Windags Skills

Saga patterns, compensating actions, and two-phase commit for distributed transactions. Activate on: distributed transaction, saga, compensating action, two-phase commit, eventual consistency, cross-service transaction. NOT for: single-database transactions (use database-connection-pool-manager), event sourcing (use cqrs-event-sourcing-architect).

Build face recognition systems with InsightFace, ArcFace, enrollment pipelines, HDBSCAN clustering, and privacy-compliant architecture. Activate on: face recognition, face enrollment, face clustering, identity verification, facial search. NOT for: general object detection (computer-vision-pipeline), emotion analysis (ai-engineer).

Use when introducing a feature flag system, choosing between release flags / experiment flags / operational flags / kill switches / permission flags, designing percentage rollouts, building kill-switch + circuit-breaker patterns, structuring evaluation contexts (user IDs, plan tier, region), or building flag-cleanup discipline. Triggers: LaunchDarkly / GrowthBook / Unleash / Flagsmith / OpenFeature, percentage ramp, sticky bucketing, kill switch wired to alerting, "we still have flags from 2 years ago", flag debt, OpenFeature provider, evaluation context, default value on provider failure. NOT for A/B test statistical analysis (separate skill), traffic-split routing at the edge, build-time bundler defines, or environment-based config.

Applies game theory to multi-agent coordination protocols with advisory claims, repeated interactions, daemon-mediated correlation, and deviation penalties. Use for Nash equilibrium checks, folk-theorem cooperation analysis, correlated-equilibrium routing, and price-of-anarchy audits in strategic agent systems. NOT for consumer pricing, card-game strategy, or general microeconomics outside agent coordination.

Build production CI/CD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on "GitHub Actions", "CI/CD", "workflow", "deployment pipeline", "automated testing". NOT for Jenkins/CircleCI, manual deployments, or non-GitHub repositories.

Choose what kind of knowledge to transfer between teacher and student models: response, feature, or relational, and decide among offline, online, self, or cross-modal distillation schemes. Best for distillation strategy selection, capacity-gap diagnosis, and transfer planning. Activate on "knowledge distillation", "teacher-student", "soft labels", "feature distillation", "online distillation", or "cross-modal transfer". NOT for generic compression checklists or unrelated training work.

Mobile push notification expert for FCM, APNs, deep linking, rich notifications, and notification channels. Activate on: push notifications, FCM setup, APNs configuration, notification channels, deep link from notification, rich notification, notification permissions, silent push. NOT for: in-app messaging (use react-native-architect), email notifications (use devops-automator), SMS (use api-architect).

Build production document ingestion pipelines with chunking, embedding, and vector DB storage. Activate on: document ingestion, chunking strategy, embedding pipeline, vector DB ingestion, RAG indexing. NOT for: LLM prompt design (prompt-engineer), retrieval query logic (ai-engineer), or vector DB ops/migration (vector-database-migration-tool).

Compiling formal invariants (TLA+, Alloy, temporal logic) into runtime monitors that continuously audit agent coordination daemons. The Arbiter pattern: a verification agent that smoke-tests live sessions against proven properties and triggers salvage on violation. NOT FOR application performance monitoring (use observability skills), log aggregation, static analysis, or unit testing.

Extract keyframes, detect scenes, and build CLIP-indexed temporal search over video content. Activate on: keyframe extraction, scene detection, video search, video indexing, temporal analysis. NOT for: video editing/rendering (video-processing-editing), video generation (ai-video-production-master).

Implementing the relying-party (server) side of WebAuthn / passkeys to replace passwords — the registration ceremony, the authentication ceremony, the verification steps the server MUST perform on each (challenge match, origin match, RP ID hash, signature, counter monotonicity), conditional UI for autofill, and the synced-vs-device-bound distinction. Grounded in W3C WebAuthn-3, FIDO Alliance, passkeys.dev, and SimpleWebAuthn.

API gateway and reverse proxy configuration with Kong, Nginx, Traefik, routing, and auth middleware. Activate on: API gateway, reverse proxy, Kong, Nginx, Traefik, load balancer, ingress, auth middleware. NOT for: rate limiting algorithms (use api-rate-limiting-throttling-expert), service mesh (use service-mesh-microservices-expert).

Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols. Implements suicide ideation detection, automated escalation, and crisis resource integration. Use for mental health apps, recovery platforms, support communities. Activate on "crisis detection", "suicide prevention", "mental health NLP", "intervention protocol". NOT for general sentiment analysis, medical diagnosis, or replacing professional help.

Analyze bonded agent systems, escrow workflows, slashing rules, oracle trust, Sybil cost, and front-running risk in protocols where agents post bonds or stake reputation. Use for collateral sizing, griefing analysis, dispute design, and bonded-agent security reviews. NOT for smart contract auditing, DeFi tokenomics, blockchain consensus design, or trading strategy.

PgBouncer, connection optimization, and pooling strategies for database performance. Activate on: connection pool, PgBouncer, database connections, pool size, connection limit, Prisma pool, Drizzle pool. NOT for: query optimization (use data-warehouse-optimizer), database schema design (use dimensional-modeler).

Message queues, pub/sub, event sourcing with Kafka, RabbitMQ, Redis Streams. Activate on: event-driven, message queue, pub/sub, Kafka, RabbitMQ, event bus, async messaging, dead letter queue. NOT for: CQRS projections (use cqrs-event-sourcing-architect), real-time WebSocket (use websocket-realtime-expert), observability (use observability-apm-expert).

Design dashboards for migrations and runtimes. Use for authority drift, verifier status, burn-down, runtime health, or pain panels. NOT for vanity analytics, ad hoc charts, or duplicate reporting.

Application of Six Sigma quality methodology to AI agent process improvement and reliability

Build image generation pipelines with Stable Diffusion, FLUX, ControlNet, LoRA, and ComfyUI workflows. Activate on: image generation pipeline, ComfyUI workflow, ControlNet, LoRA training, diffusion model. NOT for: video generation (ai-video-production-master), image classification (computer-vision-pipeline).

Automate Kubernetes deployment lifecycle: kubectl rollouts, GitOps sync (ArgoCD/Flux), namespace and secret management, rollout monitoring, and failed deployment troubleshooting. Use when deploying manifests to clusters, debugging stuck rollouts, setting up GitOps pipelines, or managing multi-environment promotion. NOT for: generating K8s manifests (use kubernetes-manifest-generator), blue-green/canary traffic shifting (use blue-green-deployment-orchestrator), cluster provisioning (use terraform-module-builder), CI/CD pipeline config (use github-actions-pipeline-builder).

Plan and run manager-led, role-based teams where assignments change by round, roles may be added midstream, and the manager decides when the work is ready to ship. Use when delegation should adapt to emerging evidence rather than a fixed review loop. NOT for static approval chains, uncoordinated message swarms, or blackboard-style shared-state diagnosis.

Design agent-labor markets with bond pricing, escrow settlement, oracle incentives, cold-start bootstraps, and collusion-resistant marketplace rules. Use for collateralized task contracts, Float Plan bond sizing, settlement design, and incentive analysis for agent work. NOT for general auction theory teaching, DeFi tokenomics, payment gateway integration without marketplace incentives, or generic game theory tutoring.

Tenant isolation, row-level security, shared/siloed schema patterns for SaaS platforms. Activate on: multi-tenant, tenant isolation, RLS, shared database, SaaS architecture, tenant context, data isolation. NOT for: connection pooling (use database-connection-pool-manager), API gateway routing (use api-gateway-reverse-proxy-expert).

Facilitate collaborative, emotionally aware conversations and guide toward productive dialogue. Use when the user wants de-escalation, mutual understanding, structured discussion, conflict resolution, or mentions 'productive discussion', 'collaborative debate', 'dialog vs debate', 'find common ground', 'help us talk about', 'de-escalate'. Includes a couples-in-recovery mode for fragile nervous systems. Can orchestrate other discourse skills in a structured sequence.

Drawing the `'use client'` boundary correctly in React Server Components apps (Next.js App Router, RSC frameworks) — leaf-pushing, slot composition, serialization rules, and environment poisoning prevention. Grounded in react.dev and Next.js 16 docs.

Choosing between Server-Sent Events and WebSockets for real-time client connections, and implementing whichever you pick correctly — SSE wire format per WHATWG, WebSocket frame format per RFC 6455, automatic reconnection with `Last-Event-ID`, ping/pong heartbeats, the HTTP/1.1 6-connection-per-origin limit, and the proxy-buffering trap that silently breaks SSE. Grounded in WHATWG, RFC 6455, MDN.

Distributed task allocation protocol where agents negotiate task assignments through contract bidding

Use when changing schema on a live production database without dropping traffic, doing expand/contract migrations, backfilling new columns on million-plus-row tables, dual-writing across schemas, renaming a hot column, splitting a table, or adding a foreign key to a big table. Triggers: ALTER TABLE locks the world, "must be removed in a separate deploy", expand-contract-cleanup phases, NOT NULL on populated column, foreign-key add on big table, dropping a column still read by old replicas, lock_timeout choice, gh-ost vs pt-online-schema-change. NOT for greenfield schema design, ORM-managed migration mechanics (Prisma/Drizzle), D1/Supabase CLI quirks, or NoSQL document migrations.

Jetpack Compose navigation expert with type-safe routes, Hilt DI, and MVVM/MVI architecture. Activate on: Jetpack Compose navigation, Compose type-safe routes, Hilt dependency injection, MVVM Android, MVI pattern, Compose state management, NavHost, ViewModel. NOT for: XML layouts (use frontend-architect), iOS SwiftUI (use swiftui-data-flow-expert), React Native (use react-native-architect).

Istio, Envoy, circuit breakers, and service discovery for microservices. Activate on: service mesh, Istio, Envoy, sidecar, circuit breaker, service discovery, mTLS, traffic management. NOT for: API gateway edge routing (use api-gateway-reverse-proxy-expert), application-level observability (use observability-apm-expert).

Android background task specialist for WorkManager, Foreground Services, Doze mode, and battery optimization. Activate on: WorkManager, background task Android, Foreground Service, Doze mode, battery optimization, periodic work, background sync Android, JobScheduler. NOT for: iOS background tasks (use swiftui-data-flow-expert), React Native background (use mobile-offline-sync-architect), UI architecture (use jetpack-compose-navigation-expert).

Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns. Activate on "optimize prompt", "improve this prompt", "prompt engineering", or ANY complex task request. Requires prompt-learning MCP server. NOT for simple questions (just answer them), NOT for direct commands (just execute them), NOT for conversational responses (no optimization needed).

Design roadside signs and large-format ads for businesses, especially automotive dealers. Use for pylon signs, monument signs, lot banners, highway billboards, digital roadside boards, service-lane signage, used-car event signs, lease or finance campaign concepts, and other driver-at-speed messaging where legibility, offer hierarchy, and dealer ad compliance matter. Activate on "road sign", "billboard", "dealership sign", "car dealer ad", "pylon sign", "monument sign", "service lane signage", "automotive billboard", "roadside ad", "dealer lease offer", or "drive-by signage". NOT for fabrication drawings, permitting or local sign-code review, web or social ad campaigns, or full brand identity systems.

Blue-green and canary deployment orchestrator with traffic shifting and automated rollback. Activate on: blue-green deployment, canary release, rolling deployment, traffic shifting, rollback automation, progressive delivery, Argo Rollouts, Flagger. NOT for: K8s manifest generation (use kubernetes-manifest-generator), CI/CD pipeline setup (use github-actions-pipeline-builder), monitoring (use monitoring-stack-deployer).

Redis caching patterns, cache-aside, write-through, TTL strategies, and invalidation. Activate on: caching, Redis, cache invalidation, cache-aside, write-through, TTL, CDN cache, stale-while-revalidate. NOT for: CDN/reverse proxy setup (use api-gateway-reverse-proxy-expert), database query optimization (use data-warehouse-optimizer).

name: human-centered-design-fundamentals

Production stability patterns including circuit breakers, bulkheads, and resilience strategies for real-world systems

Formal protocol verification with ProVerif and Tamarin Prover for multi-agent coordination systems. Use when modeling secrecy properties (escrow opacity, session note confidentiality), replay resistance (token dismissal finality, backup-restore attacks), delegation chain correctness, or append-only log integrity in applied pi calculus. Use when deciding between ProVerif and Tamarin for a given property. Use when extending existing .pv models (e.g., harbor_card_v3_delegation.pv) with new security queries. NOT for general cryptography tutorials, TLS certificate management, key management operations (rotation, storage, HSM integration), or smart contract verification (use Solidity-specific tools).

Token bucket, sliding window, and Redis-based rate limiting for API protection. Activate on: rate limiting, throttling, token bucket, sliding window, API abuse, DDoS protection, quota management. NOT for: API gateway setup (use api-gateway-reverse-proxy-expert), caching (use cache-strategy-invalidation-expert).

Expert in color theory, palette harmony, and perceptual color science for computational photo composition. Specializes in earth-mover distance optimization, warm/cool alternation, diversity-aware palette selection, and hue-based photo sequencing. Activate on "color palette", "color harmony", "warm cool", "earth mover distance", "Wasserstein", "LAB space", "hue sorted", "palette matching". NOT for basic RGB manipulation (use standard image processing), single-photo color grading (use native-app-designer), UI color schemes (use vaporwave-glassomorphic-ui-designer), or color blindness simulation (accessibility specialists).

Applies political philosophy frameworks (Hobbes, Locke, Rousseau, Rawls, Sen, Ostrom) to software architecture decisions -- authority models, resource allocation, capability assignment, and commons governance. NOT FOR general philosophy courses, ethics of AI alignment, trolley problems, or moral philosophy of consciousness.

Vaporwave + glassomorphic UI designer for photo/memory apps. Masters SwiftUI Material effects, neon pastels, frosted glass blur, retro-futuristic design. Expert in 2025 UI trends (glassmorphism, neubrutalism, Y2K), iOS HIG, dark mode, accessibility, Metal shaders. Activate on 'vaporwave', 'glassmorphism', 'SwiftUI design', 'frosted glass', 'neon aesthetic', 'retro-futuristic', 'Y2K design'. NOT for backend/API (use backend-architect), Windows 3.1 retro (use windows-3-1-web-designer), generic web (use web-design-expert), non-photo apps (use native-app-designer).

Apply Conway's homomorphism principle to multi-agent system design, recognizing that agent coordination structure predetermines system architecture and capability.

FIPA standard library of communicative acts (speech acts) for agent-to-agent messaging semantics

Analysis of how suppressing volatility creates fragile systems vulnerable to black swan events

Apply the foundational taxonomy of workflow control patterns to evaluate, design, and debug complex coordination systems. Based on the seminal "Workflow Patterns" research establishing pattern-based expressiveness evaluation.

API migration strategies, deprecation workflows, and header/URL/content versioning. Activate on: API versioning, backward compatibility, deprecation, breaking change, API migration, v1 v2, sunset header. NOT for: schema evolution in data (use schema-evolution-manager), gateway routing (use api-gateway-reverse-proxy-expert).

Decompose DAGs into execution chains using width bounds, stratification, virtual nodes, and matching. Use when minimizing workflow lanes in dependency graphs. NOT for cyclic graphs, generic scheduling, or one-off queries with no preprocessing payoff.

Mobile payment integration for Stripe, Apple Pay, Google Pay, in-app purchases, and subscription management. Activate on: mobile payments, Stripe SDK, Apple Pay, Google Pay, in-app purchase, StoreKit 2, Google Play Billing, subscription management, payment sheet. NOT for: backend payment processing (use api-architect), general e-commerce (use frontend-architect), financial compliance (use security-auditor).

Refactor apps so backend owns runtime truth and UI only projects snapshots. Use when tools have split authority. NOT for cosmetic UI work or new features before drift is removed.

IBM's autonomic computing vision for self-managing systems with self-configuration, healing, optimization, and protection

license: Apache-2.0 NOT for unrelated tasks outside this domain.

Mobile accessibility compliance expert for VoiceOver, TalkBack, Dynamic Type, and WCAG mobile guidelines. Activate on: mobile accessibility, VoiceOver, TalkBack, Dynamic Type, Accessibility Inspector, WCAG mobile, screen reader, accessibility audit, a11y mobile, inclusive design. NOT for: web accessibility (use design-accessibility-auditor), UI design (use native-app-designer), general testing (use test-automation-expert).

Apply NASA's battle-tested framework for building complex, mission-critical systems where failure has catastrophic consequences

Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

Apply normative BDI reasoning to agents that must detect norms, choose which commitments to internalize, and resolve conflicts by comparing consequences. Use when obligations, prohibitions, or policies collide in autonomous systems. NOT for simple fixed-priority rules, pure constraint satisfaction, or domains where no real normative conflict exists.

Implement executable BDI reasoning with explicit negation, paraconsistent revision, trigger-based commitment updates, and abduction. Use for runtime agent semantics and conflicting desires. NOT for purely axiomatic modal logic, black-box planners, or classical logic without operational semantics.

FIPA standard library of agent interaction protocols for structured multi-agent communication

license: Apache-2.0 NOT for unrelated tasks outside this domain.

Design deployment-focused distillation systems that balance model size, accuracy, calibration, and cascade escalation under real resource limits. Best for teacher-student compression, threshold design, and failure-aware deployment. Activate on "model compression", "teacher- student", "distillation score", "cascade model", "edge deployment", or "model calibration". NOT for generic deep-learning overviews, prompt optimization, or training work without a concrete distillation objective.