APIClaw — Amazon Daily Market Radar

> Set it. Forget it. Get alerted when it matters. Respond in user's language.

Files

Credential

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

Input (First Run)

Collect in ONE message: ✅ my_asins (1-10) | 💡 competitor_asins (up to 20) | 📌 alert_preferences. Optional: keyword, category. Category is auto-detected from first tracked ASIN if not provided.

API Pitfalls (CRITICAL)

1. Category auto-detection: categoryPath is auto-detected from tracked ASINs. If category_source in output is inferred_from_search, confirm with user
2. All keyword-based endpoints MUST include --category; ASIN-specific endpoints do NOT
3. Use API fields directly: revenue=sampleAvgMonthlyRevenue (NEVER price×sales), sales=monthlySalesFloor, concentration=sampleTop10BrandSalesRate
4. reviews/analysis: needs 50+ reviews
5. Aggregation without categoryPath: severely distorted data

Execution

1. daily-radar --asins "asin1,asin2,..." [--keyword X] [--category Y] (composite, auto-detects category from ASINs)
2. Compare against {skill_base_dir}/data/last-run.json for change detection (first run = baseline only, no alerts)
3. Generate alert-prioritized briefing → save snapshot to {skill_base_dir}/data/last-run.json

Alert Rules

Change Detection Logic

• Price change >5% → 🔴
• BSR move >20% → 🟡
• New ASINs in top 20 (vs last run) → 🟡

Growth signal validation:

• 📊 Sustained: 7+ days consistent direction
• 🔍 Possible signal: 2-3 days of change
• 💡 Single-day spike: could be promotion/restock

Change Interpretation Guide

Action Recommendations by Alert Level

• 🔴 RED: Require immediate response — check inventory, match price if needed, investigate quality issues 💡
• 🟡 YELLOW: Monitor for 3-5 days before acting — may be temporary fluctuation 💡
• 🟢 GREEN: Opportunity window — act within 1-2 weeks before competitors notice 💡

Output Spec

First run: "Baseline Established" — KPI Dashboard (current snapshot) only, no alerts.

Subsequent runs: Alert Summary → RED Alerts → YELLOW Alerts → GREEN Opportunities → KPI Dashboard (today vs yesterday) → Competitor Movement → Market Shifts → Action Items → 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), 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.

Sample bias: "Based on Top [N] by sales volume; niche/new products may be underrepresented."

Data Provenance (required)

Include a table at the end of every report:

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)

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

API Budget: ~15-30 credits

Realtime×ASINs(5-15) + History(1-2) + Market/Brand(3) + Products(1) + Price(2) + Categories(1) + Reviews(1-3).