Windags Skills

Failure diagnosis, DAG mutation, and escalation engine for the WinDAGs meta-DAG. Receives failure information and quality vectors from the Evaluator. Classifies failures on four dimensions. Follows a five-level escalation ladder. Applies seven mutation types with saga compensation. Enforces BC-EXEC-002, BC-EXEC-003, BC-FAIL-002, BC-FAIL-005. Activate when operating as the Mutator role in the meta-DAG, when diagnosing node failures, when restructuring a DAG at runtime, or when deciding escalation level.

Framework for building multi-agent conversation systems with customizable LLM-powered agents

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

Design decisions for when and what sounds to use in web apps, mobile apps, and desktop native apps — plus how to create them with AI. Covers UI sound vocabulary (confirms, alerts, transitions, errors), platform conventions (iOS, macOS, Material), creating sounds with AI tools (ElevenLabs, AudioCraft, Stable Audio), Web Audio API for procedural sounds, haptic-audio pairing, and the psychology of satisfying vs. annoying UI sounds. Activate on 'app sounds', 'UI sounds', 'notification sound', 'sound design app', 'earcons', 'sonic branding', 'interaction sounds', 'feedback sounds', 'app audio', 'satisfying sounds'. NOT for professional audio engineering (use sound-engineer), Windows 3.1 retro sounds specifically (use win31-audio-design), music composition (use sound-engineer).

BDI (Beliefs-Desires-Intentions) agency framework for designing autonomous agents with mental state architectures

Integration of BDI agent architecture with soft systems methodology for complex organizational problem-solving

Systematic framework for resurrecting and modernizing legacy codebases through archaeology, resurrection, and rejuvenation phases. Activate on "legacy code", "inherited codebase", "no documentation", "technical debt", "resurrect", "modernize". NOT for greenfield projects or well-documented active codebases.

The intelligence layer of WinDAGs. Decomposes natural language tasks into Hierarchical Task DAGs (HTDAGs), matches subtasks to skills, executes waves in parallel, and dynamically expands nodes when complexity exceeds executor capability. Use for 'orchestrate', 'execute DAG', 'parallel agents', 'decompose task', 'coordinate skills'. NOT for single-skill tasks or simple linear workflows.

Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction design across any domain (portfolios, e-commerce, SaaS, adult content, technical showcases). This skill should be used when users need exhaustive design research, pattern recognition across large example sets, or systematic visual analysis for competitive positioning.

Expert DevOps engineer for CI/CD, IaC, Kubernetes, and deployment automation. Activate on: CI/CD, GitHub Actions, Terraform, Docker, Kubernetes, Helm, ArgoCD, GitOps, deployment pipeline, infrastructure as code, container orchestration. NOT for: application code (use language skills), database schema (use data-pipeline-engineer), API design (use api-architect).

Use when running analytical SQL over Parquet/CSV/JSON without a warehouse, replacing pandas for data wrangling, joining S3 data in-place, building local data marts, or embedding OLAP into an app. Triggers: read_parquet/read_csv setup, partitioned dataset queries, hive partitioning, glob patterns for S3, COPY TO export, attach Postgres/MySQL, UDFs in Python/R, MotherDuck cloud sync, columnar performance vs row stores. NOT for OLTP workloads (concurrent writes), distributed analytics at petabyte scale (use Spark/Trino), or vector search (use pgvector/Lance).

Manage feature manifests for code traceability. Use when creating new features, updating existing features, checking feature health, or exploring the feature-to-code relationship. Activates for manifest validation, feature creation, changelog updates, and traceability queries.

Ensure HIPAA compliance when handling PHI (Protected Health Information). Use when writing code that accesses user health data, check-ins, journal entries, or any sensitive information. Activates for audit logging, data access, security events, and compliance questions.

Modern authentication implementation for 2026 - passkeys (WebAuthn), OAuth (Google, Apple), magic links, and cross-device sync. Use for passwordless-first authentication, social login setup, Supabase Auth, Next.js auth flows, and multi-factor authentication. Activate on "passkeys", "WebAuthn", "Google Sign-In", "Apple Sign-In", "magic link", "passwordless", "authentication", "login", "OAuth", "social login". NOT for session management without auth (use standard JWT docs), authorization/RBAC (use security-auditor), or API key management (use api-architect).

Deterministic pixel art upscaling using EPX/Scale2x, hq2x/hq4x, and xBR algorithms that add valid sub-pixels through pattern recognition. Activate on 'pixel art scaling', 'EPX', 'Scale2x', 'hq2x', 'hq4x', 'xBR', 'retro game upscaling'. NOT for AI/ML upscaling, photo enlargement, or simple nearest-neighbor.

Builds DAG visualizations using ReactFlow v12 with custom nodes, ELKjs auto-layout, Zustand state management, and live state updates via WebSocket. Use when implementing workflow visualization dashboards, creating custom agent node components, integrating ELK layout algorithms, or wiring execution state into React components. Activate on "ReactFlow", "workflow visualization", "DAG visualization", "ELKjs", "custom nodes", "node-based editor", "graph visualization". NOT for writing Mermaid diagrams (use mermaid-graph-writer), general React development, or static diagram rendering.

Conducts thorough landscape research, competitive analysis, best practices evaluation, and evidence-based recommendations. Expert in market research and trend analysis.

Design motion, transitions, and bespoke graphics for native Rust gpui apps — the framework behind Zed and the pd-console operator console. Use for with_animation, easing curves, BoxShadow/glow, breathing dots, pane expand/zoom/slide transitions, and custom paint/Vello/wgpu surfaces. Trigger on: gpui animation, with_animation, gpui transition, gpui easing, BoxShadow, gpui shadow, pd-console motion, gpui paint/canvas, Vello, wgpu, "lift/slide/zoom/spring in gpui", reduced-motion in a native Rust UI, "animation re-renders forever", repeat() never stops. NOT for: web/React motion (→ animation-system-architect), CLI/TUI output (→ beautiful-cli-design), general non-motion GUI layout/color/typography (→ beautiful-gui-design).

Security vulnerability scanner and OWASP compliance auditor for codebases. Dependency scanning (npm audit, pip-audit), secret detection (high-entropy strings, API keys), SAST for injection/XSS vulnerabilities, and security posture reports. Activate on 'security audit', 'vulnerability scan', 'OWASP', 'secret detection', 'dependency check', 'CVE', 'security review', 'penetration testing prep'. NOT for runtime WAF configuration (use infrastructure tools), network security/firewalls, or compliance certifications like SOC2/HIPAA (legal/organizational).

Analyze complex systems through stocks, flows, and feedback loops to find high-leverage interventions. For organizational, environmental, social, and technical systems exhibiting circular causality. NOT for linear problems or simple cause-effect chains.

Expert technical documentation specialist for developer docs, API references, and runbooks. Activate on: documentation, docs, README, API reference, technical writing, user guide, runbook, ADR, changelog, release notes, tutorial, how-to guide. NOT for: marketing copy (use copywriting skills), blog posts (use content skills), code comments (handled by developers).

High-converting web design techniques that dazzle and persuade. Covers social proof design, pricing page architecture, CTA optimization, scroll-driven persuasion, interactive demos, trust signals, and the visual craft behind sites that sell. Activate on 'sales page design', 'conversion design', 'high-converting', 'landing page that sells', 'pricing page design', 'social proof', 'dazzle', 'wow factor', 'persuasive design', 'conversion rate', 'make it sell'. NOT for copywriting (use marketing copywriting skills), not for A/B testing setup (use frontend-developer), not for paid ad creative (use marketing skills).

AI-powered career biographer that conducts empathetic interviews, extracts structured career narratives, and transforms professional stories into portfolios, CVs, and personal brand assets. This skill should be used when users want to document their career journey, create professional portfolios, generate CVs, or craft compelling career narratives.

Implement AI chatbot analytics and conversation monitoring. Use when adding conversation metrics, tracking AI usage, measuring user engagement with chat, or building conversation dashboards. Activates for AI analytics, token tracking, conversation categorization, and chat performance.

Interprets GitHub Actions run status and logs, diagnoses CI failure patterns, and suggests targeted fixes. Handles dependency install failures, test timeouts, build OOM, flaky tests, and workflow misconfigurations. Activate on: 'CI failing', 'build broken', 'workflow error', 'GitHub Actions debug', 'flaky CI', 'pipeline timeout', 'CI red'. NOT for: writing new workflows from scratch (use github-actions-pipeline-builder), CI caching strategy (use ci-cache-optimizer), deployment orchestration (use devops-automator).

Application architecture patterns and code organization — clean architecture, hexagonal architecture, feature-based structure, dependency inversion, module boundaries, SOLID principles at module scale. Activate on "clean architecture", "hexagonal architecture", "feature-based structure", "dependency inversion", "module boundaries", "architecture pattern", "folder structure", "fat controller", "circular dependency", "IoC container". NOT for microservice decomposition (use microservices-patterns) or database schema design (use database-design-patterns).

Parses complex problems into DAG (Directed Acyclic Graph) execution structures. Decomposes tasks into nodes with dependencies, identifies parallelization opportunities, and creates optimal execution plans. Activate on 'build dag', 'create workflow graph', 'decompose task', 'execution graph', 'task graph'. NOT for simple linear tasks or when an existing DAG structure is provided.

Build and extend pd-console — Port Daddy's GPU-native macOS operator console (GPUI 0.2.x, Zed's Rust UI). Covers the render-agnostic Block/Pane(Surface) contract, the two-thread reqwest↔smol refresh pipeline, Taffy flexbox layout, uniform_list virtual scroll, focus + keyboard nav, the OKLCH theme and ICS maritime flag badges, GPUI's missing text-input, and the real feature-gated cargo/CI gate. Use when adding panes, visual polish, or debugging GPUI rendering/layout/focus in core/pd-console. NOT for the TypeScript daemon, generic Rust toolchain/borrow-checker help (use rust-with-claude-code), or non-pd GPUI apps with a different theme/architecture.

Declarative programming framework for optimizing LLM prompts through compilation and automatic tuning

Use when designing, building, or debugging a Model Context Protocol (MCP) server in Node/TypeScript. Triggers: stdio JSON-RPC handshake, tool descriptions as discovery surface, lazy startup vs eager catalog loading, telemetry placement, schema design for tool inputs (zod), tool naming conventions for discoverability, error handling that does not leak stack traces, MCP client compatibility (Claude Desktop, Claude Code, Cursor), local resource fetching, secrets and env var handling, distributing as npm + claude mcp add. NOT for MCP client implementation, MCP HTTP transport (different surface), Anthropic Agent SDK building, or non-MCP plugin systems.

Motion design and micro-animations for web interfaces — Framer Motion layout animations, CSS scroll-driven animations, View Transitions API, GSAP ScrollTrigger, spring physics tuning, loading choreography, and Disney's 12 principles applied to UI. Makes interfaces feel alive without feeling busy. Activate on 'web animation', 'Framer Motion', 'micro-interaction', 'scroll animation', 'page transition', 'View Transitions API', 'spring animation web', 'motion design', 'loading animation', 'skeleton screen', 'hover effect', 'GSAP ScrollTrigger'.

Build ontology logs (ologs) from problem descriptions using categorical foundations. Use when designing problem taxonomies, classifying tasks for routing, building knowledge libraries, establishing formal analogies between domains via functor search, or translating between natural language and database schemas. NOT for OWL/RDF ontology work, query tuning, or graph modeling without functional-arrow discipline.

Expert in residential hollow space detection, hidden room discovery, and safe room planning. Helps map house dimensions, identify anomalies suggesting hidden spaces, and safely explore potential voids. Knowledge of architectural history, construction methods, and non-destructive investigation techniques. Activate on "panic room", "hidden room", "secret room", "hollow space", "house mapping", "find hidden space", "room dimensions", "hidden door", "false wall", "priest hole", "prohibition era", "safe room". NOT for illegal entry, structural modifications without permits, or bypassing security systems.

Modernizes legacy scripts (bash, Node, Python) by replacing deprecated APIs, adding error handling, converting callbacks to async/await, and improving maintainability. Turns brittle one-off scripts into reliable, documented tools.

Working type director's reference for selecting, pairing, and shipping typefaces with real taste. Covers a broad, opinionated catalog of typefaces and foundries (libre through commercial), a mood/era/register-driven selection framework that never collapses to one answer, font pairing as logic, fluid type scales, variable-font axes (incl. opsz/GRAD), OpenType features, web-font performance (subsetting, font-display, size-adjust fallback metrics), and licensing literacy (SIL OFL vs commercial EULA, desktop/web/app, trials). Explicitly retires the overused AI-design defaults (Inter, Roboto, Montserrat, Poppins, Fraunces, Geist, Söhne, the Fontshare/ITF starter pack) and names fresher alternatives in every role. Use for font selection, pairing, type scales, web-font optimization, variable fonts, OpenType, and typographic systems. NOT for logo/wordmark design, icon fonts, general CSS, or image-based/raster typography.

Deploy Next.js applications to Vercel with proper configuration. Use when setting up deployment, configuring environment variables, edge functions, or troubleshooting builds. Activates for deployment issues, environment setup, and Vercel configuration.

Mental models and decision frameworks for building autonomous agents that continuously learn, explore, and accumulate skills in open-ended environments without human supervision

Creates unique web designs with brand identity, color palettes, typography, and modern UI/UX patterns. Use for brand identity development, visual design systems, layout composition, and responsive web design. Activate on "web design", "brand identity", "color palette", "UI design", "visual design", "layout". NOT for typography details (use typography-expert), color theory deep-dives (use color-theory-expert), design system tokens (use design-system-creator), or code implementation without design direction.

Creates realistic ocean and water wave effects for web using SVG filters (feTurbulence, feDisplacementMap), CSS animations, and layering techniques. Use for ocean backgrounds, underwater distortion, beach scenes, ripple effects, liquid glass, and water-themed UI. Activate on "ocean wave", "water effect", "SVG water", "ripple animation", "underwater distortion", "liquid glass", "wave animation", "feTurbulence water", "beach waves", "sea foam". NOT for 3D ocean simulation (use WebGL/Three.js), video water effects (use video editing), physics-based fluid simulation (use canvas/WebGL), or simple gradient backgrounds without wave motion.

Build WinDAGs — the orchestration platform where AI agents accumulate genuine expertise through DAGs of skillful agents. Covers DAG design, execution engines, meta-DAG architecture, skill selection, dynamic mutation, visualization, and deployment. Activate on "windags", "agent DAG", "DAG of agents", "workflow orchestration", "agent pipeline", "dynamic DAG", "meta-DAG", "build windags", "implement windags". NOT for understanding WHY decisions were made (use windags-avatar), creating individual skills (use skill-architect), or managing skill libraries (use windags-librarian).

Two-stage review engine with four-layer quality model for the WinDAGs meta-DAG. Receives completed node outputs and produces ReviewResult containing QualityVector. Stage 1 (Haiku) checks Floor + Wall on every node. Stage 2 (Sonnet) runs Ceiling evaluation conditionally using economic escalation formula. Enforces BC-EVAL-001 through BC-EVAL-006. Activate when operating as the Evaluator role in the meta-DAG, when reviewing node outputs, when computing quality vectors, or when deciding Stage 2 escalation.

Deep analysis of knowledge distillation techniques for compressing large models into smaller efficient ones

Apply Raft's design principles for building understandable, reliable distributed and multi-agent systems

Simulation of believable human behavior using LLM-powered generative agents with memory and social interaction

Choosing a Postgres connection pool mode that matches your workload — pgBouncer session/transaction/statement modes, the prepared-statement story (pgBouncer 1.21+), Supabase Supavisor's port-per-mode pattern (5432 vs 6543), AWS RDS Proxy pinning triggers, and `pg_stat_activity` diagnostics. Grounded in pgbouncer.org, supabase.com, AWS docs, and PostgreSQL docs.

Designing Postgres Row-Level Security (RLS) policies for multi-tenant authorization, especially in Supabase / PostgREST stacks — `CREATE POLICY` syntax, USING vs WITH CHECK, PERMISSIVE/RESTRICTIVE merge semantics, the `(SELECT auth.uid())` performance pattern that turns 171ms scans into <1ms, indexes still required, role-based bypass via BYPASSRLS, security-definer escape hatches. Grounded in postgresql.org, Supabase docs, and Gary Austin's RLS-Performance benchmarks.

Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on "React performance", "slow render", "useMemo", "bundle size", "virtualization". NOT for backend optimization, non-React frameworks, or premature optimization.

Design and implement Swiss modern websites using International Typographic Style principles translated for the contemporary web: strict grids, typography-led hierarchy, asymmetrical composition, disciplined whitespace, restrained color, and editorial clarity. Use for SaaS marketing sites, portfolios, product pages, documentation, dashboards, and design systems that need clarity, rigor, and visual authority. NOT for neobrutalism, skeuomorphic UI, glassmorphism, retro desktop aesthetics, maximalist collage systems, or illustration-first playful brands.

Techniques for surfacing implicit, hard-to-articulate knowledge that experts use in practice

Designing TanStack Query (React Query) v5 for server-state management — query key factories, staleTime vs gcTime, partial-match invalidation, optimistic updates with rollback, prefetching, and Next.js App Router hydration. Grounded in tanstack.com v5 docs.

Prepares for "reverse system design" rounds where you present YOUR past technical work. Use for project selection, narrative arc structuring, whiteboard diagrams, depth calibration, and hostile Q&A handling. Activate on "tech presentation", "present your work", "reverse system design", "project deep dive". NOT for designing hypothetical systems, resume writing, or career narrative extraction.

Use when designing discriminated unions, debugging control-flow analysis, choosing satisfies vs as, building branded types, writing user-defined type guards, or composing conditional types and template literal types. Triggers: "Type X is not assignable to type Y" after a type guard, exhaustiveness checks via never, satisfies vs explicit annotation, infer in conditional types, mapped types with key remapping, distributive conditional types, type-narrowing inside callbacks losing the narrowed type. NOT for runtime validation only (zod/yup), tsc compiler internals, or design-time-only types not used at runtime.

Coaches behavioral and values-fit interview preparation with negative framing, deep follow-ups, introspection, and mission alignment. Use for culture-fit rounds, Anthropic behavioral prep, failure stories, and self-awareness drilling. Activate on "behavioral interview", "values interview", "culture fit", "tell me about a failure". NOT for coding interviews, system design, resume writing, or technical deep dives.

Longitudinal memory tracking, philosophy teaching, and personal accountability with compassion. Expert in pattern recognition, Stoicism/Buddhism, and growth guidance. Activate on 'accountability', 'philosophy', 'Stoicism', 'Buddhism', 'personal growth', 'commitment tracking', 'wisdom teaching'. NOT for therapy or mental health treatment (refer to professionals), crisis intervention, or replacing professional coaching credentials.

Comprehensive introduction to multi-agent systems covering coordination, communication, and distributed AI theory

Formal verification approach to LLM evaluation ensuring correctness and consistency in automated judging

Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).

What you can build and do with an always-on AI agent that has episodic memory. Covers concrete product ideas, workflows, emergent capabilities from persistence plus memory, and real-world examples of deployed persistent agents. Helps you go from "I have the architecture" to "here's what it actually does for me." Activate on: "what can an always-on agent do", "persistent agent use cases", "agent applications", "proactive agent ideas", "what to build with episodic memory", "always-on agent product", "personal AI assistant ideas", "/always-on-agent-applications". NOT for: building the architecture (use always-on-agent-architecture), designing inputs (use always-on-agent-inputs), safety and privacy (use always-on-agent-safety).

Architecture and systems design for building always-on AI agents with episodic memory. Covers the memory hierarchy (core/recall/archival), persistence layers, agent server infrastructure, vector stores, and framework selection. Provides concrete deployment patterns for agents that maintain identity and learn across sessions. Activate on: "always-on agent", "persistent agent architecture", "episodic memory system", "agent memory design", "long-running agent", "stateful agent", "agent that remembers", "MemGPT architecture", "Letta deployment", "/always-on-agent-architecture". NOT for: choosing what data to feed the agent (use always-on-agent-inputs), brainstorming applications (use always-on-agent-applications), safety and privacy concerns (use always-on-agent-safety), general agentic patterns (use agentic-patterns).