Skip to content

nexscope-ai/nexscope-ecommerce-skills / ecommerce-product-ai-visibility

ecommerce.product-ai-visibility

Verified

Product AI Visibility & Ranking — evaluate how AI search engines (ChatGPT, Claude, Gemini, DeepSeek) recommend your product when shoppers ask buying questions. Triggers: AI visibility, product AI ranking, AI recommend, AI search, does AI mention my product.

FileKindSize
.nexscope-manifest.jsonconfig230 B
SKILL.mdskill md14.3 KB
assets/config.jsonconfig388 B
assets/prompts/evaluator.mdmarkdown9.1 KB
config.jsonconfig392 B
profiles/_template/product.mdmarkdown878 B
profiles/_template/queries.csvother1.5 KB
profiles/_template/query_rules.mdmarkdown1.2 KB
profiles/airscape-planetary-design-kilo-coffee-st/product.mdmarkdown1.9 KB
profiles/airscape-planetary-design-kilo-coffee-st/queries.csvother3.2 KB
profiles/airscape-planetary-design-kilo-coffee-st/query_rules.mdmarkdown525 B
profiles/aisi-hair-ombre-blonde-wig-glueless-curl/product.mdmarkdown1.2 KB
profiles/aisi-hair-ombre-blonde-wig-glueless-curl/queries.csvother2.6 KB
profiles/aisi-hair-ombre-blonde-wig-glueless-curl/query_rules.mdmarkdown428 B
profiles/apple-airpods-pro-3/product.mdmarkdown1.1 KB
profiles/apple-airpods-pro-3/queries.csvother2.2 KB
profiles/apple-airpods-pro-3/query_rules.mdmarkdown737 B
profiles/coffee-canister/product.mdmarkdown1.4 KB
profiles/coffee-canister/queries.csvother1.3 KB
profiles/coffee-canister/query_rules.mdmarkdown356 B
profiles/define-jacket-nulu/product.mdmarkdown1.1 KB
profiles/define-jacket-nulu/queries.csvother2.2 KB
profiles/define-jacket-nulu/query_rules.mdmarkdown736 B
profiles/iphone-17-pro/product.mdmarkdown1.3 KB
profiles/iphone-17-pro/queries.csvother2.2 KB
profiles/iphone-17-pro/query_rules.mdmarkdown731 B
profiles/macbook-air-m5/product.mdmarkdown1.0 KB
profiles/macbook-air-m5/queries.csvother2.1 KB
profiles/macbook-air-m5/query_rules.mdmarkdown732 B
profiles/rare-beauty/product.mdmarkdown1.5 KB
profiles/rare-beauty/queries.csvother1.6 KB
profiles/rare-beauty/query_rules.mdmarkdown1.1 KB
profiles/stanley-quencher-h2-0-flowstate-tumbler-/product.mdmarkdown1.4 KB
profiles/stanley-quencher-h2-0-flowstate-tumbler-/queries.csvother2.5 KB
profiles/stanley-quencher-h2-0-flowstate-tumbler-/query_rules.mdmarkdown763 B
scripts/__init__.pyscript0 B
scripts/_next_steps.pyscript10.1 KB
scripts/api_capture_runner.pyscript9.0 KB
scripts/api_client_base.pyscript8.2 KB
scripts/cli.pyscript10.0 KB
scripts/evaluator.pyscript6.9 KB
scripts/html_report.pyscript43.9 KB
scripts/loader.pyscript4.4 KB
scripts/normalizer.pyscript3.0 KB
scripts/preaggregate.pyscript7.0 KB
scripts/profile_builder.pyscript9.5 KB
scripts/send_report_email.pyscript4.4 KB
scripts/task_builder.pyscript2.7 KB
scripts/test_raw_api.pyscript2.6 KB
tmp-tr_4cc43ce22aaa/product_info.jsonconfig2.0 KB
tmp-tr_be2fd13607b6/product_info.jsonconfig2.1 KB

scripts/test_raw_api.py

View on GitHub
import json, sys, os, re, time
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from api_client_base import GATEWAY_BASE_URL, GATEWAY_API_KEY, CURRENT_YEAR
import requests

query = "best coffee canister for fresh beans " + CURRENT_YEAR
system_prompt = "You are a helpful shopping assistant. Recommend specific products with prices and where to buy."

url = GATEWAY_BASE_URL + "/chat/completions"
headers = {"Authorization": "Bearer " + GATEWAY_API_KEY, "Content-Type": "application/json"}
payload = {
    "model": "global.anthropic.claude-sonnet-4-6",
    "messages": [
        {"role": "system", "content": system_prompt},
        {"role": "user", "content": query}
    ],
    "tools": [{"type": "web_search"}],
    "temperature": 0.7,
    "max_tokens": 4096
}

print("Calling API with web_search tool...")
resp = requests.post(url, headers=headers, json=payload, timeout=120)
print("Status:", resp.status_code)
data = resp.json()

with open("/tmp/raw_response_claude.json", "w") as f:
    json.dump(data, f, indent=2, ensure_ascii=False)

print("Top-level keys:", list(data.keys()))
if "choices" in data:
    msg = data["choices"][0].get("message", {})
    print("Message keys:", list(msg.keys()))
    if "annotations" in msg:
        anns = msg["annotations"]
        print("Annotations count:", len(anns))
        for a in anns[:3]:
            print("  ", json.dumps(a, ensure_ascii=False)[:200])
    if "tool_calls" in msg:
        tcs = msg["tool_calls"]
        print("Tool calls count:", len(tcs))
        for tc in tcs[:2]:
            print("  ", json.dumps(tc, ensure_ascii=False)[:300])
    content = msg.get("content", "")
    if isinstance(content, list):
        print("Content is LIST, blocks:", len(content))
        for i, block in enumerate(content[:10]):
            if isinstance(block, dict):
                btype = block.get("type", "unknown")
                print(f"  [{i}] type={btype} keys={list(block.keys())}")
                if "url" in str(block.get("type","")) or "search" in str(block.get("type","")) or "citation" in str(block.get("type","")):
                    print("      ", json.dumps(block, ensure_ascii=False)[:500])
            elif isinstance(block, str):
                print(f"  [{i}] text len={len(block)}")
    elif isinstance(content, str):
        print("Content is string, length=", len(content))
        urls = re.findall(r"https?://[^\s\)]+", content)
        print("URLs in text:", len(urls))
        for u in urls[:5]:
            print(" ", u)
    if "citations" in msg:
        print("msg.citations:", json.dumps(msg["citations"], ensure_ascii=False)[:500])

print("Full response saved to /tmp/raw_response_claude.json")
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall