DEV Community: Scavio AI

How to give your OpenClaw agent Access To Youtube Real-Time Data in Less Than 2 Minutes

Scavio AI — Thu, 02 Apr 2026 07:20:27 +0000

Your OpenClaw agent can't watch YouTube. But it can read it — if you give it the right skill.

This is particularly useful for RAG pipelines. YouTube tutorials stay more current than official docs for fast-moving topics like LangChain, CrewAI, or new model releases. Instead of asking your agent to summarize a video it can't access, give it the actual transcript.

1. Install the skill

clawhub install scavio-youtube

2. Set your API key

Get a free key at scavio.dev (1,000 credits/month, no card), then:

export SCAVIO_API_KEY=sk_live_your_key

3. Ask your agent

Your agent can now search YouTube, pull video metadata, and extract transcripts:

Find the most-viewed LangChain tutorial from this year and summarize what it covers.

Search YouTube for CrewAI getting started videos and tell me which one has the most views.

Get the transcript for video sVcwVQRHIc8 and explain the main steps it covers.

The skill covers four endpoints: search, metadata, transcript, and trainability check. Your agent picks the right one based on what you're asking.

What comes back

Search returns video ID, title, channel, view count, duration, publish date, and thumbnail.

Transcript returns timestamped text segments — your agent can inject these directly into context and answer questions grounded in the actual video content.

Metadata returns views, likes, comments, tags, categories, and channel info.

Trainability returns whether the video has captions, what languages, its license, and whether it's suitable for AI training.

Direct API access

import os, requests

BASE = "https://api.scavio.dev"
HEADERS = {"Authorization": f"Bearer {os.environ['SCAVIO_API_KEY']}"}

# Search (note: parameter is "search" not "query")
results = requests.post(f"{BASE}/api/v1/youtube/search", headers=HEADERS,
    json={"search": "langchain tutorial", "sort_by": "view_count"}).json()

# Transcript
video_id = results["data"][0]["videoId"]
transcript = requests.post(f"{BASE}/api/v1/youtube/transcript", headers=HEADERS,
    json={"video_id": video_id, "language": "en"}).json()

text = " ".join(seg["text"] for seg in transcript["data"])

Full docs at scavio.dev/docs

(I work with the Scavio team.)

How to give your OpenClaw agent Access To Walmart Data in Less Than 2 Minutes

Scavio AI — Wed, 01 Apr 2026 20:38:56 +0000

If you're building a shopping or price comparison agent with OpenClaw, Amazon alone isn't enough. A lot of US retail happens at Walmart — and Walmart has data Amazon doesn't, like in-store availability, same-day pickup, and local pricing by ZIP code.

Here's how to add it.

1. Install the skill

clawhub install scavio-walmart

2. Set your API key

Get a free key at scavio.dev (1,000 credits/month, no card), then:

export SCAVIO_API_KEY=sk_live_your_key

3. Ask your agent

Your agent can now search Walmart products and look up product details by ID:

Find standing desks under $300 on Walmart sorted by best seller.

Search Walmart for air purifiers that can be delivered by tomorrow to ZIP code 10001.

Look up Walmart product 123456789 and give me the full details including current price and availability.

The skill covers both product search (with price range, sort, fulfillment speed, delivery ZIP, and in-store filters) and full product detail lookup by Walmart product ID.

What makes this different from Amazon

Walmart-specific filters your agent can use:

fulfillment_speed — today, tomorrow, 2_days, anytime
fulfillment_type — in_store for click-and-collect
delivery_zip — localized pricing and availability by ZIP code
store_id — filter to a specific Walmart store

These don't exist in the Amazon skill. If your agent needs to answer "can I get this today near me?", Walmart is the right call.

Pair with scavio-amazon for price comparison

Install both skills and your agent can compare prices across retailers automatically:

Compare the price of Sony WH-1000XM5 headphones on Amazon and Walmart.

Both skills return the same JSON structure so the agent can reason over them together without any adapter logic.

Direct API access

import os, requests

response = requests.post(
    "https://api.scavio.dev/api/v1/walmart/search",
    headers={"Authorization": f"Bearer {os.environ['SCAVIO_API_KEY']}"},
    json={"query": "standing desk", "sort_by": "best_seller", "max_price": 300},
)
print(response.json()["data"])

Full docs at scavio.dev/docs

(I work with the Scavio team.)

How to give your OpenClaw agent Access To Real-time SERP - Google Search Data in Less Than 2 Minutes

Scavio AI — Wed, 01 Apr 2026 12:11:41 +0000

By default your OpenClaw agent only knows what it already knows. The moment it needs to look something up — check a fact, find documentation, get current news — it has no way to reach the web.

Here's how to fix that.

1. Install the skill

clawhub install scavio-google

2. Set your API key

Get a free key at scavio.dev (1,000 credits/month, no card), then:

export SCAVIO_API_KEY=sk_live_your_key

The skill won't load without this — it gates on SCAVIO_API_KEY so you get a clear error rather than a silent failure.

3. Ask your agent

That's it. Your agent can now search Google. Just ask it naturally:

Search for the latest LangChain agent tools and summarize what you find.

Find recent news about AI funding rounds this week.

Look up the documentation for CrewAI tool calling and explain how it works.

The skill teaches your agent when to use Google search, how to call the API, and how to interpret the results — including news, images, maps, and knowledge graph data depending on what you're asking for.

What comes back

The agent gets structured JSON — titles, URLs, descriptions, position — not raw HTML. It can reason over the results directly without any parsing step.

For news queries it also gets source, date, and domain. For full-mode queries (2 credits) it gets knowledge graph, people also ask, and related searches.

Direct API access

If you want to call the API yourself outside of OpenClaw:

import os, requests

response = requests.post(
    "https://api.scavio.dev/api/v1/google",
    headers={"Authorization": f"Bearer {os.environ['SCAVIO_API_KEY']}"},
    json={"query": "langchain agent tools", "search_type": "classic"},
)
print(response.json()["results"])

Full docs at scavio.dev/docs

(I work with the Scavio team.)

How to give your OpenClaw agent Access To Amazon Data in 2 Minutes

Scavio AI — Tue, 31 Mar 2026 20:17:49 +0000

Want your OpenClaw agent to look up product prices, find ASINs, or research what's on Amazon? Out of the box it can't — there's no Amazon search built in.

Here's how to add it.

1. Install the skill

clawhub install scavio-amazon

2. Set your API key

Get a free key at scavio.dev (1,000 credits/month, no card), then:

export SCAVIO_API_KEY=sk_live_your_key

3. Ask your agent

Your agent can now search Amazon and look up products by ASIN:

Find the best-reviewed mechanical keyboards under $100 on Amazon.

Look up ASIN B09XS7JWHH and tell me the price, rating, and key features.

Search Amazon Germany for standing desks and find the top 3 by rating.

The skill covers both product search (with sorting, pagination, category, and marketplace filters) and full product detail lookup by ASIN. It supports 12 Amazon marketplaces — com, co.uk, de, fr, co.jp, ca, it, es, in, com.au, com.br, com.mx.

What comes back

The agent gets structured JSON with name, ASIN, URL, price, currency, rating, review count, Prime status, best seller flag, and image URL. For product detail lookups it also gets description, feature bullets, categories, availability, and seller info.

Direct API access

import os, requests

# Search
response = requests.post(
    "https://api.scavio.dev/api/v1/amazon/search",
    headers={"Authorization": f"Bearer {os.environ['SCAVIO_API_KEY']}"},
    json={"query": "mechanical keyboard", "sort_by": "average_review"},
)
print(response.json()["data"])

# Product by ASIN
response = requests.post(
    "https://api.scavio.dev/api/v1/amazon/product",
    headers={"Authorization": f"Bearer {os.environ['SCAVIO_API_KEY']}"},
    json={"query": "B09XS7JWHH"},
)
print(response.json()["data"])

Full docs at scavio.dev/docs

(I work with the Scavio team.)