Use when optimizing Navan API call patterns for high-volume integrations — caching, batching, connection pooling, and pagination strategies. Trigger with "navan performance tuning" or "navan api optimization" or "navan caching".

Secure Navan API credentials with OAuth 2.0 best practices, SSO/SAML, and SCIM provisioning. Use when hardening a Navan integration, rotating credentials, or configuring identity provider SSO. Trigger with "navan security", "navan sso", "navan credentials", "navan scim".

Common Notion API mistakes: wrong page ID format (dashes), rich text array structure, block children not returned with page, pagination required for all lists, 3 req/sec shared across endpoints, not sharing pages with integration. Use when debugging or reviewing Notion code. Trigger with phrases like "notion mistakes", "notion pitfalls", "notion common errors", "notion gotchas", "notion debugging".

Apply Notion API security best practices for integration tokens, OAuth2 flows, least-privilege capabilities, and page-level access control. Use when securing integration tokens, configuring OAuth2 for public integrations, rotating credentials, or auditing which pages an integration can access. Trigger with phrases like "notion security", "notion secrets", "secure notion", "notion API key security", "notion token rotation", "notion OAuth2", "notion permissions audit".

Set up CI/CD pipelines for OneNote integrations with Graph API testing and mock strategies. Use when configuring GitHub Actions, setting up test credentials, or building mock-based CI tests. Trigger with "onenote ci", "onenote github actions", "onenote test pipeline", "graph api ci".

Launch, manage, and scale OCI compute instances with capacity retry logic. Use when provisioning VMs, selecting instance shapes, or handling "out of capacity" errors. Trigger with "oci compute", "launch instance", "out of capacity", "instance shapes".

Install and configure Oracle Cloud Infrastructure (OCI) SDK and CLI authentication. Use when setting up a new OCI integration, generating API signing keys, or debugging config file errors. Trigger with "install oraclecloud", "setup oci auth", "oraclecloud credentials", "oci config".

Configure CI/CD pipelines for Shopify apps with GitHub Actions, API version testing, and Shopify CLI deployment. Use when setting up automated testing, deployment pipelines, or API version monitoring for Shopify apps. Trigger with phrases like "shopify CI", "shopify GitHub Actions", "shopify automated tests", "CI shopify", "shopify deploy pipeline".

Configure Shopify local development with Shopify CLI, hot reload, and ngrok tunneling. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with Shopify. Trigger with phrases like "shopify dev setup", "shopify local development", "shopify dev environment", "develop with shopify", "shopify CLI dev".

Apply Shopify security best practices for API credentials, webhook HMAC validation, and access scope management. Use when securing API keys, validating webhook signatures, or auditing Shopify security configuration. Trigger with phrases like "shopify security", "shopify secrets", "secure shopify", "shopify HMAC", "shopify webhook verify".

Upgrade Shopify API versions and migrate from REST to GraphQL with breaking change detection. Use when upgrading API versions, migrating from deprecated REST endpoints, or handling Shopify's quarterly API release cycle. Trigger with phrases like "upgrade shopify", "shopify API version", "shopify breaking changes", "migrate REST to GraphQL", "shopify deprecation".

Deploy Speak language learning features to Vercel, Cloud Run, or containerized environments. Use when implementing deploy integration, or managing Speak language learning platform operations. Trigger with phrases like "speak deploy integration", "speak deploy integration".

Implement Supabase Auth (signUp, signIn, OAuth, session management), Storage (upload, download, signed URLs, bucket policies), and Realtime (Postgres changes, broadcast, presence). Use when building user auth flows, file upload features, or live-updating UIs with Supabase. Trigger with phrases like "supabase auth", "supabase storage upload", "supabase realtime subscribe", "supabase oauth", "supabase file upload", "supabase presence", "supabase rls storage".

Execute TwinMind primary workflow: Meeting transcription and summary generation. Use when implementing meeting capture, building transcription features, or automating meeting documentation. Trigger with phrases like "twinmind transcription workflow", "meeting transcription", "capture meeting with twinmind".

Optimize TwinMind costs across Free, Pro ($10/mo), and Enterprise tiers with usage monitoring and tier selection guidance. Use when implementing cost tuning, or managing TwinMind meeting AI operations. Trigger with phrases like "twinmind cost tuning", "twinmind cost tuning".

Deploy TwinMind integrations to production environments with Chrome extension deployment, mobile app configuration, and API access setup. Use when implementing deploy integration, or managing TwinMind meeting AI operations. Trigger with phrases like "twinmind deploy integration", "twinmind deploy integration".

Diagnose and fix common Vercel deployment and function errors. Use when encountering Vercel errors, debugging failed deployments, or troubleshooting serverless function issues. Trigger with phrases like "vercel error", "fix vercel", "vercel not working", "debug vercel", "vercel 500", "vercel build failed".

Execute use Cascade for intelligent debugging and error analysis. Activate when users mention "debug with ai", "error analysis", "cascade debug", "find bug", or "troubleshoot code". Handles AI-assisted debugging workflows. Use when debugging issues or troubleshooting. Trigger with phrases like "windsurf debugging ai", "windsurf ai", "windsurf".

Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + tier split + file-first rules carry over. Lossy (no slash commands, no actual skill dispatch) but useful. Trigger with /hyperflow:bridge, "make hyperflow work in desktop", "make hyperflow work in claude.ai", "embed hyperflow doctrine in CLAUDE.md", "portable hyperflow rules".

Build different types of Claude-powered applications — chatbots, RAG systems, Use when working with architecture-variants patterns. agents, content pipelines, and code generation tools. Trigger with "claude architecture", "anthropic rag", "build with claude", "claude agent pattern", "anthropic app design".

Diagnose and fix Anthropic API errors — authentication, rate limits, Use when working with common-errors patterns. overloaded, context length, and content policy issues. Trigger with "anthropic error", "claude 429", "claude overloaded", "anthropic not working", "debug claude api".

Implement tool use (function calling) with Claude to let it execute actions, Use when working with embeddings-search patterns. query databases, call APIs, and interact with external systems. Trigger with "anthropic tool use", "claude function calling", "claude tools", "anthropic structured output with tools".

Production-ready Anthropic SDK patterns — client config, retries, timeouts, Use when working with sdk-patterns patterns. error handling, TypeScript types, and async patterns. Trigger with "anthropic sdk", "claude client setup", "anthropic typescript", "anthropic python patterns".

Set up local development workflow with Clerk. Use when configuring development environment, testing auth locally, or setting up hot reload with Clerk. Trigger with phrases like "clerk local dev", "clerk development", "test clerk locally", "clerk dev environment".

Create your first project using Cursor AI features: Tab, Chat, Composer, and Inline Edit. Triggers on "cursor hello world", "first cursor project", "cursor getting started", "try cursor ai", "cursor basics", "cursor tutorial".

Use when asked to design iOS or Android mobile app screens, create mobile UI, spec mobile flows, or produce screen designs for a native app. Examples: "design the onboarding screens", "spec the checkout flow for iOS", "design a home screen for Android", "create mobile UI for this feature".

Migrate to Juicebox from other tools. Trigger: "switch to juicebox", "migrate to juicebox".

Execute Juicebox production checklist. Trigger: "juicebox production", "deploy juicebox".

Set up local development workflow for testing Lindy AI agent integrations. Use when building webhook receivers, testing agent callbacks, or iterating on Lindy-connected applications locally. Trigger with phrases like "lindy local dev", "lindy development", "test lindy locally", "lindy webhook local".

Use when setting up CI/CD pipelines that validate Navan API integrations, run booking data health checks, or generate automated compliance reports. Trigger with "navan ci integration" or "navan pipeline" or "navan github actions".

Manage the complete Navan travel booking lifecycle via REST API. Use when building travel dashboards, automating trip reporting, or syncing booking data to internal systems. Trigger with "navan travel workflow", "navan booking management", "navan trip retrieval".

Use when deploying Navan integrations with ERP systems (NetSuite, Sage Intacct, Xero), HRIS platforms (Workday, BambooHR), or identity providers (Okta, Azure AD). Trigger with "navan deploy integration" or "navan erp setup" or "navan sso deployment".

Make your first Navan API call to retrieve trip and user data. Use when verifying a new Navan integration works end-to-end after auth setup. Trigger with "navan hello world", "navan example", "test navan api", "first navan call".

Use when validating production readiness for a Navan API integration — credential rotation, alerting, rate limits, SSO, SCIM, and compliance audit trails. Trigger with "navan prod checklist" or "navan production readiness".

Implement adaptive rate-limiting for the Navan REST API with exponential backoff and request queuing. Use when building bulk data operations or encountering 429 errors from Navan. Trigger with "navan rate limits", "navan throttling", "navan 429".

Optimize Notion API usage to minimize rate-limit pressure, reduce engineering overhead, and maximize throughput. Use when auditing request volume, eliminating redundant API calls, implementing caching, or restructuring queries for efficiency. Trigger with "notion cost", "notion optimize", "notion API usage", "reduce notion requests", "notion rate limit budget", "notion efficient", "notion caching".

Deploy Node.js applications that use the Notion API to production on Vercel, Railway, or Fly.io. Use when deploying Notion-powered backends, setting up NOTION_TOKEN in production secrets, configuring serverless singleton patterns, or adding health checks that verify Notion connectivity. Trigger: "deploy notion app", "notion production", "notion vercel deploy", "notion railway", "notion fly.io".

Create a minimal working Shopify app that queries products via GraphQL Admin API. Use when starting a new Shopify integration, testing your setup, or learning basic Shopify API patterns. Trigger with phrases like "shopify hello world", "shopify example", "shopify quick start", "simple shopify app", "first shopify API call".

Create your first Speak AI tutoring session with pronunciation feedback. Use when starting a new Speak integration, testing your setup, or learning basic language learning API patterns. Trigger with phrases like "speak hello world", "speak example", "speak quick start", "first speak lesson".

Production patterns for Speak language learning API: conversation sessions, pronunciation assessment, audio preprocessing, and batch operations. Use when implementing sdk patterns features, or troubleshooting Speak language learning integration issues. Trigger with phrases like "speak sdk patterns", "speak sdk patterns".

Incident response for TwinMind failures: transcription not starting, audio not captured, sync failures, and calendar disconnect. Use when implementing incident runbook, or managing TwinMind meeting AI operations. Trigger with phrases like "twinmind incident runbook", "twinmind incident runbook".

Produce a complete firmware architecture spec for a described device — layer diagram, module responsibilities, HAL interface definitions, key state machines, RTOS decision. Use when asked to "design firmware architecture", "plan embedded firmware", "architect an IoT device", "how should I structure this firmware", or given a device description and asked what the firmware should look like.

Configure custom keyboard shortcuts for Cascade and AI features. Activate when users mention "keyboard shortcuts", "keybindings", "hotkeys", "shortcut configuration", or "customize shortcuts". Handles keybinding setup and optimization. Use when working with windsurf keyboard shortcuts functionality. Trigger with phrases like "windsurf keyboard shortcuts", "windsurf shortcuts", "windsurf".

Implement BambooHR reference architecture for production HR data pipelines. Use when designing new BambooHR integrations, building employee sync systems, or establishing architecture standards for BambooHR-powered applications. Trigger with phrases like "bamboohr architecture", "bamboohr design", "bamboohr project structure", "bamboohr system design", "bamboohr pipeline".

Debug complex Claude issues — inconsistent outputs, tool use failures, Use when working with advanced-troubleshooting patterns. streaming problems, and edge cases. Trigger with "claude inconsistent", "anthropic advanced debug", "claude tool use broken", "anthropic streaming issues".

Optimize Anthropic API costs — model selection, prompt caching, batches, Use when working with cost-tuning patterns. token reduction, and usage monitoring. Trigger with "anthropic pricing", "claude cost", "reduce anthropic spend", "anthropic billing", "claude cheaper".

Optimize Anthropic API latency — streaming, prompt caching, model selection, Use when working with performance-tuning patterns. connection reuse, and parallel requests. Trigger with "anthropic slow", "claude latency", "speed up anthropic", "anthropic performance", "claude response time".

Build Claude Code plugins — skills, agents, MCP servers, hooks, and slash commands. Use when working with reference-architecture patterns. The complete guide to extending Claude Code with the Anthropic plugin system. Trigger with "claude code plugin", "build a skill", "create mcp server", "anthropic plugin architecture", "claude code hooks".

Create a minimal working Deepgram transcription example. Use when starting a new Deepgram integration, testing your setup, or learning basic Deepgram API patterns. Trigger: "deepgram hello world", "deepgram example", "deepgram quick start", "simple transcription", "transcribe audio".

Wireframe a screen — text/ASCII by default, or hand-drawn HTML when the user says "sketch", "hand-drawn", "lo-fi HTML", "whiteboard", "graph paper", or "visual wireframe". Text mode produces a buildable ASCII spec Form and Prism can act on. HTML mode produces a single self-contained file with graph-paper background, marker headlines, sticky-note annotations, and hatched chart placeholders — looks like a designer's whiteboard, commits to nothing.

Install and configure Evernote SDK and OAuth authentication. Use when setting up a new Evernote integration, configuring API keys, or initializing Evernote in your project. Trigger with phrases like "install evernote", "setup evernote", "evernote auth", "configure evernote API", "evernote oauth".

Translate a design brief — structured I-Lang or plain English — into a concrete DESIGN.md and optional HTML token preview. Resolves 8 dimensions (palette, accent, typography, display font, layout, mood, density, constraints) to specific CSS tokens. Use when asked to "create a design brief", "write a DESIGN.md", "define the design system", "design brief for X", "what tokens should we use", or "I-Lang brief".

Use when asked to design an email template, newsletter, drip campaign email, transactional email, or any HTML email asset. Examples: "design a welcome email", "create a newsletter template", "make an onboarding email sequence", "design a password reset email", "build an email campaign".

Juicebox incident response. Trigger: "juicebox incident", "juicebox outage".

Set up Juicebox monitoring. Trigger: "juicebox monitoring", "juicebox metrics".

Create your first Lindy AI agent with a real trigger and action. Use when starting with Lindy, testing your setup, or learning basic agent workflow patterns. Trigger with phrases like "lindy hello world", "lindy example", "lindy quick start", "simple lindy agent", "first lindy".

Use when responding to Navan platform incidents — flight cancellations, booking API failures, expense sync outages, or OAuth authentication errors. Trigger with "navan incident runbook" or "navan outage response".

Set up webhook listeners for real-time Navan event notifications. Use when you need to receive booking, expense, or travel disruption events from Navan. Trigger with "navan webhooks", "navan events", "navan webhook setup".

Different Notion integration architectures: CMS (headless blog), task tracker (project management), knowledge base (wiki), form submission handler, and data pipeline source. Trigger with phrases like "notion cms", "notion headless blog", "notion task tracker", "notion wiki", "notion form handler", "notion data pipeline".

Create, update, archive, and compose Notion pages and block content. Use when building pages programmatically, appending rich content blocks, updating page properties, or managing page lifecycle (archive/restore). Trigger with phrases like "notion create page", "notion add blocks", "notion update page", "notion archive page", "notion content", "notion block types", "notion rich text".

Configure Notion enterprise access control with OAuth, workspace permissions, and audit logging. Use when implementing OAuth public integrations, managing multi-workspace access, or building permission-aware Notion applications. Trigger with phrases like "notion SSO", "notion RBAC", "notion enterprise", "notion OAuth", "notion permissions", "notion multi-workspace".

Use BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare these approaches". Also fires on cross-domain analysis, strategy questions, architecture decisions, or anything requiring multiple factors to be weighed before responding. The skill calls the reasoning MCP tool to retrieve a cognitive scaffold (named failure pattern, executable procedure, suppression vectors, falsification test) the model absorbs internally before generating its response. Catches causal shortcuts, premature conclusions, generic templates, and surface pattern matching that produce confidently-wrong answers. Do NOT trigger for simple factual lookups, syntax questions, file reads, code execution, or restating the user's input.

Collect Shopify debug evidence including API versions, scopes, rate limit state, and request logs. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Shopify problems. Trigger with phrases like "shopify debug", "shopify support bundle", "collect shopify logs", "shopify diagnostic".

Set up Speak language learning API integration and authentication. Use when configuring Speak API access, setting up OAuth with OpenAI Realtime API for speech, or initializing a language tutoring application. Trigger with phrases like "install speak", "setup speak", "speak auth", "configure speak API", "speak language learning setup".

Test and validate Claude integrations in CI/CD pipelines — Use when working with ci-integration patterns. GitHub Actions, mocking strategies, and cost control. Trigger with "anthropic ci", "test claude in ci", "anthropic github actions", "claude automated testing".

Handle sensitive data with Claude — PII redaction, conversation management, Use when working with data-handling patterns. context window optimization, and data retention policies. Trigger with "anthropic data privacy", "claude pii", "anthropic context window", "manage claude conversations", "anthropic data retention".

Collect debug evidence for Anthropic API issues — request IDs, headers, Use when working with debug-bundle patterns. error payloads, and reproduction steps for support tickets. Trigger with "anthropic debug", "claude support ticket", "anthropic request id", "debug claude api call".

Deploy Claude-powered applications to Vercel, Fly.io, and Cloud Run Use when working with deploy-integration patterns. with proper secrets management and streaming support. Trigger with "deploy anthropic", "claude production deploy", "anthropic vercel", "deploy claude app".

Respond to Anthropic API incidents — outages, degraded performance, Use when working with incident-runbook patterns. error spikes, and rate limit issues in production. Trigger with "anthropic down", "claude outage", "anthropic incident", "claude not responding", "anthropic 529".

Common mistakes when building with the Anthropic API and how to avoid them. Use when working with known-pitfalls patterns. Trigger with "anthropic mistakes", "claude pitfalls", "anthropic gotchas", "common claude errors", "anthropic anti-patterns".

Migrate from OpenAI/GPT to Anthropic/Claude — API differences, Use when working with migration-deep-dive patterns. prompt adaptation, SDK swap, and feature mapping. Trigger with "migrate to claude", "openai to anthropic", "switch from gpt to claude", "replace openai with anthropic".

Stream Claude responses, use system prompts, handle multi-turn conversations, Use when working with model-inference patterns. and process structured output with the Messages API. Trigger with "anthropic streaming", "claude messages api", "claude inference", "stream claude response".

Monitor Claude API calls — log tokens, latency, costs, errors, and Use when working with observability patterns. set up alerts for production Claude integrations. Trigger with "anthropic monitoring", "claude observability", "track claude usage", "anthropic logging".

Implement content safety guardrails for Claude — input filtering, Use when working with policy-guardrails patterns. output validation, usage policies, and prompt injection defense. Trigger with "anthropic content policy", "claude safety", "claude guardrails", "anthropic prompt injection", "claude content filtering".

Production readiness checklist for Claude-powered applications — Use when working with prod-checklist patterns. error handling, monitoring, fallbacks, cost controls, and security. Trigger with "anthropic production", "claude production ready", "anthropic launch checklist", "go live with claude".

Handle Anthropic rate limits — understand tiers, implement backoff, Use when working with rate-limits patterns. optimize throughput, and monitor usage. Trigger with "anthropic rate limit", "claude 429", "anthropic throttling", "anthropic usage limits", "claude tokens per minute".

Build fault-tolerant Claude integrations — retries, circuit breakers, Use when working with reliability-patterns patterns. fallbacks, timeouts, and graceful degradation. Trigger with "anthropic reliability", "claude fault tolerance", "anthropic circuit breaker", "claude fallback".

Secure your Anthropic integration — API key management, input validation, Use when working with security-basics patterns. prompt injection defense, and data privacy. Trigger with "anthropic security", "claude api key security", "anthropic prompt injection", "secure claude integration".

Use Anthropic Message Batches for async bulk processing and event handling. Use when working with webhooks-events patterns. Trigger with "anthropic batches", "claude batch api", "anthropic async", "bulk claude processing", "anthropic webhook".

Install Cursor IDE and configure authentication across macOS, Linux, and Windows. Triggers on "install cursor", "setup cursor", "cursor authentication", "cursor login", "cursor license", "cursor download".

Configure Juicebox multi-environment. Trigger: "juicebox environments", "juicebox staging".

Implement Juicebox rate limiting. Trigger: "juicebox rate limit", "juicebox 429", "juicebox throttle".

Handle Juicebox webhooks and events. Trigger: "juicebox webhooks", "juicebox events".

Set up Lindy AI account, API access, and webhook authentication. Use when onboarding to Lindy, configuring API keys for webhook triggers, or connecting Lindy agents to your application. Trigger with phrases like "install lindy", "setup lindy", "lindy auth", "configure lindy API key", "lindy webhook secret".

Use when collecting diagnostic data from a Navan API integration — OAuth token inspection, API response capture, connectivity testing, and request/response logging. Trigger with "navan debug bundle" or "debug navan api".

Set up OAuth 2.0 authentication for the Navan REST API. Use when configuring a new Navan integration or rotating API credentials. Trigger with "install navan", "setup navan auth", "navan credentials", "navan oauth".

Deep debugging for Notion API: response inspection, permission chain tracing, property type mismatches, pagination edge cases, and block nesting limits. Use when standard troubleshooting fails or investigating intermittent errors. Trigger with phrases like "notion deep debug", "notion permission trace", "notion property mismatch", "notion pagination bug", "notion nesting limit".

Implement data handling, PII protection, and GDPR/CCPA compliance for Notion integrations. Use when handling sensitive data from Notion pages, implementing data redaction, or ensuring compliance with privacy regulations. Trigger with phrases like "notion data", "notion PII", "notion GDPR", "notion data retention", "notion privacy", "notion CCPA".

Governance for Notion integrations: integration naming standards, page sharing policies, property naming conventions, database schema standards, and access audit scripts. Trigger with phrases like "notion governance", "notion policy", "notion naming convention", "notion access audit", "notion schema standard".

Graceful degradation when Notion is down: offline cache, retry with exponential backoff, circuit breaker, health checks, and fallback content. Use when building fault-tolerant Notion integrations for production. Trigger with phrases like "notion reliability", "notion circuit breaker", "notion offline fallback", "notion health check", "notion graceful degradation".

Implement secure Obsidian plugin development practices. Covers credential storage, input validation, XSS prevention, network security, URI handler safety, and Electron security. Use when handling user data, storing API keys, making network requests, or preparing for community plugin submission. Trigger with phrases like "obsidian security", "secure obsidian plugin", "obsidian data protection", "obsidian privacy", "obsidian api key storage".

Retell AI advanced troubleshooting — AI voice agent and phone call automation. Use when working with Retell AI for voice agents, phone calls, or telephony. Trigger with phrases like "retell advanced troubleshooting", "retellai-advanced-troubleshooting", "voice agent".

Retell AI migration deep dive — AI voice agent and phone call automation. Use when working with Retell AI for voice agents, phone calls, or telephony. Trigger with phrases like "retell migration deep dive", "retellai-migration-deep-dive", "voice agent".

Production-ready Retell AI SDK patterns for voice agent applications. Use when building production voice agents, implementing retry logic, or establishing patterns. Trigger with phrases like "retell patterns", "voice agent patterns", "retell best practices".

Retell AI webhooks events — AI voice agent and phone call automation. Use when working with Retell AI for voice agents, phone calls, or telephony. Trigger with phrases like "retell webhooks events", "retellai-webhooks-events", "voice agent".

Handle Speak API rate limits with exponential backoff, request queuing, and optimization strategies. Use when implementing rate limits features, or troubleshooting Speak language learning integration issues. Trigger with phrases like "speak rate limits", "speak rate limits".