← Back to Skills Marketplace
apiclaw

Apiclaw

by apiclaw · GitHub ↗ · v1.1.1 · MIT-0
cross-platform ✓ Security Clean
150
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install apiclaw-core
Description
General overview, 11 API endpoints. AI-powered commerce data infrastructure with 200M+ Amazon products. Endpoints: category browsing, market metrics, product...
README (SKILL.md)

📋 Live API Reference: Field names and parameters may change. If you encounter field errors, check the latest OpenAPI spec at https://apiclaw.io/api/v1/openapi-spec for current field definitions.

APIClaw — Commerce Data Infrastructure for AI Agents

200M+ Amazon products. 11 endpoints. One API key.

Quick Start

  1. Get key: apiclaw.io/api-keys (1,000 free credits)
  2. export APICLAW_API_KEY='hms_live_xxx'
  3. Base URL: https://api.apiclaw.io/openapi/v2 — all POST with JSON body
  4. Auth: Authorization: Bearer YOUR_API_KEY
  5. New keys need 3-5s to activate. If 403, wait and retry.

⚠️ Critical API Pitfalls (ALL skills must follow)

  1. Keyword search is broad → MUST lock categoryPath first via categories endpoint
  2. Brand/price-band queries MUST include --category to avoid cross-category contamination
  3. Revenue = sampleAvgMonthlyRevenue directly. NEVER calculate avgPrice × totalSales (overestimates 30-70%)
  4. Sales = monthlySalesFloor (lower bound). Fallback: 300,000 / BSR^0.65, tag as 🔍
  5. Use API fields directly: sampleOpportunityIndex, sampleTop10BrandSalesRate — never reinvent
  6. reviews/analysis needs 50+ reviews; fallback to realtime ratingBreakdown
  7. Aggregation endpoints (price-band, brand) without categoryPath produce severely distorted data
  8. Price-band and brand endpoints only accept keyword (not categoryPath) — cross-validate returned products

11 Endpoints

# Endpoint Purpose Key Output
1 categories Browse/search category tree categoryPath, productCount
2 markets/search Market-level metrics sampleAvgMonthlySales, sampleAvgPrice, topSalesRate, sampleNewSkuRate
3 products/search Product search (14 modes) asin, price, monthlySalesFloor, rating, ratingCount, fbaFee
4 products/competitors Competitor discovery same fields as products/search
5 realtime/product Live ASIN detail rating, features, bestsellersRank[], buyboxWinner.price, variants
6 reviews/analysis AI review insights (11 dims) sentimentDistribution, consumerInsights, topKeywords
7 products/price-band-overview Price band summary hottestBand, bestOpportunityBand, sampleOpportunityIndex
8 products/price-band-detail Full 5-band distribution priceBands[] with sales, brands, ratings per band
9 products/brand-overview Brand concentration sampleTop10BrandSalesRate (CR10), sampleBrandCount
10 products/brand-detail Per-brand breakdown brands[] with sales, revenue, sampleProducts
11 products/history Time series (single ASIN per call) timestamps[], price[], bsr[], monthlySalesFloor[], rating[], ratingCount[], sellerCount[], title/imageUrl/bestSeller/newRelease/aPlus/inventoryStatus changelogs

Known Quirks

  • topN, listingAge, newProductPeriod are strings ("10" not 10)
  • Response .data is always an array — use .data[0]
  • ratingCount not reviewCount everywhere
  • bsr (int) in products vs bestsellersRank (array) in realtime
  • buyboxWinner.price — NOT top-level price in realtime
  • realtime/product does NOT return: monthlySalesFloor, fbaFee, sellerCount
  • reviewCountMin/Max filters currently broken (API-56)
  • reviews/analysis may 500 for certain ASINs (API-58) — retry different ASIN
  • Rate limit: 100 req/min, 10 req/sec burst
  • categories uses categoryKeyword (not keyword) and parentCategoryPath (not parentCategoryName)
  • reviews/analysis: mode required ("asin"/"category"), use asins (plural array) not asin

Field Differences Across Endpoints

Data markets products/competitors realtime reviews price-band brand history
Sales sampleAvgMonthlySales monthlySalesFloor ❌ ❌ sampleSalesRate sampleGroupMonthlySales monthlySalesFloor[]
Price sampleAvgPrice price buyboxWinner.price ❌ bandMin/MaxPrice sampleAvgPrice price[]
BSR sampleAvgBsr bsr (int) bestsellersRank[] ❌ ❌ ❌ bsr[]
Rating sampleAvgRating rating rating avgRating sampleAvgRating sampleAvgRating rating[]
Reviews sampleAvgReviewCount ratingCount ratingCount reviewCount ❌ sampleAvgRatingCount ratingCount[]
Insights ❌ ❌ ❌ ✅ consumerInsights ❌ ❌ ❌
Concentration topSalesRate ❌ ❌ ❌ sampleTop3BrandSalesRate CR10 ❌
Opportunity ❌ ❌ ❌ ❌ sampleOpportunityIndex ❌ ❌

Confidence Labels (all skills)

  • 📊 Data-backed — direct API data
  • 🔍 Inferred — logical reasoning from data
  • 💡 Directional — suggestions, predictions

Strategy recommendations and subjective conclusions are NEVER 📊. Extreme growth (>200%) = 💡 only.

Data Notes

  • Sales (monthlySalesFloor) = lower-bound estimate
  • Realtime = live; products/competitors = ~T+1 delay
  • Amazon US only (amazon.com) — more marketplaces planned
  • Each call consumes credits; check meta.creditsConsumed

Links

Usage Guidance
This skill is internally consistent: it documents and implements an HTTP client for api.apiclaw.io and only requires APICLAW_API_KEY. Before installing: 1) Confirm you trust the API provider (https://apiclaw.io) and the repository homepage (the listed GitHub URL). 2) Supply the API key via an environment variable rather than committing it to files; if you create config.json in the skill directory, avoid storing secrets in shared repos. 3) Be aware API calls consume credits and are subject to rate limits (documented in SKILL.md). 4) If you need higher assurance, review scripts/apiclaw.py locally (it is included) to confirm there are no unexpected network calls or file accesses beyond the documented behavior.
Capability Analysis
Type: OpenClaw Skill Name: apiclaw-core Version: 1.1.1 The skill bundle provides a legitimate interface for the APIClaw Amazon commerce data service. The core logic in scripts/apiclaw.py uses standard Python libraries to interact with the official API endpoint (api.apiclaw.io) and includes robust error handling, rate limiting, and composite workflows for market analysis. No evidence of data exfiltration, malicious execution, or prompt injection was found; the instructions in SKILL.md are focused on ensuring the AI agent interprets commerce data correctly.
Capability Assessment
✓ Purpose & Capability
Name/description match the included materials: an 11-endpoint API client for APIClaw. The only required credential is APICLAW_API_KEY, which is exactly what a networked API client would need.
✓ Instruction Scope
SKILL.md and the script confine behavior to constructing POST requests to api.apiclaw.io, handling retries/rate-limits, and formatting results. The script will also look for a local config.json in the skill directory as a fallback for the key — this is local-scope behavior and is documented.
✓ Install Mechanism
No install spec (instruction-only) and no external download/install steps. A single Python CLI file is included; nothing in the manifest attempts to fetch or execute arbitrary remote code during install.
✓ Credentials
Only APICLAW_API_KEY is declared/used. The script checks that env var and optionally a config.json in the skill directory for the same key. No unrelated secrets or system credentials are requested.
✓ Persistence & Privilege
Skill is not forced always-on and does not request system-wide configuration changes. It reads a config.json located within the skill directory if present; it does not modify other skills or global agent settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install apiclaw-core
  3. After installation, invoke the skill by name or use /apiclaw-core
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.1
- Added author and homepage fields to SKILL metadata for improved attribution and discoverability. - Bumped version to 1.1.1. - No changes to functionality or API endpoints.
v1.1.0
Initial release
Metadata
Slug apiclaw-core
Version 1.1.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Apiclaw?

General overview, 11 API endpoints. AI-powered commerce data infrastructure with 200M+ Amazon products. Endpoints: category browsing, market metrics, product... It is an AI Agent Skill for Claude Code / OpenClaw, with 150 downloads so far.

How do I install Apiclaw?

Run "/install apiclaw-core" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Apiclaw free?

Yes, Apiclaw is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Apiclaw support?

Apiclaw is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Apiclaw?

It is built and maintained by apiclaw (@apiclaw); the current version is v1.1.1.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463556 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259610 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200551 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191226 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190235 · by oswalpalash

💬 Comments