Agent skill

Serpapi

SerpApi search engine results API via curl. An agent skill from nicepkg/ai-workflow.

Install Serpapi

skills CLI

$ npx skills add nicepkg/ai-workflow --skill serpapi -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install nicepkg/ai-workflow serpapi --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/nicepkg/ai-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/workflows/video-creator-workflow/.claude/skills/serpapi .claude/skills/serpapi && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "serpapi" agent skill from https://github.com/nicepkg/ai-workflow/tree/main/workflows/video-creator-workflow/.claude/skills/serpapi into .claude/skills/serpapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serpapi", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/nicepkg/ai-workflow/tree/main/workflows/video-creator-workflow/.claude/skills/serpapi

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add nicepkg/ai-workflow --skill serpapi -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install nicepkg/ai-workflow serpapi --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nicepkg/ai-workflow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/workflows/video-creator-workflow/.claude/skills/serpapi .agents/skills/serpapi && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "serpapi" agent skill from https://github.com/nicepkg/ai-workflow/tree/main/workflows/video-creator-workflow/.claude/skills/serpapi into .agents/skills/serpapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serpapi", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nicepkg/ai-workflow --skill serpapi -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install nicepkg/ai-workflow serpapi --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nicepkg/ai-workflow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/workflows/video-creator-workflow/.claude/skills/serpapi .cursor/skills/serpapi && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "serpapi" agent skill from https://github.com/nicepkg/ai-workflow/tree/main/workflows/video-creator-workflow/.claude/skills/serpapi into .cursor/skills/serpapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serpapi", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/nicepkg/ai-workflow.git --path workflows/video-creator-workflow/.claude/skills/serpapi

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add nicepkg/ai-workflow --skill serpapi -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install nicepkg/ai-workflow serpapi --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nicepkg/ai-workflow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/workflows/video-creator-workflow/.claude/skills/serpapi .gemini/skills/serpapi && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "serpapi" agent skill from https://github.com/nicepkg/ai-workflow/tree/main/workflows/video-creator-workflow/.claude/skills/serpapi into .gemini/skills/serpapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serpapi", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install nicepkg/ai-workflow serpapi

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add nicepkg/ai-workflow --skill serpapi -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/nicepkg/ai-workflow.git skills-src && mkdir -p .github/skills && cp -r skills-src/workflows/video-creator-workflow/.claude/skills/serpapi .github/skills/serpapi && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "serpapi" agent skill from https://github.com/nicepkg/ai-workflow/tree/main/workflows/video-creator-workflow/.claude/skills/serpapi into .github/skills/serpapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serpapi", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add nicepkg/ai-workflow --skill serpapi -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install nicepkg/ai-workflow serpapi --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/nicepkg/ai-workflow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/workflows/video-creator-workflow/.claude/skills/serpapi .opencode/skills/serpapi && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "serpapi" agent skill from https://github.com/nicepkg/ai-workflow/tree/main/workflows/video-creator-workflow/.claude/skills/serpapi into .opencode/skills/serpapi/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "serpapi", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: serpapi
GitHub stars: 285
Token cost: ~1.4k tokens
SKILL.md length: 428 words
Files: 1
Skills in repo: 61
Repo updated: Jan 20, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

SerpApi search engine results API via curl. An agent skill from nicepkg/ai-workflow.

Works in 9 steps: Basic Google Search → Search with Location → Google Image Search → …
Other search engines
SKILL.md covers When to Use, Prerequisites, How to Use and Supported Engines, plus 2 more sections
Calls bash and jq; reaches serpapi.com; needs SERPAPI_API_KEY and API_KEY

What it does

Serpapi is an agent skill from nicepkg/ai-workflow. SerpApi search engine results API via curl. Use this skill to scrape Google, Bing, YouTube, and other search engines.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Web scraping and Web search. It works with SerpApi, YouTube, Google Maps Platform and Bash. The repository describes itself as: 🚀 170+ pre-built skills for Claude Code, Cursor, Codex & 14+ AI tools. Stop re-teaching your AI the same things. One command → instant domain expertise. Marketing, SEO, Trading… The licence is MIT.

When your agent uses it

Other search engines
Tasks that involve Web scraping
Tasks that involve Web search

Example prompts

“/serpapi”

Requirements

A credential in SERPAPI_API_KEY
A credential in API_KEY

Workflow steps

9 steps, taken from the step headings in SKILL.md.

Basic Google Search
Search with Location
Google Image Search
Google News Search
Google Shopping Search
YouTube Search
Google Maps / Local Results
Pagination
Check Account Info

What it can do on your machine

Read from SKILL.md and the folder at commit d167b41. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- bash
- jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- serpapi.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- SERPAPI_API_KEY
- API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Serpapi loads about 1.4k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 428 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~31
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nicepkg/ai-workflow at commit d167b41, republished under its MIT licence (© nicepkg). 428 words, ~1,398 tokens.

Download SKILL.mdSave it as .claude/skills/serpapi/SKILL.md (or your agent's skills folder).

name: serpapi
description: SerpApi search engine results API via curl. Use this skill to scrape Google, Bing, YouTube, and other search engines.
vm0_secrets: SERPAPI_API_KEY

SerpApi

Use SerpApi via direct curl calls to scrape search engine results from Google, Bing, YouTube, and more.

Official docs: https://serpapi.com/search-api

When to Use

Use this skill when you need to:

Scrape Google search results (organic, ads, knowledge graph)
Search Google Images, News, Videos, Shopping
Get local business results from Google Maps
Scrape other search engines (Bing, YouTube, DuckDuckGo, etc.)
Monitor SERP rankings for SEO analysis

Prerequisites

Sign up at SerpApi
Go to Dashboard and copy your API key
Store it in the environment variable SERPAPI_API_KEY

bash

export SERPAPI_API_KEY="your-api-key"

Pricing

Free tier: 100 searches/month
API key is passed as a query parameter api_key

Important: When using $VAR in a command that pipes to another command, wrap the command containing $VAR in bash -c '...'. Due to a Claude Code bug, environment variables are silently cleared when pipes are used directly.
bash
bash -c 'curl -s "https://api.example.com" -H "Authorization: Bearer $API_KEY"'

How to Use

All examples below assume you have SERPAPI_API_KEY set.

Base URL: https://serpapi.com/search

1. Basic Google Search

Search Google and get structured JSON results:

bash

bash -c 'curl -s "https://serpapi.com/search?engine=google&q=artificial+intelligence&api_key=${SERPAPI_API_KEY}"' | jq '.organic_results[:3] | .[] | {title, link, snippet}

2. Search with Location

Search from a specific location:

bash

bash -c 'curl -s "https://serpapi.com/search?engine=google&q=best+coffee+shops&location=San+Francisco,+California&gl=us&hl=en&api_key=${SERPAPI_API_KEY}"' | jq '.organic_results[:3]'

Parameters:

location: City, state, or address
gl: Country code (us, uk, de, etc.)
hl: Language code (en, de, fr, etc.)

3. Google Image Search

Search for images:

bash

bash -c 'curl -s "https://serpapi.com/search?engine=google_images&q=sunset+beach&api_key=${SERPAPI_API_KEY}"' | jq '.images_results[:3] | .[] | {title, original, thumbnail}

4. Google News Search

Search news articles:

bash

bash -c 'curl -s "https://serpapi.com/search?engine=google_news&q=technology&api_key=${SERPAPI_API_KEY}"' | jq '.news_results[:3] | .[] | {title, link, source, date}

5. Google Shopping Search

Search products:

bash

bash -c 'curl -s "https://serpapi.com/search?engine=google_shopping&q=wireless+headphones&api_key=${SERPAPI_API_KEY}"' | jq '.shopping_results[:3] | .[] | {title, price, source}

6. YouTube Search

Search YouTube videos:

bash

bash -c 'curl -s "https://serpapi.com/search?engine=youtube&search_query=python+tutorial&api_key=${SERPAPI_API_KEY}"' | jq '.video_results[:3] | .[] | {title, link, channel, views}

7. Google Maps / Local Results

Search local businesses:

bash

bash -c 'curl -s "https://serpapi.com/search?engine=google_maps&q=restaurants&ll=@40.7128,-74.0060,15z&api_key=${SERPAPI_API_KEY}"' | jq '.local_results[:3] | .[] | {title, rating, address}

Parameters:

ll: Latitude, longitude, and zoom level (e.g., @40.7128,-74.0060,15z)

8. Pagination

Get more results using the start parameter:

bash

# First page (results 1-10)
bash -c 'curl -s "https://serpapi.com/search?engine=google&q=machine+learning&start=0&api_key=${SERPAPI_API_KEY}"' | jq '.organic_results | length'

# Second page (results 11-20)
bash -c 'curl -s "https://serpapi.com/search?engine=google&q=machine+learning&start=10&api_key=${SERPAPI_API_KEY}"' | jq '.organic_results | length'

Show full SKILL.md (173 more words)Show less

9. Check Account Info

Check your API usage and credits:

bash

bash -c 'curl -s "https://serpapi.com/account?api_key=${SERPAPI_API_KEY}"' | jq '{plan_name, searches_per_month, this_month_usage}

Supported Engines

Engine	Parameter	Description
Google Search	`engine=google`	Web search results
Google Images	`engine=google_images`	Image search
Google News	`engine=google_news`	News articles
Google Shopping	`engine=google_shopping`	Product search
Google Maps	`engine=google_maps`	Local businesses
YouTube	`engine=youtube`	Video search
Bing	`engine=bing`	Bing web search
DuckDuckGo	`engine=duckduckgo`	Privacy-focused search

Common Parameters

Parameter	Description
`q`	Search query (required)
`engine`	Search engine to use
`location`	Geographic location for search
`gl`	Country code (e.g., us, uk)
`hl`	Language code (e.g., en, de)
`start`	Pagination offset (0, 10, 20...)
`num`	Number of results (max 100)
`safe`	Safe search (`active` or `off`)
`device`	Device type (`desktop`, `mobile`, `tablet`)

Guidelines

Use specific engines: Use google_images, google_news etc. instead of tbm parameter for cleaner results
Add location for local searches: Use location and gl for geo-targeted results
Cache results: SerpApi caches results by default; use no_cache=true for fresh data
Monitor usage: Check /account endpoint to track API credits
Use jq filters: Filter large JSON responses to extract only needed data

Files

Just SKILL.md in workflows/video-creator-workflow/.claude/skills/serpapi of nicepkg/ai-workflow.

Open the folder on GitHubat commit d167b41

Compare with similar skills

Serpapi next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Serpapi compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Serpapi this skillnicepkg/ai-workflow	285	—	~1.4k	Automated safety check: Pass	MIT	8 mo ago
Apify Competitor Intelligencemajiayu000/claude-skill-registry	666	4 repos	~1.3k	Automated safety check: Notes	MIT	today
Google Maps ScraperMahanaicoach/google-maps-scraper-kit	1.3k	—	~2.8k	Automated safety check: Pass	MIT	2 days ago
Deepapidavidondrej/skills	4.1k	—	~2.5k	Automated safety check: Pass	MIT	today
Bright Data Best Practicesbrightdata/skills	264	1 repos	~3.6k	Automated safety check: Pass	MIT	today
Apify Audience Analysismajiayu000/claude-skill-registry	666	3 repos	~1.2k	Automated safety check: Notes	MIT	today

Similar skills

Apify Competitor Intelligence
majiayu000/claude-skill-registry
Analyze competitor strategies, content, pricing, ads, and market positioning across Google Maps, Booking.com, Facebook, Instagram, YouTube, and TikTok.
666 GitHub starsUsed in 4 repos~1.3k tokens
Data & AnalyticsAuto-check: notes
Google Maps Scraper
Mahanaicoach/google-maps-scraper-kit
Scrape Google Maps business listings (name, address, phone, website, rating, reviews, lat/lng, hours, emails) via the local gosom google-maps-scraper REST API.
1.3k GitHub stars~2.8k tokensUpdated 2 days ago
Data & AnalyticsAuto-check passed
Deepapi
davidondrej/skills
Use DeepAPI for all web search, deep research, and web scraping (websites, LinkedIn, GitHub, X/Twitter, YouTube, Instagram) instead of built-in search, research, fetch, or browser tools.
4.1k GitHub stars~2.5k tokensUpdated today
Data & AnalyticsAuto-check passed
Bright Data Best Practices
brightdata/skills
Build production-ready Bright Data integrations with best practices baked in.
264 GitHub starsUsed in 1 repo~3.6k tokens
Data & AnalyticsAuto-check passed
Apify Audience Analysis
majiayu000/claude-skill-registry
Understand audience demographics, preferences, behavior patterns, and engagement quality across Facebook, Instagram, YouTube, and TikTok.
666 GitHub starsUsed in 3 repos~1.2k tokens
Data & AnalyticsAuto-check: notes
Apify Brand Reputation Monitoring
majiayu000/claude-skill-registry
Scrape reviews, ratings, and brand mentions from multiple platforms using Apify Actors.
666 GitHub starsUsed in 3 repos~1.1k tokens
Data & AnalyticsAuto-check: notes

Questions about Serpapi

What does Serpapi do?

SerpApi search engine results API via curl. An agent skill from nicepkg/ai-workflow. Serpapi is an agent skill from nicepkg/ai-workflow. SerpApi search engine results API via curl.

When should I use Serpapi?

Serpapi fits situations like: other search engines; tasks that involve Web scraping; tasks that involve Web search.

How do I install Serpapi in Claude Code?

Run `npx skills add nicepkg/ai-workflow --skill serpapi -a claude-code`. Or copy the skill folder (workflows/video-creator-workflow/.claude/skills/serpapi in nicepkg/ai-workflow) into .claude/skills/serpapi in your project. Claude Code loads it when a task matches its description.

How do I install Serpapi in Codex?

Run `npx skills add nicepkg/ai-workflow --skill serpapi -a codex`. Or copy the skill folder (workflows/video-creator-workflow/.claude/skills/serpapi in nicepkg/ai-workflow) into .agents/skills/serpapi in your project. Codex loads it when a task matches its description.

Can I use Serpapi in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nicepkg/ai-workflow --skill serpapi -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/serpapi, .gemini/skills/serpapi, .github/skills/serpapi and .opencode/skills/serpapi in your project.

What does Serpapi need to run?

Going by SKILL.md and its folder, Serpapi needs the command-line tools its instructions call (bash and jq) and credentials named SERPAPI_API_KEY and API_KEY. Our summary lists: A credential in SERPAPI_API_KEY; A credential in API_KEY.

Does Serpapi access the network?

SKILL.md names 1 domain. In commands or code: serpapi.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Serpapi safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Serpapi use?

Serpapi is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Serpapi use?

About 1.4k tokens (SKILL.md is roughly 5.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Serpapi?

Skills that share tags, products or a category with Serpapi: Apify Competitor Intelligence (majiayu000/claude-skill-registry, 666 stars), Google Maps Scraper (Mahanaicoach/google-maps-scraper-kit, 1.3k stars), Deepapi (davidondrej/skills, 4.1k stars) and Bright Data Best Practices (brightdata/skills, 264 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Serpapi?

nicepkg (a GitHub organization) maintains it in nicepkg/ai-workflow, which has 285 GitHub stars. The repository holds 61 skills in this directory. The repository was last updated on January 20, 2026.

Source: nicepkg/ai-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Serpapi

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

SerpApi

When to Use

Prerequisites

Pricing

How to Use

1. Basic Google Search

2. Search with Location

3. Google Image Search

4. Google News Search

5. Google Shopping Search

6. YouTube Search

7. Google Maps / Local Results

8. Pagination

9. Check Account Info

Supported Engines

Common Parameters

Guidelines

Files

Compare with similar skills

Similar skills

More from nicepkg/ai-workflow

Related

Questions about Serpapi