← Back to Skills Marketplace
576
Downloads
0
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install google-search-serper
Description
Google Search powered by Serper.dev API — 9 search types: web, news, images, videos, places, shopping, scholar, patents, autocomplete. Returns Knowledge Grap...
README (SKILL.md)
Google Search Skill
Google Search powered by Serper.dev API. Replaces Brave Search with richer results including Knowledge Graph, Answer Box, People Also Ask, and specialized search types.
When to Use
Use this skill for any Google search request. Auto-detect intent:
- Default →
search - "news about X" / "latest X" →
news - "images of X" / "pictures of X" →
images - "videos of X" / "how to X video" →
videos - "restaurants near X" / "X near me" →
places - "how much does X cost" / "buy X" →
shopping(⚠️ 2 credits — only when explicitly requested) - "papers on X" / "research about X" →
scholar - "patents for X" →
patents - "suggestions for X" →
suggest
Usage
SCRIPT_DIR="~/.openclaw/workspace/skills/google-search/scripts"
# Web search (default)
npx tsx $SCRIPT_DIR/google-search.ts search "query" [--num 10] [--time day|week|month|year] [--country us] [--lang en]
# Specialized
npx tsx $SCRIPT_DIR/google-search.ts news "query" [--num 10]
npx tsx $SCRIPT_DIR/google-search.ts images "query"
npx tsx $SCRIPT_DIR/google-search.ts videos "query"
npx tsx $SCRIPT_DIR/google-search.ts places "query"
npx tsx $SCRIPT_DIR/google-search.ts shopping "query"
npx tsx $SCRIPT_DIR/google-search.ts scholar "query" [--year 2023]
npx tsx $SCRIPT_DIR/google-search.ts patents "query"
npx tsx $SCRIPT_DIR/google-search.ts suggest "query"
npx tsx $SCRIPT_DIR/google-search.ts credits
Add --json to any command for raw JSON output.
Setup
Requires a free API key from Serper.dev:
- Sign up at https://serper.dev (2,500 free searches included)
- Copy your API key from the dashboard
- Add to your environment:
export SERPER_API_KEY=your_key_here
If the key is missing, remind the user to sign up at serper.dev — it's free and takes 30 seconds.
Workflow
- Run the appropriate search command
- Parse the formatted output
- If deeper content is needed, use
web_fetchon promising links - Credit balance is shown in every response — monitor usage
- Shopping costs 2 credits — only use when user explicitly asks for prices/shopping
Time Filters
--time accepts: hour, day, week, month, year (or h, d, w, m, y)
Notes
- Rate limit: 5 req/sec on free tier
- All searches cost 1 credit except shopping (2 credits)
- Results include rich data: Knowledge Graph, Answer Box, People Also Ask, Related Searches
Usage Guidance
This skill appears to do what it says: it sends queries to https://google.serper.dev using the SERPER_API_KEY. Before installing, verify you are comfortable sending your search queries to Serper.dev (queries and any included sensitive text will leave your environment). Ensure you set SERPER_API_KEY in your environment (package.json and SKILL.md require it). Note the registry metadata in the submission omitted the required env var — that mismatch is likely a packaging oversight but double-check the manifest presented by your installer. Be mindful of credit usage (free tier limits and shopping costs 2 credits) and that the agent may fetch external result links (web_fetch) which can retrieve arbitrary remote content. If you want stricter control, limit agent autonomy or review the included scripts locally before enabling the skill.
Capability Analysis
Type: OpenClaw Skill
Name: google-search-serper
Version: 1.0.3
The skill is a legitimate wrapper for the Serper.dev API to provide Google Search capabilities. It follows standard practices by using an environment variable (SERPER_API_KEY) for authentication and making authorized POST requests to the official Serper.dev endpoint (google.serper.dev). No evidence of data exfiltration, malicious execution, or prompt injection was found in the code (google-search.ts, serper.ts) or instructions (SKILL.md).
Capability Assessment
Purpose & Capability
The name/description match the implementation: the scripts call https://google.serper.dev endpoints for the listed search types. One minor inconsistency: the registry metadata at the top of the report lists "Required env vars: none / Primary credential: none," while package.json and SKILL.md declare SERPER_API_KEY as the primary environment variable — the key is required for the stated purpose and appears in code.
Instruction Scope
SKILL.md instructs the agent to run the included Node script, parse results, and optionally use web_fetch on promising links. All operations described are within the scope of performing web searches and follow-ups; the only external transmissions are search queries to serper.dev and optional fetches of result URLs.
Install Mechanism
There is no install spec that downloads arbitrary code. This is effectively an instruction+script skill: it expects Node.js 18+ (native fetch) and runs local TypeScript via npx/tsx. No remote installers, URL-shortened downloads, or archive extraction are present.
Credentials
The only sensitive item required is SERPER_API_KEY, which is appropriate and necessary to call Serper.dev. The earlier registry metadata omission of this env var is an inconsistency in the package manifest/registry listing (but not a functional problem in the files). No other credentials or broad config paths are requested.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide settings. It can be invoked by the agent (normal behavior) but does not demand permanent elevated presence.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install google-search-serper - After installation, invoke the skill by name or use
/google-search-serper - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Added a YAML metadata block to SKILL.md with name and an expanded description.
- Description now clearly lists all 9 supported Google search types and when to use the skill.
- No CLI or usage changes; documentation content retained below new metadata.
- Improved guidance on when to use this skill versus Brave Search.
v1.0.2
- Updated dependency versions in package.json for improved stability and compatibility.
- No changes to usage, interface, or functionality.
v1.0.1
- Added setup instructions for obtaining a free Serper.dev API key, including signup link and environment variable setup.
- Now includes a user reminder to sign up for Serper.dev if the API key is missing.
- Clarified "Environment" section to "Setup" with step-by-step API key guidance.
v1.0.0
Initial release: 9 Google search types via Serper.dev — web, news, images, videos, places, shopping, scholar, patents, autocomplete. 2,500 free searches.
Metadata
Frequently Asked Questions
What is Google Search (Serper.dev)?
Google Search powered by Serper.dev API — 9 search types: web, news, images, videos, places, shopping, scholar, patents, autocomplete. Returns Knowledge Grap... It is an AI Agent Skill for Claude Code / OpenClaw, with 576 downloads so far.
How do I install Google Search (Serper.dev)?
Run "/install google-search-serper" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Google Search (Serper.dev) free?
Yes, Google Search (Serper.dev) is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Google Search (Serper.dev) support?
Google Search (Serper.dev) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Google Search (Serper.dev)?
It is built and maintained by minilozio (@minilozio); the current version is v1.0.3.
More Skills