Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 404 files from 1 741 authors, of which 61 763 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
| Validate messaging consistency across website, GitHub repos, and local documentation generating read-only discrepancy reports. Use when checking content alignment or finding mixed messaging. Trigger with phrases like "check consistency", "validate documentation", or "audit messaging".
|
| A B Test Config Creator - Auto-activating skill for ML Deployment. Part of the ML Deployment skill category.
| Ab Test Analyzer - Auto-activating skill for Data Analytics. Part of the Data Analytics skill category.
| Configure CI/CD pipeline for Abridge clinical AI integrations with GitHub Actions. Use when setting up automated testing, FHIR validation, HIPAA compliance checks, or deployment pipelines for healthcare AI applications. "abridge automated testing", "abridge CI/CD".
| Diagnose and fix common Abridge clinical AI integration errors. Use when encountering EHR connectivity failures, note generation errors, audio streaming issues, or FHIR validation problems with Abridge. "fix abridge issue", "abridge troubleshoot".
| Implement Abridge ambient clinical documentation capture-to-note pipeline. transcription, AI note generation, and EHR note insertion. "ambient documentation workflow", "abridge note generation".
| Implement Abridge patient-facing documentation and after-visit summary generation. Use when building patient portal integration, generating plain-language summaries, multi-language translations, or after-visit instructions from clinical encounters. "abridge patient-facing", "abridge multilingual".
| Optimize Abridge clinical AI costs through tier selection, session management, and usage monitoring for healthcare organizations. Use when analyzing Abridge billing, optimizing encounter volume, or right-sizing your Abridge contract for provider count. "abridge budget", "abridge ROI".
| Collect Abridge debug evidence for support tickets and troubleshooting. Use when filing Abridge support tickets, collecting diagnostic data, or preparing evidence for escalation to Abridge engineering. "abridge diagnostics", "collect abridge evidence".
| Deploy Abridge clinical AI integration to HIPAA-compliant cloud infrastructure. Use when deploying to GCP Cloud Run, AWS ECS, or Azure Container Apps with healthcare-grade secrets management and compliance controls. "abridge AWS deploy", "abridge HIPAA infrastructure".
| Create a minimal Abridge ambient AI clinical documentation example. Use when testing Abridge integration, verifying EHR connectivity, or learning how Abridge captures and structures clinical conversations.
| Set up Abridge clinical AI platform authentication and EHR integration credentials. Use when onboarding a healthcare org to Abridge, configuring Epic/Athena integration, or setting up developer sandbox access for ambient AI documentation.
| Configure Abridge local development with FHIR server, synthetic data, and hot reload. Use when setting up a development environment for clinical AI integration, testing encounter workflows locally, or iterating on EHR integration code.
| Optimize Abridge clinical AI integration performance for high-volume deployments. Use when reducing note generation latency, optimizing audio streaming throughput, improving FHIR push performance, or scaling for multi-site health systems. "abridge slow", "abridge scale".
| Execute Abridge production readiness checklist for clinical AI deployment. Use when launching Abridge in a healthcare org, preparing for go-live, or validating HIPAA compliance before production deployment. "abridge launch readiness", "abridge prod deploy".
| Implement Abridge rate limiting, backoff, and session throttling patterns. Use when handling 429 errors, managing concurrent encounter sessions, or optimizing API throughput for high-volume clinical deployments. "abridge concurrent sessions".
| Implement Abridge reference architecture for clinical AI integration. Use when designing a new Abridge deployment, reviewing project structure, or planning multi-site health system rollouts with EHR integration. "abridge system design", "abridge multi-site".
| Apply production-ready patterns for Abridge clinical AI integration. Use when building reusable Abridge client wrappers, implementing HIPAA-compliant error handling, or establishing team coding standards for healthcare AI.
| Apply HIPAA-compliant security practices for Abridge clinical AI integrations. Use when securing PHI in transit/at rest, configuring access controls, implementing audit logging, or preparing for HIPAA security audits. "abridge access control", "abridge audit logging".
| Plan and execute Abridge integration upgrades and EHR migration procedures. Use when upgrading Abridge API versions, migrating between EHR systems, or handling breaking changes in clinical documentation workflows. "migrate abridge EHR", "abridge breaking changes".
| Implement Abridge webhook handling for clinical documentation events. Use when receiving note completion notifications, encounter status changes, provider enrollment events, or quality alert callbacks from Abridge. "abridge note completed event", "abridge encounter event".
| Acceptance Criteria Creator - Auto-activating skill for Enterprise Workflows. Part of the Enterprise Workflows skill category.
| This skill enables Claude to audit access control implementations in various systems. It uses the access-control-auditor plugin to identify potential vulnerabilities and misconfigurations related to access control. Use this skill when the user asks to "audit access control", "check permissions", "assess access rights", or requests a "security review" focused on access management. It's particularly useful for analyzing IAM policies, ACLs, and other access control mechanisms in cloud environments, applications, or infrastructure. The skill helps ensure compliance with security best practices and identify potential privilege escalation paths.
Manage Slack channel access control — pairing, allowlist, channel opt-in
| Accessibility Audit Runner - Auto-activating skill for Frontend Development. Part of the Frontend Development skill category.
| This skill enables Claude to perform comprehensive accessibility audits. It uses the accessibility-test-scanner plugin to identify WCAG 2.1/2.2 compliance issues, validate ARIA attributes, check keyboard navigation, and assess screen reader compatibility. Use this skill when the user requests an accessibility scan, audit, or compliance check, or when terms like "WCAG", "ARIA", "screen reader", "accessibility testing", or "a11y" are mentioned. It provides actionable insights for improving web application accessibility.
Extract action items from today's Granola/Grain meetings, create Todoist tasks, complete fulfilled tasks, and draft meeting-triggered follow-up emails. Use when running the daily action items cron, post-meeting cron, or when user asks to process meeting action items. NOT for general email drafting without meeting context.
| Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques. it is triggered when the user requests assistance with fine-tuning a model, adapting a pre-trained model to a new dataset, or performing... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
Build production-ready AI agents using Google's Agent Development Kit with Claude integration, React patterns, multi-agent orchestration, and comprehensive tool libraries
| Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. Use when asked to "deploy ADK agent" or "orchestrate agents". Trigger with phrases like 'deploy', 'infrastructure', or 'CI/CD'.
| Execute software engineer specializing in creating production-ready ADK agents with best practices, code structure, testing, and deployment automation. Use when asked to "build ADK agent", "create agent code", or "engineer ADK application". Trigger with relevant phrases based on skill purpose.
| Terraform infrastructure specialist for Vertex AI ADK Agent Engine production deployments. Provisions Agent Engine runtime, Code Execution Sandbox, Memory Bank, VPC-SC, IAM, and secure multi-agent infrastructure.
| introspection, Firefly job failure analysis, PDF Services error codes, and network-layer diagnostics for Adobe endpoints. Trigger with phrases like "adobe hard bug", "adobe mystery error", "adobe impossible to debug", "difficult adobe issue", "adobe deep debug".
| Adobe App Builder serverless, and dedicated microservice with event-driven Firefly/PDF pipelines. Decision matrix based on team size and throughput. Trigger with phrases like "adobe architecture", "adobe blueprint", "adobe app builder vs standalone", "adobe microservice".
| Configure CI/CD pipelines for Adobe integrations with GitHub Actions, including OAuth credential injection, PDF Services testing, Firefly API smoke tests, and secret scanning for Adobe credential patterns. Trigger with phrases like "adobe CI", "adobe GitHub Actions", "adobe automated tests", "CI adobe", "adobe pipeline".
| Diagnose and fix common Adobe API errors across Firefly Services, PDF Services, Photoshop API, and Adobe I/O Events. Use when encountering Adobe errors, debugging failed requests, or troubleshooting integration issues. Trigger with phrases like "adobe error", "fix adobe", "adobe not working", "debug adobe", "adobe 403", "adobe 429".
| and expand image using the Firefly v3 API. Use when generating images from prompts, filling or expanding images with AI, or building creative automation pipelines. Trigger with phrases like "adobe firefly", "generate image adobe", "firefly text to image", "adobe AI image", "generative fill".
| document generation from templates, and PDF-to-Markdown conversion. Use when building document automation, extracting content from PDFs, or generating dynamic reports. Trigger with phrases like "adobe pdf", "pdf services", "extract pdf", "create pdf", "document generation", "pdf to markdown".
| Optimize Adobe API costs across Firefly Services (generative credits), PDF Services (document transactions), and Photoshop/Lightroom APIs. Use when analyzing Adobe billing, reducing API costs, or implementing usage monitoring and budget alerts. Trigger with phrases like "adobe cost", "adobe billing", "adobe credits", "reduce adobe costs", "adobe pricing", "adobe budget".
| Implement data handling for Adobe APIs including PII redaction in logs, Firefly content policy compliance, PDF document data classification, and GDPR/CCPA data subject access requests via Adobe Privacy Service. Trigger with phrases like "adobe data", "adobe PII", "adobe GDPR", "adobe data retention", "adobe privacy", "adobe content policy".
| Collect Adobe debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Adobe API problems. Trigger with phrases like "adobe debug", "adobe support bundle", "collect adobe logs", "adobe diagnostic".
| Deploy Adobe-powered applications to Vercel, Cloud Run, and Adobe App Builder with proper credential injection and health monitoring. Use when deploying Adobe API integrations to production platforms. Trigger with phrases like "deploy adobe", "adobe Vercel", "adobe Cloud Run", "adobe App Builder deploy", "adobe production deploy".
| Configure Adobe enterprise identity with Admin Console SCIM provisioning, User Management API, product profile-based RBAC, and Federated ID with Azure AD or Google Workspace. Trigger with phrases like "adobe SSO", "adobe RBAC", "adobe enterprise", "adobe roles", "adobe SCIM", "adobe user management".
| PDF extraction, and Photoshop background removal. Use when starting a new Adobe integration, testing your setup, or learning basic Adobe API patterns. Trigger with phrases like "adobe hello world", "adobe example", "adobe quick start", "simple adobe code", "first adobe API call".
| Execute Adobe incident response procedures with triage, mitigation, and postmortem for Firefly Services, PDF Services, and I/O Events outages. Use when responding to Adobe-related incidents, investigating API failures, or running post-incident reviews. Trigger with phrases like "adobe incident", "adobe outage", "adobe down", "adobe on-call", "adobe emergency".
| Install and configure Adobe Developer Console OAuth Server-to-Server credentials. Use when setting up a new Adobe integration, configuring API credentials, or initializing Adobe SDKs (Firefly Services, PDF Services, I/O Runtime). Trigger with phrases like "install adobe", "setup adobe", "adobe auth", "configure adobe credentials", "adobe developer console".
| not caching IMS tokens, ignoring Firefly content policy, missing async job polling, and leaking p8_ secrets. Real code examples with fixes. Trigger with phrases like "adobe mistakes", "adobe anti-patterns", "adobe pitfalls", "adobe what not to do", "adobe code review".
| Implement load testing, auto-scaling, and capacity planning for Adobe API integrations with k6 scripts targeting Firefly, PDF Services, and Photoshop APIs, plus Kubernetes HPA configuration. Trigger with phrases like "adobe load test", "adobe scale", "adobe performance test", "adobe capacity", "adobe benchmark".
| Configure Adobe local development with App Builder CLI, Runtime actions, hot reload, and mock testing for Firefly/PDF/Photoshop APIs. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with Adobe APIs. Trigger with phrases like "adobe dev setup", "adobe local development", "adobe dev environment", "develop with adobe", "aio app".
| to Firefly Services, consolidating Creative Cloud integrations, and strangler-fig migration from competitor document/image APIs to Adobe. Trigger with phrases like "migrate adobe", "adobe migration", "switch to adobe", "adobe replatform", "replace with adobe".
| Configure Adobe OAuth credentials and API access across development, staging, and production environments with separate Developer Console projects, secret managers, and environment-specific scoping. Trigger with phrases like "adobe environments", "adobe staging", "adobe dev prod", "adobe environment setup", "adobe config by env".
| Set up comprehensive observability for Adobe API integrations with Prometheus metrics, OpenTelemetry traces, structured logging, and alert rules covering Firefly, PDF Services, and Photoshop APIs. Trigger with phrases like "adobe monitoring", "adobe metrics", "adobe observability", "monitor adobe", "adobe alerts", "adobe tracing".
| Optimize Adobe API performance with token caching, async job batching, connection pooling, and response caching for Firefly, PDF Services, and Photoshop API workflows. Trigger with phrases like "adobe performance", "optimize adobe", "adobe latency", "adobe caching", "adobe slow", "adobe batch".
| Implement Adobe-specific lint rules, CI policy checks, and runtime guardrails covering credential scanning (p8_ patterns), Firefly content policy pre-screening, PDF Services quota enforcement, and OAuth scope validation. Trigger with phrases like "adobe policy", "adobe lint", "adobe guardrails", "adobe eslint", "adobe content policy".
| Execute Adobe production deployment checklist covering credential management, API health checks, rate limit configuration, and rollback procedures for Firefly Services, PDF Services, and I/O Events integrations. Trigger with phrases like "adobe production", "deploy adobe", "adobe go-live", "adobe launch checklist".
| Implement Adobe API rate limiting, backoff, and quota management across Firefly, PDF Services, Photoshop, and I/O Events APIs. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Adobe. Trigger with phrases like "adobe rate limit", "adobe throttling", "adobe 429", "adobe retry", "adobe backoff", "adobe quota".
| Implement Adobe reference architecture for production integrations covering Firefly Services, PDF Services, I/O Events, and App Builder with layered project layout, error boundaries, and health monitoring. Trigger with phrases like "adobe architecture", "adobe project structure", "how to organize adobe", "adobe layout", "adobe best practices".
Claude Skills — questions
Answers built from the skills we actually parsed.