Skip to main content Startseite Ersteller agents-store claude-plugins sdk-patterns
sdk-patterns This skill should be used when the user asks about "Firecrawl SDK", "Exa SDK", "exa-js", "exa-py", "Perplexity SDK", "Jina SDK", "web search client library", "search npm package", "search Python package", or needs code patterns for integrating web search services into a project.
Zur Installation springen Skills Marktplatz Entdecken und erkunden Sie KI-Skills, die von der Community erstellt wurden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Prompt-Details anzeigen Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
npx skills add https://github.com/Agents-Store/claude-plugins --skill sdk-patternsDer Befehl bleibt in einer Zeile. Scrollen Sie horizontal, um ihn vor dem Kopieren vollständig zu prüfen.
Sie bevorzugen eine lokale Kopie? Laden Sie die Dateien herunter, die SkillsMP derzeit vorliegen.
ZIP herunterladen Herunterladen... Mehr aus diesem Repository
Verwandte Berufe SOC
Basierend auf der SOC-Berufsklassifikation
name sdk-patterns description This skill should be used when the user asks about "Firecrawl SDK", "Exa SDK", "exa-js", "exa-py", "Perplexity SDK", "Jina SDK", "web search client library", "search npm package", "search Python package", or needs code patterns for integrating web search services into a project.
Web Search Services SDK Patterns
Code patterns for integrating Firecrawl, Exa, Perplexity, and Jina into application code.
Firecrawl
Installation
npm install firecrawl
pip install firecrawl-py
TypeScript
import { Firecrawl } from 'firecrawl' ;
const firecrawl = new Firecrawl ({ apiKey : process.env .FIRECRAWL_API_KEY });
const result = await firecrawl.scrape ('https://example.com' , {
formats : ['markdown' , 'links' ],
});
console .log (result.markdown );
const searchResults = await
search
'Next.js tutorials'
limit
10
const
await
crawl
'https://docs.example.com'
limit
50
const
await
startCrawl
'https://docs.example.com'
limit
50
const
await
getCrawlStatus
id
const
await
map
'https://example.com'
const
await
batchScrape
'https://example.com/a'
'https://example.com/b'
options
formats
'markdown'
const
await
extract
urls
'https://example.com/pricing'
prompt
'Extract pricing plans'
schema
type
'array'
items
type
'object'
properties
plan
type
'string'
price
type
'string'
v4 also adds interact() / stopInteraction() for live browser-session page manipulation.
Python from firecrawl import Firecrawl
firecrawl = Firecrawl(api_key=os.environ["FIRECRAWL_API_KEY" ])
doc = firecrawl.scrape("https://example.com" , formats=["markdown" ])
print (doc.markdown)
results = firecrawl.search("Next.js tutorials" , limit=10 )
crawl = firecrawl.crawl("https://docs.example.com" , limit=50 )
Exa
Installation npm install exa-js
pip install exa-py
TypeScript import Exa from 'exa-js' ;
const exa = new Exa (process.env .EXA_API_KEY );
const results = await exa.search ('React hooks best practices' , {
numResults : 10 ,
type : 'auto' ,
});
const withContent = await exa.search ('Prisma ORM examples' , {
numResults : 5 ,
contents : {
text : { maxCharacters : 5000 },
highlights : { maxCharacters : 200 },
},
});
const githubResults = await exa.search ('authentication middleware' , {
numResults : 10 ,
includeDomains : ['github.com' ],
});
const similar = await exa.findSimilar ('https://example.com/article' , {
numResults : 10 ,
});
const { answer } = await exa.answer ('What changed in React 19 server components?' );
const run = await exa.agent .runs .create ({
query : 'Compare the top 3 vector databases for a Next.js RAG app' ,
effort : 'auto' ,
});
const finished = await exa.agent .runs .pollUntilFinished (run.id );
Python from exa_py import Exa
exa = Exa(api_key=os.environ["EXA_API_KEY" ])
results = exa.search(
"React hooks patterns" ,
num_results=10 ,
type ="auto"
)
with_content = exa.search(
"Prisma examples" ,
num_results=5 ,
contents={"text" : {"max_characters" : 5000 }}
)
Perplexity
Installation npm install @perplexity-ai/perplexity_ai
pip install perplexityai
TypeScript import { Perplexity } from '@perplexity-ai/perplexity_ai' ;
const client = new Perplexity ({ apiKey : process.env .PERPLEXITY_API_KEY });
const response = await client.responses .create ({
preset : 'low' ,
input : 'Compare tRPC vs GraphQL for Next.js' ,
});
const sonarResponse = await client.chat .completions .create ({
model : 'sonar-pro' ,
messages : [
{ role : 'user' , content : 'What are the latest React 19 features?' },
],
});
const searchResults = await client.search .create ({
query : 'React 19 new features' ,
max_results : 5 ,
});
Python from perplexity import Perplexity
client = Perplexity()
response = client.responses.create(
preset="low" ,
input ="Compare tRPC vs GraphQL for Next.js"
)
sonar_response = client.chat.completions.create(
model="sonar-pro" ,
messages=[{"role" : "user" , "content" : "React 19 features" }]
)
search_results = client.search.create(query="React 19 new features" , max_results=5 )
Jina Jina's API is HTTP-based — no dedicated SDK package needed. Use fetch or requests directly.
TypeScript
const response = await fetch ('https://r.jina.ai/https://nextjs.org/docs' , {
headers : { 'Authorization' : `Bearer ${process.env.JINA_API_KEY} ` },
});
const markdown = await response.text ();
const searchResponse = await fetch ('https://s.jina.ai/?q=React+hooks' , {
headers : {
'Authorization' : `Bearer ${process.env.JINA_API_KEY} ` ,
'Accept' : 'application/json' ,
},
});
const results = await searchResponse.json ();
const embedResponse = await fetch ('https://api.jina.ai/v1/embeddings' , {
method : 'POST' ,
headers : {
'Authorization' : `Bearer ${process.env.JINA_API_KEY} ` ,
'Content-Type' : 'application/json' ,
},
body : JSON .stringify ({
model : 'jina-embeddings-v5-text-small' ,
input : ['text to embed' ],
}),
});
Python import requests
headers = {"Authorization" : f"Bearer {os.environ['JINA_API_KEY' ]} " }
response = requests.get("https://r.jina.ai/https://example.com" , headers=headers)
markdown = response.text
search = requests.get(
"https://s.jina.ai/" ,
params={"q" : "React hooks" },
headers={**headers, "Accept" : "application/json" }
)
results = search.json()
rerank = requests.post(
"https://api.jina.ai/v1/rerank" ,
headers={**headers, "Content-Type" : "application/json" },
json={
"model" : "jina-reranker-v3.5" ,
"query" : "best database for real-time" ,
"documents" : ["PostgreSQL" , "Redis" , "MongoDB" ]
}
)
Best Practices
Store API keys in environment variables, never in code
Handle rate limits with exponential backoff
Use the appropriate service for each task (see mcp-patterns routing table)
Prefer SDK methods over raw HTTP when SDK is available
Use TypeScript types for type safety when integrating search results
