VincentChuWaiChow
- 787 skills
- 0 followers
- 24 repo stars
- 3 days ago last updated
- ▌ Snowflake Cortex AI Agent Security Governor · vincentchuwaichow bundleUse this skill to review the security and governance boundary of Snowflake AI: Cortex Agents and their identity and effective data reach, CORTEX_USER versus CORTEX_AGENT_USER and AI-function privileges including grants to PUBLIC, Cortex Search corpora as an untrusted-content surface, Cortex Analyst semantic exposure, tools and MCP connectors as privilege grants, prompt and indirect prompt injection, exfiltration paths, guardrails, adversarial evaluation, observability, and cost per successful task. Trigger before any Cortex or agentic capability is exposed to users. Static review only: it never creates or invokes an agent, and it never approves an AI system from its prompt.
- ▌ Snowflake Live Data Protection Policy Guard · vincentchuwaichow bundleApproval-gated live guard for exactly one Snowflake data-protection policy attachment, detachment, or replacement on one object or column. Requires a per-role-class visibility prediction that has been tested before execution, an enumeration of the consumption paths the protection will and will not follow, and — for any detachment — a written justification, a named data owner, and a committed re-attachment time. Never displays sensitive values, including during verification. Runs as a custom role scoped to the single target and policy; never ACCOUNTADMIN.
- ▌ Fabric Power Bi Business Insights Governance · vincentchuwaichow bundleReview Microsoft Fabric and Power BI business-insights governance — semantic model trust (shared/endorsed/certified models, Build permission), row-level and object-level security, workspace roles, OneLake catalog discoverability and lineage, sensitivity labels and Microsoft Purview DLP for Power BI, certified-dataset reuse, and capacity oversight. Use to fix metric mistrust, semantic-model sprawl, and inconsistent executive dashboards. Static review only; production workspace-role, RLS, and capacity changes are escalated.
- ▌ Power Platform Governance Dataverse Security · vincentchuwaichow bundleReview and advise on Power Platform environment strategy, Data Loss Prevention (DLP) policy design, Dataverse security model, business unit hierarchy, security roles and teams, table/row/column-level permissions, connector governance, and Center of Excellence (CoE) alignment. Flags environment sprawl, weak DLP, unmanaged connectors, over-privileged Dataverse roles, insecure ad-hoc sharing, and misaligned business unit design. Static review only — no live tenant mutations. Escalates production DLP changes through the live-guard gate.
- ▌ Netsuite Suitescript Secure Code Review Skill · vincentchuwaichow bundleFlashlight skill for static security review of SuiteScript 2.x code against OWASP Top 10 (2021) pitfall patterns (OSCP-001 through OSCP-048), extended with Vanguard severity taxonomy mapping and CI pipeline gate recommendations. Adapted from Oracle netsuite-owasp-secure-coding (UPL-1.0). T0 static review — no live account connection required. TRIGGER when: user submits SuiteScript 2.x code for security review, asks about SuiteQL injection prevention, output encoding in Suitelets or RESTlets, CSRF in SuiteScript, file upload security, RESTlet hardening, DOM XSS in client scripts, postMessage origin validation, or AI prompt-injection in SuiteScript. Trigger phrases: SuiteScript security review, OWASP SuiteScript, SuiteQL injection, XSS in Suitelet, RESTlet hardening, CSRF token SuiteScript, file upload SuiteScript, OSCP vulnerability, secure coding SuiteScript. DO NOT TRIGGER when: request is for SuiteScript 1.0 (recommend migration first), SuiteFlow workflow logic review (use netsuite-suiteflow-automation-agen
- ▌ Snowflake Business Value Adoption Strategist · vincentchuwaichow bundleUse this skill to test whether a Snowflake initiative removes a business constraint anyone owns: value hypothesis, pre-work baseline, benefit modelling by credibility category, unit economics, causal attribution, adoption, time to value, decision latency, alternatives including do-nothing, benefit realization, and translation into executive KPIs. Trigger when an initiative is proposed, prioritized, or being justified — and especially when the justification is that Snowflake supports the capability. Static review only, and it may return NO-GO on a technically sound proposal.
- ▌ Snowflake Data Platform Engineering At Azure · vincentchuwaichow bundleDesign and review Snowflake data platform engineering on Azure, covering warehouse sizing and cost governance, Azure Private Link requirements, storage integration with ADLS Gen2 and Azure Blob, Snowpipe automation, object tagging, dynamic data masking, row access policies, and ACCESS_HISTORY lineage for GDPR and CCPA compliance.
- ▌ Databricks Unity Catalog Governance At Azure · vincentchuwaichow bundleDatabricks Unity Catalog Governance at Azure
- ▌ Marketing Conversion Flow Dark Pattern Review · vincentchuwaichow bundleUse this skill when reviewing marketing conversion flow specifications — subscription sign-up, upsell interstitial, free-trial enrollment, and cancellation path — for dark-pattern practices that invalidate consent or constitute unfair or deceptive acts under FTC Section 5 and state privacy laws. Trigger when a user provides a UX flow specification including step-by-step page descriptions, annotated wireframes, CTA labels, pre-checked options, visual weight of accept vs decline paths, countdown timer specs, or cancellation flow step counts. Scope is limited to marketing conversion flows; consent banner review is handled by a separate skill.
- ▌ Netsuite Identity Access Role Permission Skill · vincentchuwaichow bundleStatic review flashlight for NetSuite role configurations, permission assignments, and Segregation-of-Duties design. Validates custom roles against standard baselines, resolves permission codes from the 684-code SDF catalog, and flags SoD conflicts and over-permissioned roles. TRIGGER when: user asks to review a NetSuite role, check permissions on a role, audit segregation of duties, validate a custom role, analyze SDF customrole XML, check who has Administrator access, review run-as configuration for a script or integration, map permissions to least privilege, or assess 2FA role designations. Trigger phrases: review netsuite role, check role permissions, segregation of duties netsuite, custom role from standard, sdf customrole xml, least privilege role, who has administrator, run-as role, 2fa role designation. DO NOT TRIGGER when: the question is about OAuth 2.0, TBA, SSO, or SAML configuration (use netsuite-sso-oauth-tba-skill); when SDF project structure or deployment pipeline is the subject (use netsuite-
- ▌ Netsuite Sandbox Nonproduction Governance Skill · vincentchuwaichow bundleStatic-review flashlight for NetSuite sandbox, Release Preview, and non-production environment governance. Enforces the confirmed isolation facts: OAuth 2.0 authorized apps and client credentials flow setup in production are NOT copied to sandbox or Release Preview (and are cleared on each sandbox refresh); TBA tokens created in production are NOT copied to sandbox or Release Preview. Enforces that sandbox success does not equal production readiness without explicit re-authorization. TRIGGER when: user asks about sandbox governance, OAuth app re-authorization after sandbox refresh, TBA token management across environments, Release Preview usage policies, environment isolation between production and sandbox, sandbox-to-production promotion readiness, or sandbox refresh impact on integration testing. Trigger phrases: sandbox refresh, OAuth re-authorize sandbox, Release Preview isolation, sandbox governance, non-production environment, sandbox success production readiness, TBA token sandbox. DO NOT TRIGGER when:
- ▌ Snowflake Live Pipeline Streaming Change Guard · vincentchuwaichow bundleApproval-gated live guard for exactly one Snowflake pipeline or ingestion change — one task, stream, dynamic table, or pipe operation, or one bounded backfill. Requires a freshness and count baseline, the last successful processing state, the offset or checkpoint position, a downstream consumer enumeration, and an explicit duplication-or-loss analysis before execution, plus a passing reconciliation afterwards. Refuses unbounded replays and replays into targets with no deduplication path. Runs as a custom role scoped to the single object; never ACCOUNTADMIN.
- ▌ Salesforce Live Change Approval Protocol · vincentchuwaichow bundleSalesforce Live Change Approval Protocol
- ▌ M365 Exchange Sharepoint Information Governance · vincentchuwaichow bundleReview and advise on Exchange Online and SharePoint Online plus OneDrive information governance covering mailbox and site lifecycle, external and anonymous sharing controls, SharePoint Advanced Management (Restricted Content Discovery, site access reviews, data access governance reports), retention and records management via Microsoft Purview, oversharing remediation feeding Microsoft 365 Copilot readiness, and information architecture. Cert anchor MS-102. Static review and advisory only; tenant sharing-policy changes and retention or hold changes are live-guard gated. Refuses to weaken sharing controls or remove holds for convenience.
- ▌ Revenue Critical Journey Integrity Review · vincentchuwaichow bundleUse this skill to review the cross-tier seams of revenue-critical journeys — checkout, payment submission, account creation, and login — for idempotency of money-moving and account-creating requests, server-side re-validation of client-enforced rules, webhook duplicate/out-of-order handling, retry-storm safeguards, and PCI DSS SAQ-scope judgment. Use when a request crosses client-to-server, system-to-processor, or webhook-back-into-system and a failure at that seam would double-charge, double-fulfill, bypass a required step, drop revenue, or misjudge PCI scope. Static review only; it does not execute payment flows and its PCI SAQ output is an advisory scoping opinion, never a compliance attestation.
- ▌ Environment To Production Release Protocol · vincentchuwaichow bundleUse this skill when a Power Platform or Dynamics 365 solution must progress through a structured dev-to-test-to-production release pipeline using managed solutions and Power Platform pipelines, when rollback readiness must be verified before go-live, or when a deployment approval gate must be enforced. Defines the full ALM release flow — solution packaging, pipeline stage progression, pre-deployment validation, approval, deployment, rollback verification, and post-deployment confirmation. Does not authorize production deployments directly; all production-impacting actions require human approval from the environment owner or release manager. Does not replace a qualified Power Platform admin or ALM specialist.
- ▌ Typescript Public API And Declaration Governance · vincentchuwaichow bundleUse this skill to statically review a published TypeScript type surface: `.d.ts` correctness and emit strategy (`declaration`, `isolatedDeclarations`, rollups, API reports), public-versus-accidental exports, breaking-change classification and the semver decision, the consumer compilation matrix, and compile-time type-contract tests (`expectTypeOf`/`assertType` under `--typecheck`, `@ts-expect-error`). Reads declarations and configuration only; it never compiles, publishes, or runs the package.
- ▌ Salesforce Data Exposure Escalation Protocol · vincentchuwaichow bundleSalesforce Data Exposure Escalation Protocol
- ▌ Databricks Live Unity Catalog Grant Guard At Azure · vincentchuwaichow bundleMutating-runtime live guard for Unity Catalog privilege management on Azure Databricks. Executes exactly ONE GRANT or REVOKE of a single privilege on a single Unity Catalog securable (schema, table, or volume) to a single principal — with explicit written human approval, dry-run preflight, prior-state capture, and a named rollback owner. Phase B strictly-scoped controlled mutation; never bulk, never wildcard, never ALL PRIVILEGES, never metastore/account admin grants.
- ▌ Typescript Business Critical Automation Governance · vincentchuwaichow bundleUse this skill to statically review whether a privileged TypeScript automation (backfill, migration, reconciliation script) may run and under what controls: dry-run coverage of the write path, technical and business idempotency, blast-radius bounds, approval separation, checkpoint/resume, rollback and reconciliation evidence, audit trail, and a named inverse operation — with particular attention to type-stripped, never-type-checked execution holding production credentials combined with floating-promise partial commits. Never executes anything; reads script source and named credential scope only.
- ▌ Kubernetes Live Network Architecture Mutation Guard · vincentchuwaichow bundleGuard live kubectl apply, patch, or create operations on Kubernetes networking *architecture* surface — Service spec (`internalTrafficPolicy`, `externalTrafficPolicy`, `topology-mode`, `trafficDistribution`), CoreDNS Corefile, NodeLocal DNSCache install, Gateway API resources (Gateway / HTTPRoute / GRPCRoute / TLSRoute / ReferenceGrant), and ClusterMesh peer Secrets. HARD REFUSE one-way doors (CNI replacement, kube-proxy mode swap, MTU change, Pod / Service CIDR resize, namespace deletion). Pre-flight `kubectl auth can-i` matrix against a least-privilege ServiceAccount before any write. Use only when an intentional architecture-level networking mutation is requested against a confirmed cluster target with a documented rollback path.
- ▌ Vanguard Frontier Agentic Install · vincentchuwaichowInstall all Vanguard Frontier Agentic Codex agents and companion skills into the current user's ~/.codex home after adding or installing the plugin marketplace.
- ▌ AWS Maestro · vincentchuwaichow bundleRoute AWS tasks to the narrowest specialist or team of specialists from the 42-agent catalog. Use when you do not already know the specialist. Not for direct AWS answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatches live-guard agents — requires explicit human confirmation with blast-radius and rollback before routing to any live deployment or production-change specialist.
- ▌ GCP Maestro · vincentchuwaichow bundleGCP Maestro routing skill. Classify the user's GCP task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatch live-guard agents. Understands GCP's global VPC model, resource hierarchy (org→folder→project), and IAM inheritance before routing any networking or identity task.
- ▌
- ▌ PHP Maestro · vincentchuwaichow bundleRoute PHP-board governance tasks to the narrowest specialist or a genuinely multi-domain parallel team from the PHP catalog. Use when you do not already know which PHP specialist handles the task. Not for direct PHP answers or specialist review; Maestro classifies, dispatches, and hands off to php-board-chair-agent (or the named owning human until one exists) only. Detects and refuses live-mutation or destructive requests (deploy, database migration in prod, force-push), requiring explicit human confirmation before any such action. Treats security, supply-chain, and runtime-EOL findings as blocking hard gates that are never averaged into an approval.
- ▌ Sap Maestro · vincentchuwaichow bundleRoute SAP AI workflow requests to the correct domain skill using taxonomy classification, a routing table, and dispatch mode selection. Use when an incoming request spans multiple SAP domains (BTP, S/4HANA, SuccessFactors, Ariba, etc.) and the correct downstream skill or agent must be identified before any action is taken. Does not touch live systems.
- ▌ AWS Agentcore · vincentchuwaichow bundleBuild, test, migrate, integrate, and deploy Amazon Bedrock AgentCore agents. Use for AgentCore runtime, local development, import/migration, deployment, Memory, Gateway/MCP tools, Identity, Observability, Browser, Code Interpreter, Evaluations, Registry, Payments, policy, and harness-vs-code-path decisions. Load references only when that component is needed.
- ▌ Java Maestro · vincentchuwaichow bundleJava Maestro routing skill. Classify the user's Java/JVM task, select the narrowest static-review specialist from the Java board (or the smallest team, max 4), and dispatch. Trigger when a user brings a Java, JVM, Spring, Jakarta EE, JDK-upgrade, JPA/Hibernate, or Java-security task and it is not yet clear which specialist should handle it. Routes only — never answers Java questions itself, never runs code, never requests secrets.
- ▌ Pr Babysit · vincentchuwaichowThe repeatable loop for watching a pull request until it is merged or closed, pairing webhook subscription with a scheduled self check-in so CI results, new pushes, and merge-conflict transitions are never missed; use when asked to watch, babysit, or autofix a PR, or right after creating one.
- ▌
- ▌ Ionos Maestro · vincentchuwaichow bundleClassify incoming IONOS Cloud requests and route them to the narrowest applicable specialist agent. Covers DCD topology review, security and GDPR compliance, managed Kubernetes, cost optimization, and DBaaS lifecycle operations. Use this skill when the task domain is not yet identified or spans multiple IONOS Cloud areas.
- ▌ Dotnet Maestro · vincentchuwaichow bundle.NET Maestro routing skill. Classify the user's .NET task, select the narrowest specialist agent or the right team of specialists from the .NET board, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Trigger when a user brings a .NET, C#, ASP.NET Core, EF Core, NuGet, .NET Aspire, or .NET performance/observability task and it is not yet clear which specialist should handle it. Routes only — never answers .NET questions itself, never runs code, never requests secrets.
- ▌ Finops Maestro · vincentchuwaichow bundleRoute FinOps tasks to the narrowest specialist or team of specialists from the catalog. Use when you do not already know the specialist. Not for direct FinOps answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatches live-guard agents — requires explicit human confirmation with blast-radius and rollback before routing to any live mutation specialist.
- ▌ Huawei Maestro · vincentchuwaichow bundleHuawei Cloud Maestro routing skill. Classify the user's Huawei Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatch live-guard agents. MLPS 2.0 and sovereignty-aware — flags when workloads require MLPS Level 3 controls or government cloud configurations. Understands Huawei's enterprise-project model and SCP-based org governance.
- ▌ Kotlin Maestro · vincentchuwaichow bundleUse this skill to classify a Kotlin, JVM-Kotlin, Android, or Kotlin Multiplatform task and route it to the narrowest static-review specialist on the Kotlin board, or to gate a production-mutation request to a named human owner. Routing and classification only — it never reviews Kotlin work itself, never answers a Kotlin question directly, and never contacts a live system.
- ▌ Nvidia Maestro · vincentchuwaichow bundleRoute NVIDIA tasks to the narrowest specialist or team of specialists from the NVIDIA agent catalog. Use when you do not already know the specialist. Not for direct NVIDIA answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatches the live-runtime promotion gatekeeper — requires explicit human confirmation with blast-radius and rollback before routing to any runtime-evidence specialist.
- ▌ Python Maestro · vincentchuwaichow bundleUse this skill to classify a Python application, runtime, packaging, framework, data, or code-level task and route it to the narrowest static-review specialist on the Python board, or to gate a production-mutation request to a named human owner. Routing and classification only — it never reviews Python work itself, never answers a Python question directly, and never contacts a live system.
- ▌ D365 Maestro · vincentchuwaichow bundleRoute Dynamics 365 tasks to the narrowest D365 specialist from the catalog. Use when you do not already know the specialist. Not for direct D365 answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 4) for multi-domain tasks. Enforces Success by Design gates and segregation-of-duties escalation. Never auto-dispatches live-guard agents — requires explicit human confirmation with blast-radius and rollback before routing to any D365 production cutover, data migration to prod, or posting-config agent.
- ▌ M365 Maestro · vincentchuwaichow bundleRoute Microsoft 365 tasks to the narrowest M365 specialist from the catalog. Use when you do not already know the specialist. Not for direct M365 answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatches live-guard agents — requires explicit human confirmation with blast-radius and rollback before routing to any agent that changes live tenant configuration.
- ▌ Alibaba Maestro · vincentchuwaichow bundleAlibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatch live-guard agents. China-region aware — flags when workloads are in mainland China regions and applicable regulatory frameworks (MLPS 2.0, DSL, PIPL) differ from international regions.
- ▌
- ▌ Contabo Maestro · vincentchuwaichow bundleRouter skill for classifying Contabo tasks and delegating to the narrowest specialist for cost analysis, capacity planning, security hardening, VPS/VDS lifecycle operations, or Object Storage management. Use when the user asks a Contabo question that spans multiple domains or needs triage before specialist engagement.
- ▌ Finance Maestro · vincentchuwaichow bundleRoute corporate finance questions to the narrowest specialist in the catalog. Use when you do not already know the specialist needed. Not for direct finance answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 3) for multi-domain tasks. Never auto-dispatches any write-capable agent — requires explicit human confirmation before routing to any agent with planning system or ERP write access.
- ▌ Carbon Cost Pair · vincentchuwaichow bundlePair every cloud spend value with a kgCO2e estimate by region and service category for CSRD and SEC climate disclosure. Input is region, service category, and dollar value; output is paired kgCO2e with confidence label (vendor-published, third-party, or estimated) and source citation. Defaults to electricity-only Scope 2 market-based factors.
- ▌ Hetzner Maestro · vincentchuwaichow bundleRoute and classify Hetzner Cloud tasks to the narrowest qualified specialist — cost optimization, infrastructure review, capacity planning, firewall guard, or server lifecycle guard. Use when the user's Hetzner request spans multiple domains or needs triage before specialist engagement.
- ▌ D365 Commerce · vincentchuwaichow bundleReview Dynamics 365 Commerce across omnichannel retail operations — Store Commerce POS, e-commerce storefront, call center channels, Commerce Scale Unit, channel management, product catalogs and assortments, pricing and discounts, inventory visibility, and store operations. Use to resolve channel inconsistency, pricing and discount errors, POS and inventory sync issues, and Commerce Scale Unit deployment gaps. Static review only; production channel and pricing configuration changes are escalated.
- ▌ Hr Risk Triage Review · vincentchuwaichow bundleUse this skill when triaging HR and employment-relations risk for an enterprise People function — terminations, discipline, performance management, accommodations, leave, wage/hour, worker classification, discrimination, harassment, retaliation, whistleblower reports, layoffs, and HR policy exceptions. Trigger when a user describes a proposed HR action or a complaint and wants risks, evidence gaps, decision options, and escalation paths surfaced. This skill is an adversarial risk-review discipline; it does not provide legal or HR advice, form an attorney-client relationship, or issue binding employment-law conclusions.
- ▌ Test Flakiness Triage · vincentchuwaichow bundleUse this skill when triaging flaky tests across any test framework — analyzing a flaky-test report, CI rerun history, or a set of intermittently failing tests to assign each a root-cause category and a remediation or quarantine path. Trigger when a user reports tests that pass on re-run, asks why CI is unreliable, provides a flaky-test dashboard export, or wants a quarantine policy. This skill reviews evidence statically; it does not execute or re-run tests.
- ▌ AWS Network Architect · vincentchuwaichow bundleDesign, review, and troubleshoot AWS network, hybrid, and multi-cloud connectivity across VPCs, Transit Gateway, Direct Connect, VPN, Cloud WAN, Route 53 Resolver, private DNS, CIDRs, route tables, endpoints, segmentation, ingress, egress, inspection, and failover. Prefer this for connectivity and routing; prefer API/edge, S3, or security skills for those specialized surfaces.
- ▌
- ▌ Frontend Maestro · vincentchuwaichow bundleRoute frontend governance tasks to the narrowest specialist or parallel team (max 4) from the frontend agent catalog. Use when you do not already know which frontend specialist handles the task. Not for direct frontend answers; Maestro classifies, dispatches, and hands off to frontend-board-chair-agent only. Never auto-dispatches live-mutation-capable specialists — requires explicit human confirmation with blast-radius and rollback before routing to any live-guard specialist.
- ▌ GCP Network Architect · vincentchuwaichow bundleDesign and review GCP network architecture including global VPC topology, Shared VPC patterns, Cloud Interconnect/VPN hybrid connectivity, Cloud NAT, DNS, Cloud Armor, and Traffic Director service mesh.
- ▌ GCP Spanner Architect · vincentchuwaichow bundleDesign Cloud Spanner schemas with hotspot avoidance, interleaving strategies, optimal indexing, processing-unit sizing, and global write patterns for distributed OLTP at scale.
- ▌ Java Spring Security · vincentchuwaichow bundleUse this skill when statically reviewing a Spring Security 6 service's authorization and endpoint-exposure posture — multiple SecurityFilterChain beans and securityMatcher disjointness/ordering, authorizeHttpRequests matcher sequencing (first-match-wins, permitAll before authenticated, anyRequest() last), request-level vs @PreAuthorize/@PostAuthorize/@Secured method-security precedence, AuthorizationManager delegation and fail-closed behavior, CSRF on state-changing endpoints, and Spring Boot Actuator exposure (management.endpoints.web.exposure.include, EndpointRequest, securing /actuator). Trigger when a user provides Spring Security configuration (HttpSecurity/SecurityFilterChain beans, method-security annotations, actuator properties) or asks whether an endpoint or actuator surface is safely secured. Reads source and sanitized configuration only; it never builds, runs, or contacts a live system.
- ▌
- ▌ Ovhcloud Maestro · vincentchuwaichow bundleClassify incoming OVHcloud requests by domain and route to the narrowest qualified specialist agent. Use when the user's task spans or is unclear across IAM, FinOps, Kubernetes, networking, or live-guard KMS domains. Does not answer specialist questions directly; produces a routing verdict with evidence and hands off with a clear scope statement.
- ▌ Scaleway Maestro · vincentchuwaichow bundleClassify and route Scaleway tasks to the narrowest qualified specialist agent. Use when a user presents a Scaleway request that spans IAM, cost, Kapsule/Kubernetes, networking, or live-guard domains, and the correct specialist is not yet identified. Produces a domain verdict, recommended specialist, and routing rationale without answering specialist questions directly.
- ▌ Agentic Delegation · vincentchuwaichowDelegate exploration sweeps to Haiku subagents and bulk writing to Sonnet subagents while the orchestrator keeps architecture, security-sensitive edits, and commits; use at the start of any multi-step task in this repo to minimize token spend by delegating to cheaper models.
- ▌ Definition Of Done · vincentchuwaichowThe ordered finish-line runner for any change in this repo — generators, then the asset-integrity refresh last on its own, then the full gate suite, then commit and push; use before declaring any change finished or whenever the stop hook reports uncommitted or untracked changes.
- ▌ Payroll Advisor · vincentchuwaichow bundleMulti-jurisdiction payroll accounting reference framework covering compensation expense recognition, employee benefits, pension/post-retirement obligations, and payroll tax compliance.
- ▌ AWS Iac Patch Executor · vincentchuwaichow bundleEdit AWS IaC files including CloudFormation, SAM, CDK config, and Terraform to patch defects, prepare change set review, or unblock rollout work. Prefer this for bounded repo changes only; do not use for apply, deploy, or destructive infrastructure execution.
- ▌ AWS Solution Architect · vincentchuwaichow bundleDesign and stress-test AWS cross-domain solution architectures when the request spans multiple AWS domains or needs an architecture decision record. Prefer narrower AWS skills for single-domain IAM, network, EKS, ECS, serverless, RDS, DynamoDB, S3, Bedrock, IaC, cost, security, migration, compliance, or incident asks.
- ▌ GCP Cloud Auth Advisor · vincentchuwaichow bundleAdvise on Google Cloud authentication and authorization patterns — covering Application Default Credentials (ADC), service account best practices, Workload Identity Federation (for GKE pods and external workloads), human user auth (gcloud, IAP, Identity Platform), service-to-service auth (OIDC ID tokens, short-lived credentials), and anti-patterns like service account key downloads. Use when designing auth flows, debugging GCP auth failures, implementing least-privilege SA setup, or migrating from SA keys to keyless authentication.
- ▌ GCP Firebase Developer · vincentchuwaichow bundleBuild, configure, and operate Firebase-powered web and mobile applications — covering Firestore, Firebase Auth, Firebase Hosting, Cloud Functions for Firebase, Firebase Storage, App Check, Firebase Remote Config, and Firebase Analytics. Use when building mobile/web apps with Firebase, setting up authentication flows, designing Firestore data models, deploying Firebase Hosting, or configuring Firebase security rules.
- ▌ GCP Solution Architect · vincentchuwaichow bundleDesign GCP solutions aligned with the Google Cloud Architecture Framework when the request spans resource hierarchy, product selection, or multi-service architecture decisions. Prefer narrower GCP skills for single-domain network, GKE, Cloud Run, data pipeline, database, or landing zone asks.
- ▌
- ▌ CI Test Pipeline Review · vincentchuwaichow bundleUse this skill when reviewing how a CI pipeline runs tests — gating, sharding, parallelism, fail-fast behavior, artifact retention, and flaky-test quarantine wiring. Trigger when a user provides a CI workflow file (GitHub Actions, GitLab CI, CircleCI, Jenkins), asks why CI is slow or unreliable as a merge gate, or wants to know whether their test pipeline actually blocks bad merges. This skill reviews CI configuration statically; it does not trigger or run pipelines.
- ▌ Argocd Gitops Review · vincentchuwaichow bundleUse this skill for Argo CD GitOps review across Application, AppProject, ApplicationSet, sync windows, RBAC, sync impersonation, and Argo CD Agent multi-cluster topologies. Trigger when the user asks whether an Argo CD configuration is safe for production, whether automated sync should be enabled, whether prune+selfHeal is appropriate, whether AppProject scope is too wide, or how to enforce least-privilege sync identity.
- ▌ AWS Waf Security Review · vincentchuwaichow bundleReview AWS workloads against the Well-Architected Framework Security Pillar: identity foundations, detective controls, infrastructure protection, data protection, and incident response readiness.
- ▌ Databricks Mlops · vincentchuwaichow bundleUse this skill to review machine-learning model lifecycle on Databricks: MLflow 3 with Unity Catalog as default registry, alias-based promotion and champion/challenger patterns, feature-store design with point-in-time correctness, Model Serving endpoint configuration and traffic management, inference-table auto-logging with at-least-once guarantees, batch inference with `ai_query()`, and cross-environment promotion paths. Establishes evidence linking tests to production deployments without executing inference.
- ▌ GCP Cost Finops Analyst · vincentchuwaichow bundleAnalyze GCP spend via Billing exports, optimize committed-use and sustained-use discounts, design cost attribution (labels/tags), investigate budget alert drift, and recommend rightsizing for Compute, GKE, and BigQuery. Prefer gcp-bigquery-cost-performance-analyst for deep BigQuery query and slot optimization unless the request is primarily billing export analysis, CUD/SUD coverage, or cross-service cost attribution.
- ▌ GCP Waf Security Review · vincentchuwaichow bundleEvaluate GCP workload security posture against the Google Cloud Well-Architected Framework security pillar — covering zero trust, shift-left security, preemptive cyber defense, AI security governance, and regulatory compliance. Use when assessing architecture security requirements, designing security controls, or auditing a GCP workload against WAF security recommendations.
- ▌ Java Kafka Reliability · vincentchuwaichow bundleUse this skill when statically reviewing a Kafka producer/consumer pipeline for whether it actually delivers the delivery semantics it claims — idempotent-producer-vs-exactly-once conflation, transactional read-process-write wiring (transactional.id, initTransactions, sendOffsetsToTransaction, consumer isolation.level=read_committed), at-least-once with or without an idempotent consumer, commit-before-process message loss, ordering (max.in.flight.requests.per.connection combined with idempotence), consumer lag as the operational SLA signal, max.poll.interval.ms rebalance stalls, DLQ/retry-topic design, and acks=all plus min.insync.replicas durability. Trigger when a user provides producer/consumer configuration, Kafka client or Spring @KafkaListener code, or a topic/partition design and asks whether messages can be lost, duplicated, reordered, or stuck, or whether an "exactly-once" claim actually holds. Reads source and sanitized configuration only; it never opens a broker connection, produces or consumes a l
- ▌
- ▌ Marketing Maestro · vincentchuwaichow bundleRoute marketing-governance review tasks to the narrowest specialist or team of specialists from the catalog. Use when you do not already know which marketing-governance specialist you need. Not for direct answers; Maestro classifies, dispatches, and synthesizes only. Dispatches a single agent for focused tasks or a parallel team (max 4) for multi-domain tasks. Never auto-dispatches live-guard or mutating agents — requires explicit human confirmation with blast-radius and rollback before any live mutation.
- ▌ Microsoft Maestro · vincentchuwaichow bundleRoute Microsoft SaaS tasks to the right sub-maestro (m365-maestro-agent, d365-maestro-agent, power-platform-maestro-agent, copilot-governance-maestro-agent) or directly to a specialist. Use when you do not already know the specialist. Not for direct Microsoft answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single sub-maestro or agent for focused tasks, parallel team (max 4) for multi-domain tasks. Refuses Azure IaaS and infrastructure tasks and deflects to azure-maestro. Never auto-dispatches live-guard agents — requires explicit human confirmation with blast-radius and rollback before routing to any live-tenant-mutation agent.
- ▌
- ▌
- ▌
- ▌ Sap Fiori Ui5 UX Review · vincentchuwaichow bundleReview SAP Fiori and SAPUI5 applications for Fiori design guidelines adherence, UI5 app structure and MVC correctness, OData consumption patterns, performance, accessibility, and Fiori launchpad integration. Use when assessing Fiori app code, manifest.json, XML views, controllers, OData model binding, or launchpad tile configuration for quality, compliance with SAP UX standards, and readiness for productive use. Does not touch live systems.
- ▌ Snowflake Maestro · vincentchuwaichow bundleUse this skill to classify a Snowflake task and route it to the narrowest review specialist on the Snowflake board, or to gate a mutation request behind explicit written human approval. Trigger when a Snowflake architecture, administration, identity, network, governance, compliance, FinOps, query performance, pipeline, streaming, analytics, ML, Cortex AI, Native App, BCDR, DevOps/IaC, migration, or business-value task arrives and the right specialist is not yet obvious. Routing only: it never answers a Snowflake question itself, never executes SQL, and never auto-dispatches a live guard.
- ▌ Terraform Maestro · vincentchuwaichow bundleRoute a Terraform or OpenTofu task to the right advisory specialist on the IaC board. Use when the specific specialist is not already known. Not for direct IaC answers — this skill classifies, dispatches, and synthesizes only. Applies documented thresholds so a change is not sprayed across four agents when one owns it, and stops for written human confirmation before any live apply, destroy, or state mutation is handed to a cloud live-guard agent.
- ▌ Focus Spec Normalizer · vincentchuwaichow bundleNormalize vendor-specific billing rows (AWS CUR, Azure Cost Management, GCP Billing Export, OCI) into FOCUS v1.2 columns from user-pasted CSV or JSON input. Refuses to invent column values not derivable from the input. No credentials accepted; operates on user-supplied data only.
- ▌ GCP Alloydb AI Developer · vincentchuwaichow bundleDesign and build AI-powered applications on AlloyDB for PostgreSQL using AlloyDB AI — covering vector search, hybrid search (vector + full-text), AI SQL functions (ai_generate, ai_classify, ai_score, ai_embed), model endpoint management, and the AlloyDB Omni edge runtime. Prefer gcp-alloydb-cloudsql-dba for cluster operations, backup, HA, and DBA tasks; use this skill when the request is primarily about AlloyDB AI search, SQL AI functions, or embedding pipelines.
- ▌ GCP Alloydb Cloudsql Dba · vincentchuwaichow bundleOperate AlloyDB clusters and Cloud SQL instances — HA configuration, read replicas, connection pooling, maintenance windows, backup strategy, and performance diagnostics.
- ▌ GCP Gemini API Developer · vincentchuwaichow bundleBuild, integrate, and debug Gemini API applications on Google Cloud Agent Platform (formerly Vertex AI) using the unified google-genai SDK. Covers text generation, multimodal inputs, function calling, structured output, embeddings, context caching, batch prediction, streaming, Live API (bidirectional voice/video), and model tuning across Python, TypeScript/JavaScript, Go, Java, and C#. Use when building Gemini-powered applications, migrating from deprecated Vertex AI or google-generativeai SDKs, or integrating Gemini capabilities into a GCP-hosted service.
- ▌
- ▌ Helm Chart Quality Review · vincentchuwaichow bundleUse this skill when a user provides a Helm chart or asks to review Helm chart quality, security, or testability — including Chart.yaml, values.yaml, templates/, tests/, or chart-testing CI configuration.
- ▌
- ▌ Accounting Maestro · vincentchuwaichow bundleRoute accounting questions to the narrowest specialist in the catalog. Use when you do not already know the specialist needed. Not for direct accounting answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 3) for multi-domain tasks. Never auto-dispatches any write-capable agent — requires explicit human confirmation before routing to any agent with ledger or ERP write access.
- ▌ AWS Change Impact Advisor · vincentchuwaichow bundleAssess AWS change impact using change sets, deployment blast radius, rollback readiness, dependency mapping, risk, go/no-go context, approval context, and stakeholder communication. Prefer this for non-destructive pre-change advisory work; prefer IaC or platform-specific skills for deep implementation review.
- ▌ AWS Eks Platform Operator · vincentchuwaichow bundleReview Amazon EKS Kubernetes platform operations across cluster access, IRSA, IAM roles for service accounts, pod identity, node groups, Karpenter, autoscaling, CNI/network policy, upgrades, reliability, observability, and cost. Use only for EKS/Kubernetes; prefer ECS/Fargate operator for ECS services.
- ▌ AWS Landing Zone Governor · vincentchuwaichow bundleReview and design AWS landing zones, AWS Control Tower environments, Organizations structures, OUs, account vending patterns, guardrails, central logging, security/audit accounts, and multi-account governance. Use when the user asks how to structure AWS accounts or govern a cloud estate.
- ▌ AWS Live Iac Change Guard · vincentchuwaichow bundleGuard live CloudFormation, SAM, CDK, and Terraform-backed AWS infrastructure changes with change set, drift, stack policy, rollback trigger, approval, and execute gates. Use only for intentional live IaC execution with confirmed targets.
- ▌ AWS Pipeline Fix Operator · vincentchuwaichow bundleRepair AWS pipeline configuration, buildspecs, workflow files, deployment steps, artifact wiring, release guardrails, and CodeDeploy integration in-repo. Use for non-destructive CI/CD corrections; do not trigger live pipeline runs or mutate cloud state.
- ▌ Databricks Maestro · vincentchuwaichow bundleUse this skill to classify an incoming Databricks task and route it to the narrowest owning specialist on the Databricks board. Classifies on intent, business context, artifact type, blast radius, required evidence, implied runtime authority, and specialist ownership; emits a single owner, a parallel team of up to four with the conflict named, an unclassified request for the smallest sufficient artifact, or a live-guard gate. Routing only — it never reviews Databricks work and never dispatches a mutation.
- ▌ Frontend Board Chair · vincentchuwaichow bundleSequence frontend specialist and red-team reviews for the 10 governed workflows (new feature, perf regression, a11y audit, security review, SSR/hydration bug, design-system change, framework migration, AI-generated code review, production incident, CWV failure) and issue a binding evidence-gated approve/conditional-approve/reject decision. Use when a frontend change needs a final governance verdict, not a first-pass technical review.
- ▌ GCP Change Impact Advisor · vincentchuwaichow bundlePre-change blast radius analysis for GCP — cross-project resource dependency mapping, org policy cascade effects, Shared VPC peering impact, Service Account impersonation chain analysis, and safe change sequencing.
- ▌ GCP Gke Platform Operator · vincentchuwaichow bundleOperate GKE clusters (Standard and Autopilot), manage node pools, configure Workload Identity, enforce Binary Authorization, plan node pool upgrades, and review cluster security posture.