleAvgMonthlySales	≥1500	<200
Profit	25%	sampleAPlusRate	≥0.35	<0.15
New Entrant	20%	sampleNewSkuRate	≥0.20	<0.05
Brand Openness	20%	topBrandSalesRate	≤0.50	≥0.90 (inverted)
Capacity	10%	totalSkuCount	300-8000	extreme

Fallback (grossMargin=0 for all): redistribute to Demand 30%, New Entrant 25%, Brand 25%, Capacity 20%.

Present TOP 10 sub-markets. Ask user which to deep-dive (default: top 3). If ≤3 sub-markets, deep-dive all.

Market Viability Score (1-100)

Dimension	Weight	Good	Medium	Warning
Market Size	15%	>$10M/mo	$5-10M	<$5M
Market Trend	10%	Rising	Stable	Declining
Competition	25%	CR10<40%	40-60%	>60%
Price Opportunity	15%	oppIndex>1.0	0.5-1.0	<0.5
New Entrant Space	10%	>15%	5-15%	<5%
Consumer Pain Points	15%	Clear gaps	Some	None
Profit Potential	10%	>30%	15-30%	<15%

Go/No-Go Decision

Score	Signal	Action
70-100	✅ GO	Proceed with product development
40-69	⚠️ CAUTION	Possible but needs differentiation
0-39	🔴 AVOID	Too competitive or too small

CR10 dual-level check: Category CR10 PASS + sub-market CR10 FAIL → ⚠️ CAUTION. Both FAIL → AVOID. User criteria override: If user sets thresholds, ANY fail → CAUTION/AVOID. Never override.

Composite Command

python3 {skill_base_dir}/scripts/apiclaw.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 APIClaw 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.

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