ai-assistant-skills

Build production integrations with Anthropic Claude (Claude 4.5 Sonnet, Claude Opus 4, Claude Haiku 4) via the Messages API — system prompts, multi-turn conversations, tool use (function calling), prompt caching, extended thinking, vision, batched requests, and streaming. Use when wiring Claude into backends, agentic workflows, or evaluating it against other foundation models. Requires ANTHROPIC_API_KEY.

Deploy Cloudflare Workers, Pages, and Workers-with-static-assets safely using Wrangler 4.x with versioned uploads, gradual deployments, preview/production environments, secret bindings, observability, and one-command rollback. Use when shipping edge workloads, API routes, or full-stack apps to Cloudflare. Requires CLOUDFLARE_API_TOKEN with scoped permissions or an authenticated Wrangler session.

Deploy static sites, framework apps (Next.js, Astro, Remix, SvelteKit, Nuxt), Edge Functions, and serverless Functions to Netlify with deploy previews, branch deploys, atomic production promotion, scoped env vars, and instant rollback. Use when releasing on Netlify via CLI, API, or Git-triggered builds. Requires NETLIFY_AUTH_TOKEN (PAT) and NETLIFY_SITE_ID.

Transcribe audio with OpenAI speech-to-text models (gpt-4o-transcribe, gpt-4o-mini-transcribe, whisper-1) using prompt-guided terminology, segment-level timestamps, optional diarization via post-processing, and reliable artifact delivery. Use when converting interviews, calls, podcasts, or meeting recordings into reviewable text. Requires OPENAI_API_KEY.

Deploy Web Services, Private Services, Background Workers, Cron Jobs, Static Sites, PostgreSQL, and Key-Value (Redis-compatible) on Render via Blueprints (`render.yaml`) or the Render API with preview environments, zero-downtime rolling deploys, health checks, env-group secret scoping, and one-click rollback. Use when releasing services, applying schema migrations, or syncing infra-as-code on Render. Requires RENDER_API_KEY (owner- or workspace-scoped).

Operate Sentry end-to-end — error monitoring, performance tracing, session replay, profiling, release health, source-map upload, ownership routing, alert tuning, issue triage, and CI integration via sentry-cli — across web, mobile, and backend stacks. Use when instrumenting an app, wiring releases into deploy pipelines, or running incident-grade triage. Requires SENTRY_AUTH_TOKEN (org-scoped, `project:releases project:write`), project DSN, and (for source maps) `org` + `project` slugs.

Conduct a rigorous architecture review covering scope, drivers, quality attributes, risks, decisions, and action items. Use when a system, service, or major change needs an ATAM-lite review before commitment.

Detect and remediate architecture anti-patterns - Big Ball of Mud, Distributed Monolith, Golden Hammer, Vendor Lock-in, Premature Microservices, Lava Flow, God Service, and Shared Database. Use during audits, review prep, or when a system shows symptoms (slow change, cascading failures, ballooning ops cost).

Run an Architecture Kata (Ted Neward format) - prompt selection, timeboxed group design, rotation, and rubric-based scoring. Use for guild practice, hiring calibration, onboarding, or building shared trade-off vocabulary across an engineering org.

Select the right macro-architecture pattern by mapping drivers (scale, change rate, team topology, NFRs) to a curated 2026 catalog covering layered, hexagonal, microkernel, event-driven, microservices, modular monolith, space-based, and serverless. Use when choosing or defending a top-level structural style.

Facilitate effective architecture reviews using ATAM-lite, structured agendas, decision logs, and clear action items. Use when chairing design reviews, RFC walkthroughs, or pre-implementation gates that must produce binding decisions, not just discussion.

Prepare for system-design interviews using a repeatable framework - requirements clarification, capacity estimation, API and data design, deep dives, and trade-off articulation. Use when coaching candidates, calibrating interviewers, or self-preparing for staff/principal/architect loops.

Audit an existing system across architecture quality, technical debt, security, operations, and cost; produce a prioritized report with evidence, risk scores, and remediation roadmap. Use for due diligence, pre-replatform assessment, post-incident reviews, or yearly health checks.

Mentor engineers on architecture skills with structured growth paths, deliberate practice, and design-review pairing. Use when developing senior/staff/principal engineers, building an internal architect bench, or coaching individuals through ADRs, trade-off analysis, and stakeholder communication.

Define and enforce 8-12 architecture principles with rationale and implications. Use when establishing guardrails for technology choices, ADR reviews, or platform paved roads.

Lightweight architecture review covering quality attributes, security, operability, and cost. Use when triaging an ADR, design doc, or pre-production readiness gate without resorting to multi-day ATAM.

Estimate blast radius before merge or deploy via dependency graphs, contract tests, and ripple modeling. Use when scoping a refactor, schema change, shared-library bump, or cross-team API revision.

Map technical controls to ISO 27001:2022, SOC 2, GDPR, HIPAA, and EU AI Act, then automate verification with OPA / Conftest. Use when designing a continuous-compliance program instead of point-in-time audit cramming.

Govern third-party and OSS dependencies via SBOM, SLSA, OpenSSF Scorecard, and license policy. Use when establishing supply-chain controls, responding to CVE pressure, or preparing for SOC 2 / EU CRA audits.

Design executable architectural fitness functions per quality attribute. Use when codifying non-functional requirements as automated tests, policies, or budgets that fail the build.

Architect an Internal Developer Platform (IDP) with golden paths, Backstage, Score, and Crossplane. Use when establishing platform-as-product, paved roads, or replacing ticket-driven ops with self-service for stream-aligned teams.

Quantify and prioritize technical debt as principal plus interest. Use when building a debt register, justifying remediation budget, or sequencing payoff against feature work.

Select an architecture style (layered, hexagonal, microkernel, event-driven, microservices, modular monolith, space-based, serverless) using fitness signals and trade-offs. Use when choosing or evolving the top-level shape of a system.

Make defensible architecture decisions by translating requirements into trade-offs and ADRs. Use when choosing styles, components, or integration approaches that need a documented rationale.

Produce a one-page architecture brief covering drivers, decisions, risks, and alternatives. Use when a stakeholder needs the whole picture in five minutes - kickoffs, funding asks, vendor reviews.

Build a multi-quarter architecture roadmap with milestones, dependencies, risk markers, and Wardley-style evolution. Use when planning platform investment, sequencing migrations, or aligning squads on a target state.

Author C4 model diagrams across Levels 1-4 (System Context, Container, Component, Code) with Structurizr DSL and Mermaid. Use when documenting architecture at multiple zoom levels for mixed audiences.

Produce a C4 Level 1 System Context diagram showing actors, external systems, and scope. Use when onboarding new teams, scoping a project, or opening any architecture document.

Run an engineering RFC from draft to decision with a fixed template, review workflow, timebox, and decision log. Use when proposing non-trivial cross-team technical changes.

Author Mermaid sequence diagrams for service interactions including async, parallel, and error paths. Use when documenting request flows, integration contracts, or incident timelines.

Tailor architecture communication to executives, product managers, and engineers using the Pyramid Principle. Use when preparing review decks, steering committee briefings, or design walkthroughs.

Produce leveled Data Flow Diagrams (DeMarco/Yourdon) augmented with Mermaid sequence and trust boundaries. Use when documenting data movement, scoping a system, or driving STRIDE threat modeling.

Establish catalogs, lineage, classification, contracts, and regulatory controls across the data platform. Use when standing up a governance program or passing a GDPR/DPDP/HIPAA audit.

Design conceptual, logical, and physical data models that match the workload. Use when modeling a new domain, refactoring a legacy schema, or building an analytics warehouse.

Design batch, streaming, and CDC pipelines on a lakehouse with dbt and OpenLineage. Use when ingesting new sources, replacing nightly ETL, or building a real-time analytics surface.

Persist state as an append-only sequence of domain events with snapshots and projections. Use when audit, temporality, or replayability is a first-class requirement.

Apply Hohpe enterprise integration patterns updated for event-driven 2026 stacks. Use when wiring services with messaging, request/reply, claim check, outbox, or saga.

Evolve database and event schemas without breaking producers or consumers. Use when changing columns, fields, or message contracts in shared systems.

Select the right storage engine per workload using polyglot persistence. Use when designing a new bounded context, splitting a monolith, or replacing a hot-spotted database.

Capture significant architectural decisions as immutable, versioned MADR 4.0 records. Use when a choice is hard to reverse, affects multiple teams, or sets a long-lived constraint.