378 skills · sorted by relevance
Design criteria for using an LLM to judge AI responses through scoring or comparisons between two answers. Includes checks for order and length bias, plus validation against human judgments to assess evaluation reliability.
Turns supplied AI agent evaluation results into reports that distinguish autonomous success, human-assisted success, failure, timeout, and invalid runs. Makes metric denominators, retries, timing, costs, and comparison conditions explicit to support evidence-based decisions.
Build end-to-end tests with Playwright and Cypress to check complete user workflows, such as login and checkout. Improve test reliability through stable element selection, independent test data, appropriate waits, and debugging with traces and screenshots.
Design application and API behavior when operations fail. Choose between exceptions and Result types, which explicitly represent success or failure, and improve retries, error messages, logging, and resource cleanup so failures are easier to handle and investigate.
Review cloud spending across AWS, Azure, GCP, and OCI. Guides resource sizing, discount commitments, storage policies, cost allocation tags, and budget alerts to identify waste and establish ongoing cost management while considering performance and reliability.
Check important factual claims in courses or supplied content against available materials and authoritative sources. Review numbers, definitions, and contradictions, then receive a concise report with evidence and suggested corrections, or have generated course pages checked before delivery.
Retrieve past operational experience from OpenViking before or during coding, configuration, deployment, or recovery work. It reads relevant records, checks whether their assumptions match the current environment, and applies suitable procedures and checks.
Review Azure infrastructure code and deployed resources against five Well-Architected Framework pillars. Identify configuration drift, classify risks, and produce remediation guidance and an architecture diagram, with GitHub issues created after user approval.
Design and refine prompts for language model applications. Choose useful examples, create reusable templates and system instructions, and compare prompt variations using accuracy, consistency, response time, and token usage to guide improvements.
Design and implement machine learning systems for production use. Cover data preparation, training, prediction services, model comparisons, monitoring, and retraining, with attention to reliability, response time, resource costs, and both technical and business evaluation metrics.
Integrate Stripe payments and subscriptions into web applications, including trials, prorated plan changes, usage billing, customer portals, and invoices. Follow implementation patterns and local testing steps, with webhook signature checks and duplicate event handling to support reliable billing updates.
Find the right skill among 37 advanced engineering options for architecture, development, automation, and operations. The index maps tasks to individual skills, helping you choose which instructions to load for a specific job.
Design and build backend services with API scaffolding, database migrations, authentication reviews, and load testing. Generate route handlers from OpenAPI specifications, identify PostgreSQL optimization opportunities, and compare architecture choices against traffic, data sensitivity, and reliability requirements.
Map repeatable business processes by owner and analyze time spent working, waiting, or reworking. Using stage-level timing data, produce a process diagram, ranked bottlenecks, and cycle-time measures to focus improvements on the main constraint.
Turn documentation, code, and specifications into reusable Agent Skills. Define when each skill should activate, organize supporting references, add reproducible examples, and check new or existing skills with templates, a checklist, and a validator.
Assess Google Cloud workloads for environmental sustainability using the Well-Architected Framework. Get recommendations on lower-carbon regions, efficient computing and storage, AI energy use, and ongoing emissions measurement with Carbon Footprint.
Define reliability goals for Google Cloud services and generate Terraform files for Cloud Monitoring SLO alerts. A guided conversation gathers service scope, measurement metrics, targets, and alert conditions, then explains the PromQL queries used to evaluate them.
Audits Google Cloud Filestore instances for missing or outdated backups, overly broad file share access, and zone isolation requirements. Produces a health scorecard, prioritized findings, an instance inventory, and proposed backup remediation.
Design Google Cloud infrastructure with Terraform, validate it locally, and assess the planned changes for security, cost, and reliability. The skill then imports templates into Application Design Center, deploys them, investigates failures, and checks the deployed services.
Plan and carry out research by refining questions, improving searches, evaluating sources, and checking claims across independent references. Turn findings into cited reports that explain the evidence, conflicting views, confidence levels, and remaining gaps.
Review 72 hours of Convex deployment health events and trace read limits or conflicting writes to the responsible code. Receive prioritized performance, cost, and reliability findings with runtime evidence, source locations, and concrete fixes.
Handle repeated tool failures by documenting what went wrong and which deliverables remain blocked. Produce useful partial work with clear limits, distinguish unverified content from completed work, and provide concrete steps for recovery or handoff.
Extract plain text from Word DOCX files using shell commands first, then switch to Python's built-in ZIP reader if extraction fails or returns nothing. Supports text output without requiring the external python-docx package.
Find reusable skills in OpenSpace's local registry and explore its cloud library when needed. Review matching skills, choose where to import them locally, and decide whether to follow them or delegate the task.