APIClaw — Market Trend Scanner

Find rising categories before everyone else. Respond in user's language.

Files

{skill_base_dir}/scripts/apiclaw.py

--help

{skill_base_dir}/references/reference.md

{skill_base_dir}/scan-data/

Credential

Required:

APICLAW_API_KEY

Input

Tell the user: "Give me one or more categories to monitor (e.g. 'Pet Supplies > Dogs'). I'll scan all subcategories and find trending directions. Single or batch supported."

Required: 1+ category paths or keywords. Optional: scan depth, metric preferences.

API Pitfalls (CRITICAL)

1. Category first: resolve categoryPath via

   categories --keyword

   before anything
2. All keyword endpoints MUST include

   --category

   ; omitting it distorts aggregation
3. Use API fields directly: revenue=

   sampleAvgMonthlyRevenue

   , sales=

   monthlySalesFloor

4. Key metrics per subcategory: sampleAvgMonthlySales, sampleNewSkuRate, topBrandSalesRate, sampleAvgPrice, sampleAPlusRate, totalSkuCount, sampleFbaRate

Mode 1: Full Scan

1. categories --keyword "{keyword}"

   → resolve category path

2. market --category "{path}" --page-size 20

   → collect all subcategory market data (paginate)
3. Record 7 key metrics per subcategory (see Pitfalls #4)

4. products --keyword "{sub}" --category "{path}" --mode emerging --page-size 20

   per hot subcategory

5. products --keyword "{sub}" --category "{path}" --mode new-release --page-size 20

   per hot subcategory
6. Save baseline →

   {skill_base_dir}/scan-data/baseline.json

   , config →

   {skill_base_dir}/scan-data/watchlist.json

7. Output full trend report (see Output Spec)
8. Offer Auto-Monitor setup

Mode 2: Quick Check (scheduled)

1. Read

   {skill_base_dir}/scan-data/watchlist.json

   +

   {skill_base_dir}/scan-data/baseline.json

2. market --category "{path}"

   per watched category
3. Compare vs baseline using signal rules below
4. 🔴 alerts → notify user; else silent log
5. Save snapshot to

   {skill_base_dir}/scan-data/history/{timestamp}.json

   , update baseline

Trend Signals

Trend Interpretation & Action Guide

Subcategory Ranking Criteria

Rank subcategories by composite attractiveness (apply market-entry scoring logic):

• Demand: sampleAvgMonthlySales — higher = more attractive 📊
• Competition: topBrandSalesRate — lower = more open 📊
• Entry barrier: sampleAvgRatingCount — lower = easier entry 📊
• Activity: sampleNewSkuRate — higher = more dynamic 📊
• Margin signal: sampleAvgPrice — higher generally = better margins 🔍

Auto-Monitor

After each Full Scan, ask user to enable scheduled monitoring. If yes, generate cron config with: category list, alert thresholds, schedule. Supports OpenClaw /cron, ChatGPT Scheduled Tasks, Claude Projects. Quick Check only notifies on 🔴 alerts.

Output Spec

Full Scan: Trend Dashboard (all subcategories) → 🔥 Hot Categories TOP 5 → 🆕 New Entrants Scan → ⚠️ Risk Alerts → Subcategory Detail (per hot category) → Next Steps → Data Provenance → API Usage.

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

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 💡. Sample bias note required. User criteria override AI judgment.

Data Provenance (required)

Include a table at the end of every report:

markets/search

Extract endpoint and params from

_query

API Usage (required)

Extract from

meta.creditsConsumed

Credits remaining: N

API Budget

Full Scan: ~40-60 credits (~2-3 per subcategory × 20). Quick Check: ~20-30 credits (market only).