Process use when you need to archive historical database records to reduce primary database size. This skill automates moving old data to archive tables or cold storage (S3, Azure Blob, GCS). Trigger with phrases like "archive old database records", "implement data retention policy", "move historical data to cold storage", or "reduce database size with archival".

Process use when you need to work with schema comparison. This skill provides database schema diff and sync with comprehensive guidance and automation. Trigger with phrases like "compare schemas", "diff databases", or "sync database schemas".

Build this skill allows AI assistant to evaluate machine learning models using a comprehensive suite of metrics. it should be used when the user requests model performance analysis, validation, or testing. AI assistant can use this skill to assess model accuracy, p... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Automate and audit HubSpot deal pipeline operations without destroying real pipeline — covering stage automation loops, stale-deal safe-close logic, forecast reconciliation, custom property drift detection, quota dashboard cache-busting, and multi-pipeline duplicate detection. Use when writing or debugging workflow automations that move deals between stages, auditing pipelines for stale or duplicated opportunities, reconciling forecast numbers that disagree across reports, or hardening RevOps dashboards against property deletions and reporting-cache lag. Trigger with "hubspot deal pipeline", "hubspot stage automation", "hubspot stale deals", "hubspot forecast reconciliation", "hubspot quota dashboard", "hubspot duplicate deals", "revops pipeline audit".

Manage HubSpot lifecycle stages and list segmentation in production without silently destroying CRM trust. Covers lifecycle stage progression guards that prevent regression, dynamic list criteria drift, static list orphan detection, lead-scoring source-of-truth conflicts, webhook-missed-event recovery, and cross-portal list sync. Use when moving contacts through the funnel, building segment-based nurture flows, auditing list membership integrity, reconciling external lead scores with HubSpot native scoring, or standing up a webhook consumer that must never lose a membership-change event. Trigger with "hubspot lifecycle", "hubspot list segmentation", "hubspot dynamic list", "hubspot static list", "hubspot lead scoring conflict", "lifecycle regression", "list membership webhook", "cross-portal list sync".

Sync HubSpot CRM data to a data warehouse (BigQuery, Snowflake, or Postgres) for analytics and reporting. Covers initial backfill of millions of records under the 500K/day rate limit, incremental CDC polling via hs_lastmodifieddate, schema-drift detection with ALTER TABLE generation, association sync for contacts/deals/companies, and idempotent upsert patterns that prevent duplicate rows on retry. Use when building a HubSpot → warehouse pipeline, resyncing after a schema change, debugging duplicate rows or missing CDC updates, or recovering from a rate-limit burnout mid-backfill. Trigger with "hubspot warehouse sync", "hubspot bigquery", "hubspot snowflake", "hubspot postgres etl", "hubspot backfill", "hubspot cdc", "hubspot schema drift", "hubspot duplicate rows", "hubspot to data warehouse".

Build and harden HubSpot v3 webhook handlers that survive production: HMAC-SHA256 signature verification, Redis SET NX deduplication, async batch processing with immediate 200 ACK, dead-letter queuing for permanent failures, and event-ordering guards for property-change streams. Use when implementing HubSpot webhooks for the first time, hardening an existing handler against retry storms or duplicate processing, debugging signature verification failures, or designing a reliable event pipeline for contact, company, or deal change events. Trigger with "hubspot webhook", "hubspot signature verification", "hubspot webhook dedup", "hubspot webhook retry storm", "hubspot event handler", "hubspot property change webhook", "hubspot list membership webhook", "hubspot dead letter queue".

Process use when you need to implement multi-tier caching to improve database performance. This skill sets up Redis, in-memory caching, and CDN layers to reduce database load. Trigger with phrases like "implement database caching", "add Redis cache layer", "improve query performance with caching", or "reduce database load".

Load and chunk documents for LangChain 1.0 RAG pipelines correctly — language-aware splitters, table-safe PDF loaders, Cloudflare-compatible web loaders, chunk-boundary strategies that survive real-world structure. Use when building a RAG pipeline, diagnosing why retrieval misquotes a table, or debugging a crawler returning blank content. Trigger with "langchain document loader", "text splitter", "chunking strategy", "pdf loader", "markdown splitter", "webbaseloader".

Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, Secret Manager over `.env`. Use when prepping first prod deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", "langchain docker".

Build a correct LangGraph 1.0 ReAct agent with `create_react_agent` — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing your first tool-calling agent, migrating from `AgentExecutor` / `initialize_agent`, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", "agent loop cost".

Build a correct LangGraph 1.0 StateGraph — typed TypedDict state with reducers, nodes, edges, compile, and recursion budgets — without hitting the silent-termination and state-replacement traps. Use when writing your first LangGraph StateGraph, diagnosing why a graph halted without reaching END, or picking recursion_limit. Trigger with "langgraph statgraph", "langgraph basics", "GraphRecursionError", "langgraph conditional edges".

Persist LangGraph agent state correctly with MemorySaver and PostgresSaver — thread_id discipline, JSON-serializable state rules, time-travel, schema migration. Use when adding chat memory, migrating from ConversationBufferMemory, or time-traveling an agent state to debug an incident. Trigger with "langgraph checkpointer", "MemorySaver", "PostgresSaver", "thread_id", "langgraph time travel", "langgraph state persistence".

Build LangGraph 1.0 human-in-the-loop approval flows with `interrupt_before` / `interrupt_after` and `Command(resume=...)` — JSON-serializable state, clean resume semantics, and UI wiring for approval decisions. Use when adding an approval gate before an expensive tool call, wiring a Slack/web UI for agent approvals, or debugging a graph that crashes on interrupt. Trigger with "langgraph human in loop", "langgraph interrupt_before", "langgraph approval flow", "Command resume", "langgraph HITL".

Compose LangGraph 1.0 subgraphs correctly — shared state key propagation, Send / Command(graph=...) dispatch, callback scoping, per-subgraph recursion budgets, and testing each subgraph in isolation. Use when building a planner + executor, a nested agent team, or a reusable subgraph library. Trigger with "langgraph subgraph", "langgraph composition", "langgraph send", "nested agents", "langgraph state propagation", "Command(graph=...)", "langgraph subgraph callbacks".

Build composable middleware for LangChain 1.0 chains and LangGraph 1.0 agents — PII redaction, caching, retry, token budgets, guardrails — with ORDERING rules that avoid cache-key leakage and double-counting. Use when adding cross-cutting behavior, hardening against prompt injection, enforcing per-tenant budgets, or debugging cache-poisoning incidents. Trigger with "langchain middleware", "langgraph middleware", "PII redaction middleware", "cache middleware order", "langchain guardrails".

Build reliable dev / staging / prod isolation for LangChain 1.0 services — Pydantic `Settings` + `SecretStr`, cloud Secret Manager in prod, per-env prompt and model version pinning, env-specific checkpointer and observability. Use when graduating from `.env`-in-dev to real prod infra, or debugging a config that loaded the wrong values in the wrong env. Trigger with "langchain multi-env", "langchain pydantic settings", "langchain secret manager", "langchain env config", "langchain prod setup".

Wire LangSmith tracing and custom metric callbacks into a LangChain 1.0 chain or LangGraph 1.0 agent correctly — env-var spelling, subgraph propagation, per-tenant dimensions, cost and latency counters. Use when setting up observability on a new service, debugging blank traces in LangSmith, or adding per-tenant cost breakdowns. Trigger with "langchain observability", "langsmith tracing", "langchain callbacks", "langchain metrics".

Implement intelligent model routing to optimize cost, quality, and latency on OpenRouter. Use when building multi-model systems or optimizing spend across task types. Triggers: 'openrouter routing', 'model routing', 'route to model', 'model selection openrouter'.

Process split datasets into training, validation, and testing sets for ML model development. Use when requesting "split dataset", "train-test split", or "data partitioning". Trigger with relevant phrases based on skill purpose.

Track and optimize resource usage across application stack including CPU, memory, disk, and network I/O. Use when identifying bottlenecks or optimizing costs. Trigger with phrases like "track resource usage", "monitor CPU and memory", or "optimize resource allocation".

Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth. it uses the capacity-planning-analyzer plugin to assess current utilization, forecast growth trends, and recommend scaling strategies. use this skill when the u... Use when analyzing code or data. Trigger with phrases like 'analyze', 'review', or 'examine'.

Analyze network latency and optimize request patterns for faster communication. Use when diagnosing slow network performance or optimizing API calls. Trigger with phrases like "analyze network latency", "optimize API calls", or "reduce network delays".

Execute this skill empowers AI assistant to build reusable terraform modules based on user specifications. it leverages the terraform-module-builder plugin to generate production-ready, well-documented terraform module code, incorporating best practices for sec... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Comprehensive codebase cleanup across 11 quality dimensions: dead code, duplication, weak types, circular deps, defensive cruft, legacy code, AI slop, type consolidation, security, performance, and async patterns. Analyzes code with confidence scoring and verifies changes with build/test gates. Use when codebase has accumulated tech debt, after major feature work, before releases, or when code quality metrics are declining. Trigger with "/cleanup-code-code", "clean up the codebase", "remove dead code", "fix code quality".

Generate comprehensive compliance reports for security standards. Use when creating compliance documentation. Trigger with 'generate compliance report', 'compliance status', or 'audit compliance'.

Generate realistic test data including edge cases and boundary conditions. Use when creating realistic fixtures or edge case test data. Trigger with phrases like "generate test data", "create fixtures", or "setup test database".

Manage 10-100 HubSpot portals for agency clients with credential isolation that prevents cross-portal data contamination, per-portal audit trails for billing and GDPR/CCPA attribution, and a scriptable bulk-onboarding workflow that eliminates one-at-a-time credential setup. Use when onboarding new client portals, building a compliant per-client API call log, rotating tokens across a full agency fleet, or generating per-client compliance reports. Trigger with "hubspot agency", "multi-portal management", "hubspot credential isolation", "per-portal audit log", "hubspot compliance report", "bulk portal onboarding", "token rotation cascade", "hubspot client portals".

Bulk-migrate CRM data into HubSpot from Salesforce, Pipedrive, or Copper — or export off HubSpot — with field mapping, ID continuity, association re-linking, dedup safety, rate-limit budgeting, and rollback mitigation across 100K+ record datasets. Use when migrating any source CRM to HubSpot, recovering from a failed import with duplicate or unlinked records, or exporting out of HubSpot before switching platforms. Trigger with "hubspot bulk migration", "salesforce to hubspot", "pipedrive to hubspot", "copper to hubspot", "migrate off hubspot", "hubspot import dedup", "hubspot association relink", "hubspot field mapping", "hubspot id continuity".

Deduplicate HubSpot contacts at production scale — surviving import storms, wrong-winner merges, fuzzy-match blind spots, association orphans, rate-limit exhaustion, and silent merge failures on conflicting lifecycle or opt-out status. Use when cleaning a CRM after a bulk import, running a nightly dedup pipeline on millions of records, recovering from a merge that destroyed the wrong timeline, or building fuzzy matching beyond HubSpot's native email-uniqueness. Trigger with "hubspot dedup", "hubspot merge contacts", "hubspot duplicate contacts", "hubspot contact cleanup", "hubspot import duplicates", "hubspot fuzzy match contacts".

Survive HubSpot API rate limits at production scale. Covers daily 500K portal quota, per-10s burst limits, batch API efficiency (100x), token bucket pattern, queue-based worker architecture, and Retry-After header parsing. Use when a sync job burns the daily quota before 8am, when a parallelized batch job retry-storms on 429s, when single-record reads waste 99% of available throughput, or when instrumenting a rate-limit dashboard for an Ops Hub Enterprise portal. Trigger with "hubspot rate limit", "hubspot quota", "hubspot 429", "hubspot batch API", "hubspot token bucket", "hubspot throttle", "hubspot daily limit exhausted", "hubspot Ops Hub rate limit".

Control LangChain 1.0 AI spend with accurate streaming token accounting, model tiering, provider-specific cache hit tuning, per-tenant budgets, and retry dedup. Use when AI spend grows faster than traffic, a cost regression lands, or you need per-tenant budget enforcement. Trigger with "langchain cost", "langchain token accounting", "langchain per-tenant budget", "langchain model tiering", "prompt cache savings".

Build a LangGraph 1.0 Deep Agent — planner + subagents + virtual filesystem + reflection loop — without the state-growth and prompt-inheritance traps. Use when building a long-horizon agent that must plan, delegate subtasks, work against a scratchpad filesystem, and reflect on progress. Trigger with "langchain deep agent", "planner subagent", "virtual filesystem agent", "reflection loop", "langgraph deep agent".

Triage LangChain 1.0 / LangGraph 1.0 production incidents — LLM-specific SLOs, provider outage runbook, latency spike decision tree, cost-overrun response, agent loop containment. Use during an on-call page, in a post-mortem, or writing the team's first LLM runbook. Trigger with "langchain incident", "llm on-call", "langchain slo", "langchain outage", "langchain cost spike", "langchain agent loop".

Build a fast, deterministic local test loop for LangChain 1.0 / LangGraph 1.0 — FakeListChatModel fixtures, pytest config, VCR cassettes with key redaction, warning-filter policy. Use when adding tests to a new chain, fixing a flaky test, or making integration tests reproducible. Trigger with "langchain pytest", "FakeListChatModel", "VCR langchain", "langchain test fixtures", "langchain integration test".

Invoke Claude, GPT-4o, and Gemini through LangChain 1.0 without tripping on the content-block, token-accounting, and structured-output quirks that silently break production code. Use when initializing chat models, routing across providers, iterating AIMessage content, or choosing a structured-output method. Trigger with "langchain model inference", "ChatAnthropic", "ChatOpenAI", "with_structured_output", "AIMessage content blocks", "langchain routing".

Process use when you need to work with database sharding. This skill provides horizontal sharding strategies with comprehensive guidance and automation. Trigger with phrases like "implement sharding", "shard database", or "distribute data".

Define custom routing rules for OpenRouter requests based on user tier, task type, cost budget, and availability. Triggers: 'openrouter rules', 'routing rules', 'custom routing openrouter', 'conditional model selection'.

Enforce organizational governance for Supabase projects: shared RLS policy library with reusable templates, table and column naming conventions, migration review process with CI checks, cost alert thresholds, and security audit scripts scanning for common misconfigurations. Use when establishing Supabase standards across teams, creating RLS policy templates, setting up migration review workflows, or auditing existing projects for security and cost issues. Trigger with phrases like "supabase governance", "supabase policy library", "supabase naming convention", "supabase migration review", "supabase cost alert", "supabase security audit", "supabase RLS template".

Implement Supabase database webhooks, pg_net async HTTP, LISTEN/NOTIFY, and Edge Function event handlers with signature verification. Use when setting up database webhooks for INSERT/UPDATE/DELETE events, sending HTTP requests from PostgreSQL triggers, handling Realtime postgres_changes as an event source, or building event-driven architectures. Trigger with phrases like "supabase webhook", "database events", "pg_net trigger", "supabase LISTEN NOTIFY", "webhook signature verify", "supabase event-driven", "supabase_functions.http_request".

Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with thinking-tier review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why is this failing", "this test is broken".

Validate CSRF protection implementations for security gaps. Use when reviewing form security or state-changing operations. Trigger with 'validate CSRF', 'check CSRF protection', or 'review token security'.

Build and deploy generative AI agents on Vertex AI: Gemini model selection, RAG with grounded retrieval, function calling, multimodal extraction, evaluation, and Agent Engine deployment with operational guardrails (logs, alerts, cost controls). Use when designing, deploying, or operating Vertex AI agents on Google Cloud. Trigger with "build a Vertex agent", "deploy to Agent Engine", or "wire up RAG on Vertex AI".

Execute this skill empowers AI assistant to construct recommendation systems using collaborative filtering, content-based filtering, or hybrid approaches. it analyzes user preferences, item features, and interaction data to generate personalized recommendations... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Generate plots, charts, and graphs from data with automatic visualization type selection. Use when requesting "visualization", "plot", "chart", or "graph". Trigger with phrases like 'generate', 'create', or 'scaffold'.

Use when ready to ship — runs pre-push gates (lint, typecheck, build, tests, security sweep), commits, releases, and pushes. Standalone, never auto-invoked. Push always requires explicit confirmation. Trigger with /hyperflow:deploy, "ship it", "ready to push", "release", "cut a release", "deploy".

Execute use when detecting infrastructure drift from desired state. Trigger with phrases like "check for drift", "infrastructure drift detection", "compare actual vs desired state", or "detect configuration changes". Identifies discrepancies between current infrastructure and IaC definitions using terraform plan, cloudformation drift detection, or manual comparison.

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

Automate the ClaimCenter FNOL→investigation→reserve→payment→settlement→close pipeline including the failure paths — duplicate FNOL from multi-source intake, reserve-must-precede-payment ordering, supervisor-authorization tiers, premature settlement, and reopen-vs-new-claim ambiguity. Use when building claim intake from caller portals, IVR, or partner systems; automating reserve-setting jobs; or integrating settlement events with finance. Trigger with "claimcenter automation", "FNOL", "claim reserve", "claim payment", "claim settlement", "claim reopen".

Consume Guidewire App Events into downstream systems (SQS/SNS, Kafka, webhooks) and survive the event-side failures — events not firing because Gosu registration was missed, duplicates from queue redelivery, out-of-order arrival on the same resource, replay from a checkpoint for backfill, and back-pressure when consumers cannot keep up with producers. Use when registering App Events in Gosu, building an event-consumer service, or recovering from a missed-event window. Trigger with "guidewire app events", "guidewire webhooks", "guidewire event consumer", "guidewire event replay", "guidewire idempotent consumer".

Sync backend product events into HubSpot contact and company custom properties using idempotent batched updates — the Segment integration pattern without Segment. Use when you need to push server-side behavioral signals (feature usage, session counts, last-seen timestamps, trial milestones) into HubSpot CRM properties so sales and marketing can act on product data without a CDP in the stack. Trigger with "hubspot product events", "sync events to hubspot", "hubspot custom properties", "hubspot event pipeline", "hubspot segment alternative", "push usage data to hubspot".

Implement environment and configuration management with comprehensive guidance and automation. Use when you need to work with environment configuration. Trigger with phrases like "manage environments", "configure environments", or "sync configurations".

Design production architectures using OpenRouter as the LLM gateway. Use when planning system design, reviewing architecture, or scaling AI applications. Triggers: 'openrouter architecture', 'openrouter system design', 'openrouter at scale', 'llm gateway architecture'.

Process images using object detection, classification, and segmentation. Use when requesting "analyze image", "object detection", "image classification", or "computer vision". Trigger with relevant phrases based on skill purpose.

Use when the user has a clear-enough task and wants it decomposed into batched worker sub-tasks before any code is written. Writes a task file under .hyperflow/tasks/ and auto-chains into /hyperflow:dispatch. Trigger with /hyperflow:scope, "plan this", "decompose this task", "break this down", "write the task file".

Implement GDPR/CCPA compliance with Supabase: RLS for data isolation, user deletion via auth.admin.deleteUser(), data export via SQL, PII column management, backup/restore workflows, and retention policies. Use when handling sensitive data, implementing right-to-deletion, configuring data retention, or auditing PII in Supabase database columns. Trigger: "supabase GDPR", "supabase data handling", "supabase PII", "supabase compliance", "supabase data retention", "supabase delete user", "supabase data export".

Track and optimize application response times across API endpoints, database queries, and service calls. Use when monitoring performance or identifying bottlenecks. Trigger with phrases like "track response times", "monitor API performance", or "analyze latency".

Use when the user wants to view, search, add, edit, prune, archive, or clear hyperflow memory entries. CRUD interface for `.hyperflow/memory/` — never modifies source code, only memory files. Trigger with /hyperflow:cache, "show memory", "search memory for X", "clear memory", "what does hyperflow remember about Y".

Validate encryption implementations and cryptographic practices. Use when reviewing data security measures. Trigger with 'check encryption', 'validate crypto', or 'review security keys'.

Implement Real User Monitoring (RUM) to capture actual user performance data including Core Web Vitals and page load times. Use when setting up user experience monitoring or tracking custom performance events. Trigger with phrases like "setup RUM", "track Core Web Vitals", or "monitor real user performance".

Implement function/tool calling with OpenRouter models. Use when building agents, structured output, or tool-augmented LLM workflows. Triggers: 'openrouter function calling', 'openrouter tools', 'openrouter agent tools', 'tool use openrouter'.

Process use when you need to work with connection management. This skill provides connection pooling and management with comprehensive guidance and automation. Trigger with phrases like "manage connections", "configure pooling", or "optimize connection usage".

Process use when you need to work with security and compliance. This skill provides security scanning and vulnerability detection with comprehensive guidance and automation. Trigger with phrases like "scan for vulnerabilities", "implement security controls", or "audit security".

Scan for GDPR compliance issues in data handling and privacy practices. Use when ensuring EU data protection compliance. Trigger with 'scan GDPR compliance', 'check data privacy', or 'validate GDPR'.

Execute this skill enables comprehensive vulnerability scanning using the vulnerability-scanner plugin. it identifies security vulnerabilities in code, dependencies, and configurations, including cve detection. use this skill when the user asks to scan fo... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Upgrade Sentry SDK versions and migrate breaking API changes. Use when upgrading from Sentry v7 to v8, migrating Python SDK v1 to v2, replacing deprecated Hub/Transaction APIs, or running the migr8 codemod. Trigger: "upgrade sentry", "sentry migration", "sentry breaking changes", "migrate sentry v7 to v8", "update sentry sdk".

Execute this skill automates the setup of distributed tracing for microservices. it helps developers implement end-to-end request visibility by configuring context propagation, span creation, trace collection, and analysis. use this skill when the user re... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Setup synthetic monitoring for proactive performance tracking including uptime checks, transaction monitoring, and API health. Use when implementing availability monitoring or tracking critical user journeys. Trigger with phrases like "setup synthetic monitoring", "monitor uptime", or "configure health checks".

Execute Supabase production deployment checklist covering RLS, key hygiene, connection pooling, backups, monitoring, Edge Functions, and Storage policies. Use when deploying to production, preparing for launch, or auditing a live Supabase project for security and performance gaps. Trigger with "supabase production", "supabase go-live", "supabase launch checklist", "supabase prod ready", "deploy supabase", "supabase production readiness".

Implement enterprise Supabase reference architectures — monorepo layout, multi-tenant RLS, microservices with cross-project access, framework integration, edge functions, caching, queue patterns, and audit logging. Use when designing a new Supabase project from scratch, reviewing project structure for production readiness, planning multi-tenant isolation, or establishing team architecture standards. Trigger with phrases like "supabase architecture", "supabase project structure", "supabase monorepo", "supabase multi-tenant", "supabase reference design", "how to organize supabase at scale".

Define and track SLAs, SLIs, and SLOs for service reliability including availability, latency, and error rates. Use when establishing reliability targets or monitoring service health. Trigger with phrases like "define SLOs", "track SLI metrics", or "calculate error budget".

Validate PCI-DSS compliance for payment card data security. Use when auditing payment systems. Trigger with 'validate PCI-DSS', 'check payment security', or 'audit card data'.

Scaffold production-ready AI agents on Google's Agent Development Kit (ADK): ReAct-style single agents, multi-agent orchestration (Sequential/Parallel/Loop), tool wiring, evaluation, and optional Vertex AI Agent Engine deployment. Use when building, scaffolding, or deploying ADK agents on Google Cloud, or when wiring ADK tools and orchestration patterns. Trigger with "build an ADK agent", "scaffold an agent on ADK", or "deploy to Agent Engine".

Build and evaluate classification models for supervised learning tasks with labeled data. Use when requesting "build a classifier", "create classification model", or "train classifier". Trigger with relevant phrases based on skill purpose.

Check compliance with OWASP Top 10 security risks and best practices. Use when performing comprehensive security audits. Trigger with 'check OWASP compliance', 'audit web security', or 'validate OWASP'.

Process use when you need to work with database schema design. This skill provides schema design and migrations with comprehensive guidance and automation. Trigger with phrases like "design schema", "create migration", or "model database".

Move a Guidewire deployment to a new platform or release without breaking running policies and claims — on-prem→cloud cutover (config reconciliation, data migration, parallel-run validation), in-place version upgrade (e.g., 202403→202503) with deprecated-API regression coverage, rehearsal-driven cutover with rollback path mid-flight, and broker/claimant communication so users hit the right system at the right time. Use when planning a cloud migration, executing a version upgrade, or rehearsing a cutover. Trigger with "guidewire migration", "guidewire upgrade", "guidewire cutover", "guidewire on-prem to cloud", "202503 upgrade".

Process use when you need to work with database migrations. This skill provides schema migration management with comprehensive guidance and automation. Trigger with phrases like "create migration", "run migrations", or "manage schema versions".

Process use when you need to work with database partitioning. This skill provides table partitioning strategies with comprehensive guidance and automation. Trigger with phrases like "partition tables", "implement partitioning", or "optimize large tables".

Monitor use when you need to work with monitoring and observability. This skill provides health monitoring and alerting with comprehensive guidance and automation. Trigger with phrases like "monitor system health", "set up alerts", or "track metrics".

Optimize context window usage for OpenRouter models to reduce cost and improve quality. Use when hitting context limits, managing long conversations, or building RAG systems. Triggers: 'openrouter context', 'context window', 'openrouter token limit', 'reduce tokens openrouter'.

Use multiple AI providers (OpenAI, Anthropic, Google, Meta) through OpenRouter's unified API. Use when comparing providers, building cross-provider workflows, or maximizing availability. Triggers: 'openrouter providers', 'multi provider', 'openrouter openai anthropic', 'compare models openrouter'.

Use when starting hyperflow in a new project, refreshing the .hyperflow/ cache, or installing auto-detection shims (AGENTS.md, CLAUDE.md). One-shot project setup; does not start the spec → scope → dispatch chain. Trigger with /hyperflow:scaffold, "init hyperflow", "set up hyperflow", "refresh hyperflow", "install hyperflow shims".

Integrate Sentry with your observability stack — logging, metrics, APM, and dashboards. Use when connecting Sentry to winston/pino/structlog, correlating errors with business metrics, deciding between Sentry performance and Datadog/New Relic, building Sentry Discover dashboards, or linking events to external tools via extra context. Trigger: "sentry observability", "sentry logging", "sentry metrics", "sentry grafana", "sentry datadog correlation", "sentry discover dashboard".

Database migration patterns with Supabase CLI: npx supabase migration new, zero-downtime migrations, data backfill strategies, schema versioning, rollback strategies, and type generation. Use when creating database migrations, performing zero-downtime schema changes, backfilling data in production, managing schema versions, or planning rollback strategies. Trigger: "supabase migration", "supabase schema change", "supabase zero downtime", "supabase rollback", "supabase db push", "supabase migration new".

Test across multiple browsers and devices for cross-browser compatibility. Use when ensuring cross-browser or device compatibility with BrowserStack, Sauce Labs, LambdaTest, or Kobiton. Trigger with phrases like "test browser compatibility", "check cross-browser", "validate on browsers", "test on real devices", "kobiton test".

Execute use when you need to work with query optimization. This skill provides query performance analysis with comprehensive guidance and automation. Trigger with phrases like "optimize queries", "analyze performance", or "improve query speed".

Manage the freshie ecosystem inventory database — a CMDB tracking all plugins, skills, packs, and compliance grades across 50 SQLite tables. Use when checking ecosystem health, running discovery scans, validating compliance, remediating issues, querying inventory data, comparing runs, exporting data, or generating status reports. Trigger with "freshie status", "inventory scan", "ecosystem audit", "grade report", "compliance check", "remediate skills", "query freshie", "compare runs", "export grades", or "freshie report".

Generate API contracts and OpenAPI specifications from code or design documents. Use when documenting API contracts and specifications. Trigger with phrases like "generate API contract", "create OpenAPI spec", or "document API contract".

Test automatically generate comprehensive unit tests from source code covering happy paths, edge cases, and error conditions. Use when creating test coverage for functions, classes, or modules. Trigger with phrases like "generate unit tests", "create tests for", or "add test coverage".

Automate the PolicyCenter account→submission→quote→bind→issue→endorse→renew pipeline including the failure paths — underwriting issues blocking bind, quotes expiring before bind, referrals stuck pending approval, and mid-term endorsements that trigger unexpected premium audit recalculation. Use when building outbound integrations against PolicyCenter Cloud API (CRM-driven submission, broker-portal binding, automated renewal jobs). Trigger with "policycenter automation", "submission to bind", "policy renewal", "policy endorsement", "underwriting issue".

Build and query vector stores with LangChain 1.0 without getting burned by flipped score semantics, embedding-dim mismatches, reranker quirks, and chunk-splitter bugs. Use when building a RAG pipeline, choosing between FAISS / Pinecone / Chroma / PGVector, filtering by similarity score, or adding a reranker. Trigger with "langchain embeddings", "vector store similarity search", "langchain RAG retrieval", "FAISS score", "Pinecone score", "reranker score".

Implement audit logging for OpenRouter API calls. Use when building compliance trails, debugging production issues, or tracking model usage. Triggers: 'openrouter audit', 'openrouter logging', 'audit trail openrouter', 'log openrouter requests'.

Optimize OpenRouter request latency and throughput. Use when building real-time applications, reducing TTFT, or scaling request volume. Triggers: 'openrouter performance', 'openrouter latency', 'openrouter speed', 'optimize openrouter throughput'.

Build reusable OpenRouter client wrappers with retries, typing, and middleware. Use when creating SDKs or client libraries. Triggers: 'openrouter sdk', 'openrouter client wrapper', 'openrouter patterns', 'openrouter library'.

Scan for data privacy issues and sensitive information exposure. Use when reviewing data handling practices. Trigger with 'scan privacy issues', 'check sensitive data', or 'validate data protection'.