Analyze Apify spending from Actor run history and tune memory, crawl duration, and proxy traffic. Produce cost comparisons and monthly reports, with an optional budget guard that stops runs once spending exceeds a set limit.
Deploy Apify Actors, programs that collect web data, and connect their results to external applications. Build API routes, completion notifications, or scheduled pipelines that retrieve structured data and export CSV files.
Build an Apify Actor that crawls web pages with Crawlee, extracts structured data, and stores results in a dataset. Define its input schema, test it locally, deploy it to Apify, and retrieve results through the Apify client when needed.
Build Claude API integrations that handle streamed responses, bulk requests through Message Batches, and background jobs through queues. Track completion, authenticate internal callbacks, suppress duplicate results, and record processing outcomes without logging raw content.
Use the Apify JavaScript client to manage datasets, key-value stores, and request queues. Export scraped records as CSV, JSON, or XLSX, keep files and configuration, resume queued requests, and chain Actors into scrape, transform, and export pipelines while monitoring run status and cost.
Learn the basic Apify integration pattern: call a public Actor, wait for its run to finish, check its status, and retrieve scraped records from the default dataset using apify-client.
Set up separate Claude API configurations for development, staging, and production. The skill maps each environment to its own workspace and credentials, applies model and spend limits, and guides isolation checks and a reviewed canary before promotion.
Upgrade the Anthropic Python or TypeScript SDK and adapt applications to API changes such as moving from Text Completions to Messages. Review breaking changes, update request shapes and streaming code, run compatibility checks, and keep a rollback path for the release.
Set up Apify webhooks, HTTP notifications sent when Actor runs change status. Build handlers that fetch results, report failures, prevent duplicate processing, and start subsequent Actors, with notifications configured for every run or just one.
Create a shared API contract that defines endpoint routes, request and response schemas, TypeScript interfaces, pagination, and error formats. It helps frontend and backend agents implement against the same agreed specification.
Measure and improve Claude API performance through prompt caching, model selection, streaming, and controlled parallel requests. It compares latency, token use, throughput, and quality to document which configuration changes help.
Plan capacity and load tests for services using Claude API. Estimate request and token demand, measure latency and costs, and evaluate queues, shared rate limiting, and scaling within the organization's API limits.
Choose and plan a Claude API architecture for interactive requests, background jobs, or model routing. The skill lays out service components, failure handling, and safeguards so a team can test a selected pattern before production use.
Secure applications using the Claude API through key management, input checks, defenses against malicious instructions, and sensitive data screening. Test these controls in a sandbox and produce a verification record without exposing credentials or user content.
Set up GitHub Actions to build, test, and deploy Apify Actors, the programs that run on Apify. Add pull request checks, live API integration tests, Docker build verification, and basic execution checks after deployment.
Prepare Apollo.io integrations for production on Vercel, GCP Cloud Run, or Kubernetes. Provides deployment configurations, secure API key handling, connectivity health checks, and validation scripts to check readiness before release.
Set up local development for Apify Actors, programs that automate data collection. Create a project, define inputs, run it with the Apify CLI, and inspect stored results while repeating edits and tests before deployment.
Review Claude API integrations before production launch, covering credentials, error handling, costs, monitoring, and content safety. Collect test evidence, assess a limited rollout, and document approvals and rollback readiness.
Review Anthropic API integrations for common mistakes in SDK imports, request fields, response parsing, tool results, retries, and token limits. Use synthetic test cases to identify issues and produce a redacted review summary without exposing prompts, customer data, or credentials.
Use this skill to add application-level rules around Claude API requests and responses. It covers input checks, sensitive-output filtering, topic and model limits, per-user and global budgets, and safe policy testing with synthetic cases and aggregate records.
Use these TypeScript patterns to build Apify Actors with Crawlee or call Actors through apify-client. Examples cover crawler choice, datasets and key-value stores, proxies, typed wrappers, and handling failed requests without stopping a crawl.
Set up the official Anthropic SDK for Python or TypeScript, configure the ANTHROPIC_API_KEY environment variable, and make a small Messages API request to check authentication. Includes package installation steps and notes for proxy and deployment environments.
Set up a local development loop for Claude API projects with a reusable client, mock responses, request logging, and hot reload. Run routine tests without API calls, track model and token usage, and enable live requests deliberately when checking real API behavior.
Design Apify data collection systems using a standalone scraper, a multi-stage pipeline, or an application integration. Get directory layouts, TypeScript skeletons, input validation, configuration patterns, and health checks suited to the chosen structure.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)