Hanzo Skills

hanzo

core

claude-api

agent-designThis file covers decision heuristics for building agents on the Claude API: which primitives to reach for, how to design your tool surface, and how to manage context and cost over long runs.anthropic-cliThe ant CLI exposes every Claude API resource as a shell subcommand.batchesbatches claude-platform-on-awsAnthropic-operated access to the Claude Developer Platform through AWS infrastructure — SigV4 authentication, AWS IAM access control, and AWS Marketplace billing.error-codesThis file documents HTTP error codes returned by the Claude API, their common causes, and how to handle them.examplesUse these examples when the user needs raw HTTP requests or is working in a language without an official SDK.files-apiFiles live under client.Beta.Files (namespace Anthropic.Models.Beta.Files).live-sourcesThis file contains WebFetch URLs for fetching current information from platform.claude.com and Agent SDK repositories.managed-agentsUse these examples when the user needs raw HTTP requests or is working without an SDK.managed-agents-api-referenceAll endpoints require x-api-key and anthropic-version: 2023-06-01 headers.managed-agents-client-patternsPatterns you'll write on the client side when driving a Managed Agent session, grounded in working SDK examples.managed-agents-coreManaged Agents is built around four core concepts:managed-agents-environmentsCreating a session requires an environmentid.managed-agents-eventsSend events to a session via POST /v1/sessions/{id}/events.managed-agents-memorySessions are ephemeral by default — when one ends, anything the agent learned is gone.managed-agents-multiagentA coordinator agent can delegate to other agents within one session.managed-agents-onboardingClaude Managed Agents is a hosted agent: Anthropic runs the agent loop and provisions a sandboxed container per session where the agent's tools execute (or your own worker, with a selfhosted environment — see shared/managed-agents-self-host managed-agents-outcomesAn outcome elevates a session from conversation to work: you state what "done" looks like, and the harness runs an iterate → grade → revise loop until the artifact meets the rubric, hits maxiterations, or is interrupted.managed-agents-overviewManaged Agents provisions a container per session as the agent's workspace.managed-agents-scheduled-deploymentsA scheduled deployment runs an agent on a recurring cron schedule — each firing creates a session autonomously.managed-agents-self-hosted-sandboxesWith config.type: "selfhosted", the agent loop stays on Anthropic's orchestration layer but tool execution moves to infrastructure you control — bash, file ops, and code run inside your container, so filesystem contents and network egress n managed-agents-toolsRecommendation: Enable all prebuilt tools via agenttoolset20260401, then disable individually as needed.managed-agents-webhooksAnthropic can POST to your HTTPS endpoint when a Managed Agents resource changes state — an alternative to holding an SSE stream or polling.model-migrationHow to move existing code to newer Claude models.modelsOnly use exact model IDs listed in this file.platform-availabilityWhich features work on which provider platform.prompt-auditPrompts, skills, and tool descriptions accumulate instructions tuned to older models: emphasis added because an old model under-triggered, step-by-step scripts added because an old model planned poorly, format scaffolds written before the A prompt-cachingThis file covers how to design prompt-building code for effective caching.sdk-upgradeanthropic 1.x is deliberately a small step from the last 0.x release: no method was restructured and no new pattern is required.streamingvar parameters = new MessageCreateParams { Model = Model.ClaudeOpus48, MaxTokens = 64000, Messages = new() { Role = Role.User, Content = "Write a haiku" } };token-countingUse the counttokens endpoint (POST /v1/messages/counttokens) for accurate token counts against Claude models.tool-useFor conceptual overview (tool definitions, tool choice, tips), see shared/tool-use-concepts.md(../../shared/tool-use-concepts.md).tool-use-conceptsThis file covers the conceptual foundations of tool use with the Claude API.

engineering

blameless-postmortemDate: 2025-10-27 Incident Commander: Alice Smith (@alice) Severity: Sev2 Duration: 45 minutes (14:23 - 15:08 UTC) Impact: ~15,000 users experienced errors (10% of active users) Error Budget Impact: 15% of monthly budget consumed database-connection-pool-exhaustedService: API Service Component: Database Layer Owner: Database Team (@database-team) Last Updated: 2025-10-27 Severity: Usually SEV-2, can escalate to SEV-1 engineering-capacity-planningComprehensive capacity planning including forecasting, resource modeling, load testing, scaling strategies, cost optimization, and disaster recovery planning for production systems engineering-ci-cd-pipelinesComprehensive CI/CD pipeline design covering build, test, security, deployment automation, artifact management, and multi-platform implementation (GitHub Actions, GitLab CI, Jenkins, CircleCI)engineering-code-qualityCode quality metrics, maintainability principles, SOLID design, code smells detection, and quality measurement engineering-code-reviewCode review practices, PR etiquette, constructive feedback, automation tools, and effective review workflows engineering-continuous-integrationCI/CD pipeline design, automated testing, deployment strategies, and continuous delivery best practices engineering-deployment-strategiesProduction deployment strategies including blue-green, canary, rolling updates, zero-downtime deployments, and database migrations engineering-design-patternsGang of Four design patterns, when to use each pattern, implementation examples, and anti-patterns engineering-domain-driven-designDomain-Driven Design patterns, bounded contexts, aggregates, entities, value objects, and strategic design engineering-functional-programmingFunctional programming principles, immutability, pure functions, higher-order functions, and FP patterns engineering-incident-responseComprehensive incident response practices including lifecycle management, severity classification, war rooms, runbooks, blameless postmortems, and SRE metrics (MTTR, MTTD, MTTA, MTBF)engineering-monitoring-alertsProduction-ready monitoring and alerting strategies engineering-pair-programmingPair programming techniques, driver-navigator roles, mob programming, remote pairing tools and best practices engineering-refactoring-patternsRefactoring techniques, when to refactor, safe refactoring strategies, and code improvement patterns engineering-rfc-consensus-buildingStakeholder identification, feedback collection, consensus building, and approval processes for RFCs engineering-rfc-decision-documentationArchitecture Decision Records (ADRs), decision rationale, status tracking, and post-implementation review engineering-rfc-structure-formatRFC document structure, templates, formatting conventions, and versioning for technical design documents engineering-rfc-technical-designArchitecture proposals, technical diagrams, API design, trade-off analysis, and migration strategies for RFCs engineering-technical-debtIdentifying, measuring, tracking, and managing technical debt strategically and systematically engineering-test-driven-developmentTest-Driven Development methodology, red-green-refactor cycle, unit testing best practices, and mocking strategies error-budget-policyService: Payment API Owner: Payments Team Last Updated: 2025-10-27 Version: 2.0 flag_retirement_workflowProduction-ready workflow for safely retiring feature flags with checklists, timelines, and automation.high-memory-usageThis alert fires when memory usage exceeds 90% for more than 5 minutes on any node.on-call-runbookQuick reference for on-call engineers supporting the Payment API.pull_request_template- Bug fix (non-breaking change fixing an issue) - New feature (non-breaking change adding functionality) - Breaking change (fix or feature that breaks existing functionality) - Refactoring (no functional changes, just code restructu sev1-incident-templateThis template provides a structured approach for managing critical (SEV-1) incidents.sev1-response-workflowThis document provides a complete walkthrough of responding to a SEV-1 (critical) incident from detection to postmortem.tdd-workflowComplete guide to practicing Test-Driven Development from project setup through delivery.templateBrief description of what this alert means and why it exists.

dspy-assertionsAdding constraints and validation to DSPy programs with assertions and suggestions dspy-evaluationEvaluating DSPy programs with metrics, Evaluate class, and performance analysis dspy-modulesBuilding composable prediction modules with Predict, ChainOfThought, ReAct, and custom modules dspy-optimizersOptimizing DSPy programs with teleprompters, BootstrapFewShot, MIPROv2, and compilation dspy-ragBuilding Retrieval-Augmented Generation pipelines with DSPy and vector databases dspy-setupInstallation, configuration, and language model setup for DSPy framework including Modal and HuggingFace dspy-signaturesDefining input/output signatures for DSPy modules and language model tasks graph-ragGraph-based retrieval-augmented generation with entity extraction, community detection, and multihop reasoning hierarchical-ragMulti-level retrieval with recursive summarization and parent-child document structures for improved context selection hybrid-search-ragCombining vector search with BM25 sparse retrieval using fusion algorithms for improved RAG accuracy ml-custom-llm-evaluationDomain-specific LLM evaluation including custom metrics, RLHF evaluation, adversarial testing, bias detection, Arize Phoenix integration, and continuous evaluation patterns for production systems ml-diffusion-finetuningFine-tuning diffusion models for custom styles or subjects ml-diffusion-model-basicsUnderstanding diffusion model theory and mechanics (forward/reverse process)ml-huggingface-autotrainNeed quick fine-tuning without writing training code ml-huggingface-datasetsLoading, processing, and managing datasets with HuggingFace datasets library ml-huggingface-hubManaging models, datasets, and Spaces on HuggingFace Hub ml-huggingface-spacesDeploying Gradio and Streamlit apps on HuggingFace Spaces ml-huggingface-transformersLoading models, pipelines, inference, and tokenization with transformers library ml-llm-as-judgeComprehensive guide to LLM-as-judge evaluation patterns including Prometheus 2 models, G-Eval framework, pairwise/pointwise/reference-guided methods, bias mitigation, and uncertainty quantification ml-llm-benchmarks-evaluationComprehensive guide to evaluating LLMs using standard benchmarks including MMLU, HellaSwag, BBH, HumanEval, TruthfulQA, and GSM8K, with practical implementation using LightEval and lm-evaluation-harness ml-llm-dataset-preparationPreparing training data for LLM fine-tuning ml-llm-evaluation-frameworksProduction-grade LLM evaluation using Arize Phoenix (OpenTelemetry tracing, self-hosted evals), Braintrust (86x faster search), LangSmith, and Langfuse with cost tracking and observability integration ml-llm-model-routingIntelligent LLM routing with RouteLLM, semantic routing, and cost optimization ml-llm-model-selectionChoosing the right LLM based on capabilities, benchmarks, pricing, and use cases ml-lora-peft-techniquesFine-tuning large models with limited GPU memory ml-multi-model-orchestrationCoordinating multiple LLMs in pipelines, ensembles, and cascading workflows ml-rag-evaluation-metricsComprehensive guide to RAG evaluation using RAGAS (Faithfulness, Answer Relevancy, Context Precision/Recall), LLM-as-judge patterns, synthetic datasets, and integration with Arize Phoenix and Langfuse ml-stable-diffusion-deploymentDeploying Stable Diffusion models to production environments ml-unsloth-finetuningFine-tuning LLMs (Llama, Mistral, Qwen) efficiently rag-reranking-techniquesMulti-stage retrieval pipelines with cross-encoder and LLM-based reranking for improved RAG precision

math

abstract-algebraAbstract algebra including groups, rings, fields, Galois theory, and algebraic structures advanced-graph-algorithmsSpecialized graph algorithms including graph decomposition, vertex coloring, matching algorithms, and 2024 research advances category-theory-foundationsCategory theory foundations including categories, functors, natural transformations, limits, and adjunctions differential-equationsDifferential equations including ODEs, PDEs, analytical methods, numerical solutions graph-data-structuresEfficient graph representations including adjacency matrices, adjacency lists, edge lists, and specialized structures with space-time tradeoffs graph-theory-applicationsReal-world applications of graph algorithms including social networks, routing, dependency resolution, recommendation systems, and network analysis graph-theory-fundamentalsCore concepts, terminology, and mathematical foundations of graph theory including graph types, properties, and fundamental theorems graph-traversal-algorithmsBreadth-first search, depth-first search, topological sort, strongly connected components, and traversal-based graph analysis math-linear-algebra-computationSolving systems of linear equations (Ax = b)math-numerical-methodsSolving ordinary differential equations (ODEs)math-optimization-algorithmsMachine learning model training (gradient descent, Adam, SGD)math-probability-statisticsStatistical hypothesis testing (t-test, chi-square, ANOVA)minimum-spanning-tree-algorithmsKruskal and Prim algorithms for finding minimum spanning trees in weighted undirected graphs with union-find and priority queue optimizations network-flow-algorithmsMaximum flow, minimum cut, Ford-Fulkerson, Edmonds-Karp, and flow-based algorithms for capacity-constrained network optimization number-theoryNumber theory including primes, modular arithmetic, Diophantine equations, and cryptographic applications set-theorySet theory including ZFC axioms, ordinals, cardinals, axiom of choice, and forcing shortest-path-algorithmsDijkstra, Bellman-Ford, Floyd-Warshall, and A* algorithms for finding shortest paths in weighted graphs with various constraints topology-algebraicAlgebraic topology including fundamental groups, homology, homotopy theory, and computational topology topology-point-setPoint-set topology, metric spaces, open/closed sets, continuity, compactness, separation axioms

distributed-systems

debugging

debugging-browser-devtoolsComprehensive guide to browser developer tools for debugging web applications. Covers Chrome/Firefox/Safari DevTools including Sources panel, breakpoints, performance profiling, memory analysis, network debugging, Console API, React/Vue debugging, and Lighthouse/Core Web Vitals.debugging-concurrency-debuggingRace condition detection, deadlock debugging, and data race analysis using ThreadSanitizer and specialized tools debugging-container-debuggingDebugging applications inside containers using docker exec, kubectl debug, ephemeral containers, and distroless debugging techniques debugging-core-dump-analysisCore dump generation, GDB/LLDB analysis, crash reporting, and post-mortem debugging across platforms debugging-crash-debuggingSignal handling, crash reproduction, fuzzing for crash discovery, telemetry aggregation, and post-mortem workflows debugging-distributed-systems-debuggingDebugging distributed systems with trace correlation, cross-service workflows, request replay, clock skew handling, and chaos engineering debugging-gdb-fundamentalsComprehensive guide to GNU Debugger (GDB) for debugging C/C++/Rust programs. Covers breakpoints, stack traces, variable inspection, TUI mode, .gdbinit customization, Python scripting, remote debugging, and core file analysis.debugging-lldb-macos-debuggingComprehensive guide to LLDB debugger for macOS/iOS development. Covers LLDB vs GDB differences, Swift/Objective-C debugging, Xcode integration, command-line usage, breakpoint expressions, watchpoints, Python scripting, and performance improvements (50x faster step-over in 2025).debugging-memory-leak-debuggingComprehensive memory leak detection and debugging using heap profiling tools across multiple languages debugging-network-debuggingNetwork debugging with tcpdump, Wireshark, curl, DNS tools, SSL/TLS inspection, and network tracing utilities debugging-performance-profilingPerformance profiling with CPU profilers (perf, pprof, py-spy), flame graphs, memory profiling (heaptrack, Valgrind), and profile-guided optimization debugging-production-debuggingNon-intrusive debugging in production environments with feature flags, dynamic logging, and observability correlation debugging-python-debuggingComprehensive guide to Python debugging tools and techniques. Covers pdb (built-in debugger), ipdb (IPython integration), VSCode debugger, PyCharm debugger, pytest debugging, remote debugging with debugpy, and performance profiling with cProfile.debugging-remote-debuggingComprehensive guide to remote debugging techniques for production and development environments. Covers SSH port forwarding, VSCode Remote Development, JetBrains Gateway, container debugging (Docker), Kubernetes debugging, production-safe debugging, debug symbols, and source maps.

cloud

cloud-aws-api-gatewayAWS API Gateway REST APIs, HTTP APIs, WebSocket APIs, authorization, and integration patterns cloud-aws-databasesAWS database services - RDS, DynamoDB, ElastiCache, Aurora, migration, backup, and optimization cloud-aws-ec2-computeAWS EC2 instances, Auto Scaling, Load Balancing, AMIs, and instance lifecycle management cloud-aws-iam-securityAWS IAM policies, roles, Cognito authentication, Secrets Manager, KMS encryption, and security best practices cloud-aws-lambda-functionsAWS Lambda function development, runtime configuration, triggers, and optimization cloud-aws-networkingAWS networking - VPC, subnets, security groups, NACLs, Route53, CloudFront, Transit Gateway cloud-aws-storageAWS storage services - S3, EBS, EFS, Glacier, lifecycle policies, encryption, and data transfer cloud-gcp-computeGoogle Cloud compute services including Compute Engine, Cloud Run, and GKE cloud-gcp-databasesGoogle Cloud managed database services including Cloud SQL, Firestore, Bigtable, and Spanner cloud-gcp-iam-securityGoogle Cloud IAM, service accounts, Secret Manager, and Cloud KMS security practices cloud-gcp-networkingGoogle Cloud networking including VPC, firewall, DNS, CDN, and load balancing cloud-gcp-serverlessGoogle Cloud serverless services including Cloud Functions, Cloud Run, and App Engine cloud-gcp-storageGoogle Cloud storage services including Cloud Storage, Persistent Disk, and Filestore

elegant-design

anti-patterns❌ Building custom components when design systems have them - Always check shadcn/ui, daisyUI, HeroUI first - Don't reinvent the wheel chat-and-messagingChat is a conversation, not a document.colors-and-spacingCreate semantic color tokens, not just raw colors.components-and-accessibilityBuild from small to large: - Atoms: Buttons, inputs, labels - Molecules: Search bar (input + button), form field (label + input + error) - Organisms: Header, card, form - Templates: Page layouts - Pages: Specific instances design-systemsWhen to use: Most projects, especially with Tailwind CSS diffs-and-logsVersion control UIs and log viewers need clarity and scannability.layout-patternsStandard for complex layouts:performanceFast interfaces feel better.streaming-and-loadingContent that appears instantly feels fast.terminals-and-codeTerminals and code blocks need to be readable, beautiful, and functional.testing-and-qa- Mobile (320px, 375px, 414px widths) - Tablet (768px, 1024px widths) - Desktop (1280px, 1920px widths) - Both light and dark modes - Different font sizes (browser zoom 100%, 125%, 150%) - Slow 3G network simulation tools-and-librariesPrototyping: - Figma (https://figma.com) - Sketch (https://sketch.com) - Adobe XD typographyElegant, modern typography sets the foundation for professional interfaces.

marketing-plan

aarrr-frameworkAARRR (Dave McClure's "pirate metrics") is the spine of every plan produced by this skill.budget-planningThe problem with most SaaS marketing budgets is that they're pulled out of thin air — a number that hopefully doesn't constrain growth too much, but doesn't anchor in customer-acquisition economics either.client-typesThe 13-section plan structure stays consistent across client types.current-state-rubricThis 17-section rubric is the source of truth for Section 3 ("Current State") of every marketing plan.example-quietudeThis is the canonical reference example for the /marketing-plan skill.funding-stage-unlocksEvery marketing plan must include explicit "what changes when funding closes / when budget unlocks" reasoning.growth-patternsThe 12-month outlook in every plan (Section 10) describes a trajectory.idea-cross-referenceThe marketing-ideas skill catalogs 139 proven marketing tactics.measurement-frameworkEvery plan needs a measurement section that tells the team how to know if the plan is working.methodologyThe three-phase workflow that produces a comprehensive marketing plan.ops-stack-mappingThis doc maps every marketing-skill and every relevant MCP/API integration to the AARRR stage(s) it primarily serves.plan-templateThe canonical template for every marketing plan generated by this skill.team-and-agency-modelThe marketing operations stack (Section 11 of every plan) describes what gets done.

plt

curry-howardCurry-Howard correspondence relating proofs and programs, propositions and types dependent-typesDependent types including Π-types, Σ-types, indexed families, and proof assistants hazelnut-calculusHazelnut structure editor calculus - bidirectionally typed lambda calculus with holes and cursor, edit actions preserving static meaning, zipper structures lambda-calculusLambda calculus including untyped, simply typed, Church encodings, and reduction strategies live-programming-holesLive programming with typed holes - Hazel environment, continuous feedback, live evaluation with indeterminate results, incremental bidirectional typing (OOPSLA 2025), collaborative editing (Grove)operational-semanticsOperational semantics including small-step, big-step, evaluation strategies, and reduction systems program-verificationProgram verification including Hoare logic, SMT-based verification, refinement types, and proof-carrying code structure-editorsStructure editor design patterns - projectional editing, syntax-directed editing, edit actions, cursor management, rendering, text workflow integration type-systemsType systems including type checking, inference, polymorphism, subtyping, and soundness typed-holes-foundationsTyped holes fundamentals - incomplete programs with static/dynamic meaning, connection to gradual typing, bidirectional type checking, and theoretical foundations typed-holes-interactionIDE integration with typed holes - goal-directed programming, hole refinement, case splitting, proof search, tactics, elaborator reflection (Agda, Idris, Lean models)typed-holes-llmLLM integration with typed holes (OOPSLA 2024) - static context for code synthesis, type-driven prompting, validation, ranking, combining language servers with LLMs typed-holes-semanticsAdvanced typed holes semantics - hole closures, pattern matching with holes, type error localization, polymorphism, gradual guarantees, blame tracking

database

apache-icebergBuilding data lakes with ACID transaction support and schema evolution database-database-connection-poolingConfiguring database connections for applications database-database-selectionStarting new projects and choosing database technology database-elasticsearch-searchFull-text search and relevance optimization with Elasticsearch database-mongodb-document-designDesigning MongoDB schemas database-orm-patternsWorking with ORMs (SQLAlchemy, Prisma, GORM, Diesel)database-postgres-migrationsCreating database migrations for schema changes database-postgres-query-optimizationDebugging slow queries in PostgreSQL database-postgres-schema-designDesigning new database schemas database-redis-data-structuresImplementing caching layers duckdb-analyticsSkill: duckdb-analytics Category: Data/Analytics Related: Python, SQL, Parquet, data pipelines redpanda-streaming**Redpanda deployments**: Setting up Kafka-compatible streaming infrastructure

cryptography

07_emergency_rotation_runbookPurpose: Emergency rotation procedure for compromised secrets SLA: Complete rotation within 1 hour of detection Scope: All production secrets (databases, API keys, certificates, tokens)cryptography-certificate-managementCertificate lifecycle management including rotation, renewal, monitoring, automation with Let's Encrypt and ACME cryptography-crypto-best-practicesCryptography best practices, common mistakes, security patterns, and anti-patterns to avoid cryptography-cryptography-basicsCryptography fundamentals including symmetric/asymmetric encryption, hashing, signing, key exchange, and common algorithms cryptography-encryption-at-restProtecting stored data with encryption at rest cryptography-key-managementComprehensive cryptographic key lifecycle management, KMS integration, and compliance cryptography-pki-fundamentalsPKI fundamentals including certificate authorities, chains of trust, X.509 certificates, and certificate lifecycle cryptography-signing-verificationDigital signature creation, verification, and chain of trust for documents, code, and artifacts cryptography-sni-routingServer Name Indication (SNI) for multi-domain TLS hosting, routing, and configuration patterns cryptography-ssl-legacyLegacy SSL/TLS protocols (SSL 2.0/3.0, TLS 1.0/1.1), vulnerabilities, deprecation, and migration strategies cryptography-tls-configurationTLS/SSL configuration including TLS 1.2/1.3 setup, cipher suites, security best practices, and server configuration

formal

formal-backtracking-searchImplementing CSP solvers with systematic search formal-constraint-propagationPruning search space before backtracking search formal-csp-modelingModeling scheduling problems (meetings, courses, jobs)formal-lean-mathlib4Formalizing mathematics using existing results formal-lean-proof-basicsLearning Lean 4 from scratch formal-lean-tacticsOptimizing proof efficiency formal-lean-theorem-provingFormalizing complex mathematics formal-sat-solving-strategiesOut of Scope: - SMT theories (see z3-solver-basics.md) - Theorem proving (see lean-theorem-proving.md) - Constraint programming (see csp-modeling.md) - Solver implementation (focus on usage)formal-smt-theory-applicationsOut of Scope: - Pure SAT solving (see sat-solving-strategies.md) - Z3 API basics (see z3-solver-basics.md) - Interactive theorem proving (see lean-theorem-proving.md) - Constraint programming (see csp-modeling.md)formal-z3-solver-basicsOut of Scope: - Low-level C++ API (use Python bindings) - Custom theory development - Advanced proof engineering (see lean-theorem-proving.md) - SAT-only solving (see sat-solving-strategies.md)

frontend

frontend-browser-concurrencyService Workers, SharedWorkers, Worklets, and multi-threading patterns for advanced browser concurrency frontend-frontend-performanceOptimizing application performance frontend-nextjs-app-routerBuilding Next.js 13+ applications frontend-nextjs-seoImplementing SEO for Next.js applications frontend-react-component-patternsDesigning component architecture frontend-react-data-fetchingScope: SWR, React Query, Server Actions, caching strategies, optimistic updates Lines: ~310 Last Updated: 2025-10-18 frontend-react-form-handlingScope: React Hook Form, Zod validation, Server Actions, multi-step forms, form patterns Lines: ~290 Last Updated: 2025-10-18 frontend-react-state-managementChoosing state management solution frontend-web-accessibilityBuilding accessible web applications frontend-web-workersOffloading computation with Web Workers API, SharedArrayBuffer, and message passing patterns

mobile

ios-networkingBuilding network layers for iOS/macOS apps ios-testingWriting unit tests for iOS/macOS apps mobile-react-native-native-modulesAccessing iOS-specific APIs not available in React Native mobile-react-native-navigationImplementing multi-screen navigation in React Native apps mobile-react-native-performanceApp animations are dropping frames (not 60fps)mobile-react-native-setupStarting a new React Native project for iOS development swift-concurrencyWorking with async/await in Swift swiftdata-persistenceBuilding iOS/macOS apps with local persistence swiftui-architectureBuilding iOS/macOS apps with SwiftUI swiftui-navigationImplementing navigation in iOS 17+ apps

theme-factory

arctic-frostA cool and crisp winter-inspired theme that conveys clarity, precision, and professionalism.botanical-gardenA fresh and organic theme featuring vibrant garden-inspired colors for lively presentations.desert-roseA soft and sophisticated theme with dusty, muted tones perfect for elegant presentations.forest-canopyA natural and grounded theme featuring earth tones inspired by dense forest environments.golden-hourA rich and warm autumnal palette that creates an inviting and sophisticated atmosphere.midnight-galaxyA dramatic and cosmic theme with deep purples and mystical tones for impactful presentations.modern-minimalistA clean and contemporary theme with a sophisticated grayscale palette for maximum versatility.ocean-depthsA professional and calming maritime theme that evokes the serenity of deep ocean waters.sunset-boulevardA warm and vibrant theme inspired by golden hour sunsets, perfect for energetic and creative presentations.tech-innovationA bold and modern theme with high-contrast colors perfect for cutting-edge technology presentations.

data

data-batch-processingOrchestrating complex data pipelines with dependencies data-data-validationValidating data schema before processing data-dataflow-coordinationCoordination patterns for distributed dataflow systems including barriers, epochs, and distributed snapshots data-differential-dataflowDifferential computation for incremental updates, maintaining indexed collections and efficient joins data-etl-patternsDesigning data extraction from multiple sources (databases, APIs, files)data-pipeline-orchestrationCoordinating complex multi-step data workflows data-stream-processingProcessing real-time event streams (clicks, IoT, logs)data-streaming-aggregationsWindowing, sessionization, time-series aggregation, and late data handling for streaming systems data-timely-dataflowTimely dataflow framework for low-latency, high-throughput streaming computation with progress tracking

observability

observability-alerting-strategySetting up production monitoring and on-call rotation observability-cost-optimizationOptimizing observability costs through sampling, cardinality management, and retention strategies observability-dashboard-designBuilding Grafana dashboards for service monitoring observability-distributed-tracingDebugging latency issues in microservices observability-metrics-instrumentationInstrumenting applications for observability observability-opentelemetry-integrationIntegrating OpenTelemetry for unified observability (traces, metrics, logs)observability-production-incident-debuggingDebugging production incidents using observability data (logs, metrics, traces)observability-prometheus-monitoringProduction-ready Prometheus monitoring and alerting observability-structured-loggingSetting up application logging infrastructure

api

api-api-authenticationImplementing API authentication for new services api-api-authorizationImplementing authorization logic in APIs api-api-error-handlingDesigning error responses for REST APIs api-api-rate-limitingImplementing rate limiting for APIs api-api-versioningPlanning API changes and deciding on versioning approach api-graphql-schema-designDesigning GraphQL APIs from scratch api-rest-api-designDesigning RESTful APIs from scratch referenceComprehensive technical reference for JWT, OAuth 2.0, and API authentication specifications.

build-systems

build-systems-bazel-monoreposBazel BUILD files, WORKSPACE/MODULE.bazel, hermetic builds, remote caching, build rules, Starlark custom rules, and monorepo best practices for polyglot projects.build-systems-build-optimizationIncremental builds, dependency tracking, build caching (ccache, sccache, Bazel), parallel builds, build time profiling, and CI/CD optimization strategies.build-systems-build-system-selectionDecision matrix for choosing between Make, CMake, Gradle, Maven, Bazel, and other build systems based on project requirements, language, and scale.build-systems-cmake-patternsModern CMake target-based approach, find_package, FetchContent, generator expressions, cross-platform configuration, and installation rules for C/C++ projects.build-systems-cross-platform-buildsPlatform detection, conditional compilation, preprocessor macros, CMake cross-compilation, Zig cross-compilation, toolchain configuration, and multi-platform testing strategies.build-systems-gradle-jvm-buildsGradle Kotlin DSL and Groovy DSL, dependency management, version catalogs, build lifecycle, task configuration, multi-project builds, and performance optimization for Java/Kotlin projects.build-systems-make-fundamentalsMakefile syntax, targets, dependencies, pattern rules, and best practices for building C/C++ and multi-language projects with Make.build-systems-maven-configurationMaven POM structure, dependency management, plugin configuration, lifecycle phases, multi-module projects, profiles, and repository management for Java projects.

diagrams

mermaid-architecture-diagramsCreate C4 and block architecture diagrams with Mermaid for system design and infrastructure visualization mermaid-chartsCreate data visualization charts with Mermaid including pie, XY, quadrant, and radar charts for metrics and analytics mermaid-class-state-diagramsCreate UML class diagrams and state machines with Mermaid for object-oriented design and state modeling mermaid-er-diagramsCreate entity-relationship diagrams with Mermaid for database schema design and data modeling mermaid-flowchartsCreate process flow diagrams with Mermaid using nodes, arrows, decisions, and subgraphs for visual documentation mermaid-project-diagramsCreate Gantt charts and timeline diagrams with Mermaid for project planning and chronological visualization mermaid-sequence-diagramsCreate interaction and message flow diagrams with Mermaid showing communication between actors, services, and components over time mermaid-specializedCreate specialized diagrams with Mermaid including Git graphs, Sankey flows, mindmaps, and other advanced visualization types

modal

modal-functions-basicsBuilding serverless functions on Modal.com modal-gpu-workloadsRunning ML/AI inference on Modal modal-image-buildingConfiguring Modal runtime environments modal-modal-common-errorsEncountering Modal deployment or runtime errors modal-modal-performance-debuggingModal functions running slower than expected modal-schedulingRunning periodic tasks on Modal modal-volumes-secretsPersisting data across function invocations modal-web-endpointsCreating HTTP APIs on Modal

protocols

migration_guideComprehensive guide for migrating Protocol Buffer schemas safely while maintaining backward/forward compatibility.protocols-amqp-rabbitmqRabbitMQ and AMQP 0-9-1 message broker implementation protocols-grpc-implementationImplementing gRPC APIs with Protocol Buffers protocols-http2-multiplexingHTTP/2 protocol with multiplexing, server push, header compression, and stream prioritization protocols-kafka-streamsApache Kafka stream processing and event streaming platform protocols-mqtt-messagingMQTT pub-sub messaging for IoT and real-time applications protocols-protobuf-schemasProtocol Buffers schema design, evolution, and code generation protocols-websocket-protocolsWebSocket protocol implementation, scaling, and production deployment

caching

caching-cache-invalidation-strategiesCache invalidation patterns and techniques - time-based, event-based, key-based, and version-based invalidation for maintaining cache consistency.caching-cache-performance-monitoringMeasuring and optimizing cache performance - metrics, monitoring tools, alerts, load testing, and instrumentation for cache hit rates and latency.caching-caching-fundamentalsCore caching concepts, patterns, eviction policies, and cache design principles for optimizing application performance caching-cdn-edge-cachingCDN and edge cache optimization with Cloudflare, Fastly, and CloudFront for global performance and reduced origin load caching-http-cachingBrowser and HTTP cache layer optimization using cache headers, conditional requests, and validation strategies caching-redis-caching-patternsApplication-level caching with Redis - patterns, distributed caching, cache stampede prevention, and integration strategies for high-performance applications.caching-service-worker-cachingProgressive Web App (PWA) caching with Service Workers - offline-first architecture, caching strategies, Workbox patterns, and modern browser caching.

proxies

proxies-cache-controlHTTP caching strategies including cache headers, CDN patterns, cache invalidation, stale-while-revalidate, and edge caching optimization proxies-envoy-proxyEnvoy proxy architecture including filters, clusters, listeners, service mesh patterns, observability, and advanced load balancing proxies-forward-proxyForward proxy fundamentals including HTTP CONNECT, SOCKS protocols, authentication, and use cases for privacy, security, and access control proxies-nats-messagingNATS messaging patterns including pub/sub, request-reply, queue groups, JetStream persistence, clustering, and high-performance messaging proxies-nginx-configurationNginx configuration including server blocks, locations, upstreams, caching, SSL/TLS, security headers, and performance optimization proxies-reverse-proxyReverse proxy patterns including load balancing, SSL termination, request routing, health checks, and high availability configurations proxies-traefik-configurationTraefik configuration including dynamic service discovery, middleware chains, automatic Let's Encrypt, Docker/Kubernetes integration, and cloud-native routing

research

research-data-analysisMaster data analysis techniques including coding, statistical tests, visualization, interpretation, and reporting findings research-data-collectionMaster data collection methods including survey design, interview protocols, observation techniques, and measurement instruments research-qualitative-methodsMaster qualitative research methods including interviews, ethnography, case studies, grounded theory, and thematic analysis research-quantitative-methodsMaster quantitative research methods including statistical analysis, surveys, experiments, and hypothesis testing research-research-designMaster research study design including hypothesis formation, validity, sampling strategies, and experimental control research-research-writingMaster academic and research writing including structure, citations, reporting standards, and peer review processes research-synthesisMaster information synthesis, literature review, meta-analysis, and knowledge integration across sources

security

security-authenticationAuthentication patterns including JWT, OAuth2, sessions, and multi-factor authentication for secure user identity verification security-authorizationAuthorization models including RBAC, ABAC, policy engines, and access control patterns for securing resources security-input-validationInput validation and sanitization patterns to prevent SQL injection, XSS, command injection, and other input-based attacks security-oauth2-implementationOAuth 2.0 implementation including authorization code, client credentials, PKCE, refresh tokens, and security best practices security-secrets-managementSecrets management patterns including vaults, environment variables, key rotation, and secure credential handling for applications security-security-headersHTTP security headers including CSP, HSTS, X-Frame-Options, CORS, and other protective headers for web application security security-vulnerability-assessmentSecurity testing methodologies, OWASP Top 10, vulnerability scanning tools, and penetration testing practices

collaboration

codetour-guided-walkthroughsCreating and following CodeTour walkthroughs for codebase understanding collaboration-github-actions-workflowsSetting up CI/CD pipelines with GitHub Actions collaboration-github-issues-projectsIssue management, templates, labels, milestones, GitHub Projects, and issue linking workflows collaboration-github-pull-requestsPull request workflow, code review, merge strategies, PR checks, and collaboration best practices collaboration-github-repository-managementRepository creation, configuration, branch protection, tags, releases, and GitHub CLI operations collaboration-github-security-featuresDependabot, code scanning, secret scanning, SBOM generation, security advisories, and security best practices

containers

comparisonThis directory contains examples showing the impact of Docker optimization techniques.containers-container-networkingConfiguring container network connectivity containers-container-registry-managementChoosing a container registry (ECR/GCR/Harbor/Docker Hub)containers-container-securityHardening container images for production containers-docker-compose-developmentSetting up local development environments containers-dockerfile-optimizationWriting Dockerfiles for production applications

deployment

deployment-heroku-addonsAdding databases (Postgres, MySQL, MongoDB) to Heroku apps deployment-heroku-deploymentDeploying web applications, APIs, or worker processes to Heroku deployment-heroku-troubleshootingApplication crashes on Heroku with H10, H12, H13, H14 errors deployment-netlify-deploymentDeploying static sites, JAMstack apps, or frontend frameworks to Netlify deployment-netlify-functionsBuilding API endpoints for JAMstack applications deployment-netlify-optimizationImproving site load times and Core Web Vitals

infrastructure

infrastructure-aws-serverlessBuilding serverless APIs and backends infrastructure-cloudflare-workersBuilding serverless APIs at the edge (low latency globally)infrastructure-cost-optimizationCloud costs are growing unexpectedly infrastructure-infrastructure-securitySetting up IAM roles and policies infrastructure-kubernetes-basicsDeploying containerized applications at scale infrastructure-terraform-patternsProvisioning cloud infrastructure (AWS, GCP, Azure, Cloudflare)

offers

bonus-stackingHow to add bonuses that raise perceived value without devaluing the core offer.guarantee-designA guarantee directly raises perceived likelihood of achievement (the buyer thinks: "they'll only offer this if they're confident") and lowers effort & sacrifice (less emotional risk).offer-anatomyA complete offer has six components.offer-formatsThe right offer format depends on what you sell.scarcity-urgencyThe reason to buy now, not later.value-equationThe single most useful frame for offer design.

social

listeningHow to surface the right posts to engage with each day — instead of randomly scrolling.listening-sources-templateCopy this file to .agents/listening-sources.md in your project (or .claude/listening-sources.md) and fill in the brackets.platform-limitsQuick reference for hashtag limits, character counts, and visible text thresholds on each major social platform.post-templatesReady-to-use templates for different platforms and content types.reverse-engineeringInstead of guessing what works, systematically analyze top-performing content in your niche and extract proven patterns.short-form-videoDetailed reference for creating short-form video content on TikTok, Instagram Reels, and YouTube Shorts.

testing

testing-e2e-testingTest complete user workflows from UI to backend testing-integration-testingTest interactions between multiple components or services testing-performance-testingMeasure system performance under load (response time, throughput)testing-test-coverage-strategyDetermine what code needs testing vs what to skip testing-test-driven-developmentDesign APIs and interfaces through tests testing-unit-testing-patternsWrite isolated tests for individual functions, classes, or modules

ui-port

acceptanceChoose states appropriate to the app.exchange-exampleThis example captures a common failure mode: the shell is close, but the new system still reads as a different product because screen topology, typography, control geometry and information hierarchy diverge.ledgerUse one row per independently actionable issue.modesUse browser capture, DOM/style probes, source inspection, and automatic target edits.probe-contractUse this when live DOM access is available.screen-convergenceCreate one section per route and state.

zig

zig-build-systemUse this skill when: - Configuring build.zig - Adding dependencies - Cross-compiling projects - Creating build steps - Managing build options zig-c-interopCalling C libraries from Zig zig-memory-managementUse this skill when: - Managing memory in Zig - Using allocators correctly - Implementing defer/errdefer - Avoiding memory leaks - Understanding Zig's explicit allocation zig-package-managementAdding dependencies to Zig projects zig-project-setupInitializing new Zig projects zig-testingWriting unit tests in Zig

aso

apple-specsAll data from developer.apple.com as of March 2026.benchmarksIndustry data from AppTweak, SplitMetrics, Sensor Tower, and others.google-play-specsAll data from support.google.com and developer.android.com as of March 2026.report-templateUse this structure for all ASO audit reports.scoring-criteriaScore each dimension 0-10 using the rubrics below.

ir-query-understandingQuery expansion, spell correction, semantic search, query classification, entity recognition, and autocomplete ir-ranking-rerankingLearning to rank, cross-encoder reranking, ranking features, and evaluation metrics (nDCG, MAP, MRR)ir-recommendation-systemsCollaborative filtering, content-based filtering, hybrid recommenders, matrix factorization, and cold start solutions ir-search-fundamentalsCore information retrieval concepts including TF-IDF, BM25, inverted indexes, and Elasticsearch ir-vector-searchDense retrieval using embeddings, vector databases, approximate nearest neighbors, and hybrid search

networking

mosh-resilient-sshConnecting over unreliable networks (mobile, WiFi)mtls-implementationImplementing mutual TLS authentication nat-traversalBuilding peer-to-peer applications network-resilience-patternsBuilding robust network applications tailscale-vpnCreating secure private networks (mesh VPN)

prospecting

b2b-prospectingFor when the user sells to non-SaaS B2B — services, agencies, manufacturers, mid-market and enterprise companies, professional services firms.complianceThe legal and platform-ToS constraints that apply to prospect list building.data-sourcesTool selection guide for prospecting across all three branches.local-prospectingFor when the user sells to local small businesses — shops, gyms, restaurants, salons, clinics, professional services, contractors, real estate, fitness studios, dental practices.saas-prospectingFor when the user sells SaaS or digital services to other SaaS companies / digital businesses.

tui

bubbletea-architectureBuilding terminal UIs in Go bubbletea-componentsBuilding UIs with pre-made components ratatui-architectureBuilding terminal UIs in Rust ratatui-widgetsUsing Ratatui's built-in widgets tui-best-practicesDesigning terminal user interfaces

workflow

beads-context-strategiesUse this skill when: Managing Claude Code context while working with Beads, preventing context bloat, or preserving critical workflow state across sessions beads-dependency-managementUse this skill when: Creating relationships between issues, managing blockers, or organizing work hierarchies beads-multi-session-patternsUse this skill when: Working on complex tasks spanning multiple sessions, managing long-horizon work chains, or coordinating parallel work streams beads-workflowUse this skill when: Starting a new session with Beads, running bd commands, or managing issue workflow state workflow-project-synthesisSynthesize scattered project artifacts (plans, docs, tests, logs) into unified roadmap. Use when projects have accumulated sprawl across multiple planning documents, inconsistent naming, orphaned tests, or Beads issues out of sync with reality. Creates coherent execution plan while preserving research and maintaining referential integrity.

ads

ad-copy-templatesDetailed formulas and templates for writing high-converting ad copy.audience-targetingDetailed targeting strategies for each major ad platform.conversion-trackingHow to set up conversion tracking pixels across ad platforms.platform-setup-checklistsComplete setup checklists for major ad platforms.

ai-seo

content-patternsReusable content block patterns optimized for answer engines and AI citation.content-typesTactical guidance for optimizing specific content types for AI search citation.okfGoogle's v0.1 markdown spec for representing site content as an agent-readable bundle.platform-ranking-factorsEach AI search platform has its own search index, ranking logic, and content preferences.

anti-slop

claude_md_updatesThis document contains proposed updates to CLAUDE.md to integrate anti-slop awareness and prevention into Claude's core behavior.code-patternsReference guide for detecting AI slop patterns in code including generic variable names, obvious comments, and unnecessary abstractions. Use as reference when reviewing code quality.design-patternsReference guide for detecting AI slop patterns in visual and UX design including generic gradients, cookie-cutter layouts, and buzzword-heavy copy. Use as reference when reviewing design quality.text-patternsReference guide for detecting AI slop patterns in natural language text including overused phrases, buzzwords, and meta-commentary. Use as reference when reviewing text content for quality.

cicd

cicd-cd-deployment-patternsImplementing zero-downtime deployment strategies cicd-ci-optimizationCI pipelines are taking too long (>10 minutes for feedback)cicd-ci-securityManaging secrets and credentials in CI/CD pipelines cicd-ci-testing-strategyDesigning test execution strategies for CI pipelines

cold-email

follow-up-sequences55% of replies come from follow-ups, not the initial email.frameworksFrameworks beat templates — they teach thinking patterns, not copy-paste shortcuts.personalizationPersonalization drives 50–250% more replies (Lavender).subject-linesThe subject line determines whether the email gets read.

ebpf

ebpf-fundamentalseBPF basics including program types, verifier, maps, BCC vs libbpf toolchains, and loading programs ebpf-networkingFast packet processing with XDP, TC filtering, socket programs, load balancing, and Cilium networking ebpf-security-monitoringSecurity monitoring with eBPF including syscall tracking, file/network monitoring, Falco, Tetragon, and threat detection ebpf-tracing-observabilityUsing eBPF for tracing with bpftrace, kprobes, uprobes, tracepoints, and performance analysis

internal-comms

3p-updates3Ps can cover a team of any size, ranging all the way up to the entire company.company-newsletterIdeally it includes the following attributes: - Lots of links: pulling documents from Google Drive that are very relevant, linking to prominent Slack messages in announce channels and from executives, perhgaps referencing emails that went c faq-answers- Find questions that are big sources of confusion for lots of employees at the company, generally about things that affect a large portion of the employee base - Attempt to give a nice summarized answer to that question in order to minimiz general-commsBefore proceeding: 1.

mcp-builder

evaluationThis document provides guidance on creating comprehensive evaluations for MCP servers.mcp_best_practicesFollow these standardized naming patterns:node_mcp_serverThis document provides Node/TypeScript-specific best practices and examples for implementing MCP servers using the MCP TypeScript SDK.python_mcp_serverThis document provides Python-specific best practices and examples for implementing MCP servers using the MCP Python SDK.

product

product-prd-requirements-gatheringResearch methods, stakeholder interviews, prioritization frameworks, and requirements synthesis for PRDs product-prd-structure-templatesPRD document structure, templates, and best practices for product requirements documentation product-prd-technical-specificationsAPI specifications, data models, architecture diagrams, and technical constraints for product requirements product-prd-user-stories-acceptanceWriting effective user stories, epics, acceptance criteria, and story mapping for product requirements

public-relations

journalist-pitchingBuilding a media list, scoring journalist fit, and crafting pitches that actually get opened.media-outletsA curated, opinionated list of where to pitch for software/SaaS PR.newsjackingInjecting your POV into a story that's already trending.press-platformsJournalists posting "I need a source for X" — you respond, sometimes you get quoted, sometimes you don't.

realtime

realtime-pubsub-patternsScope: Publish/subscribe architecture, Redis Pub/Sub, message queues, and fan-out patterns Lines: 372 Last Updated: 2025-10-18 realtime-realtime-syncScope: Conflict resolution, CRDTs, operational transformation, and eventual consistency patterns Lines: 398 Last Updated: 2025-10-18 realtime-server-sent-eventsScope: SSE protocol, event streams, automatic reconnection, and fallback strategies Lines: 343 Last Updated: 2025-10-18 realtime-websocket-implementationScope: WebSocket protocol, connection management, reconnection strategies, and heartbeat patterns Lines: 387 Last Updated: 2025-10-18

revops

automation-playbooksPlatform-specific workflow recipes for HubSpot, Salesforce, scheduling tools, and cross-tool automation.lifecycle-definitionsComplete templates for lead lifecycle stages, MQL criteria by business type, SLAs, and rejection/recycling workflows.routing-rulesDecision trees, platform-specific configurations, territory routing, ABM routing, and speed-to-lead benchmarks.scoring-modelsDetailed scoring templates, example models by business type, and calibration guidance.

sales-enablement

deck-frameworksDetailed slide-by-slide guidance for building sales decks that tell a story and close deals.demo-scriptsScene-by-scene templates for different call types, with timing, talk tracks, and interaction guidance.objection-libraryCommon B2B SaaS objections with response frameworks.one-pager-templatesTemplates for different one-pager use cases, with layout guidance and copy prompts.

skill-creator

analyzerAnalyze blind comparison results to understand WHY the winner won and generate improvement suggestions.comparatorCompare two outputs WITHOUT knowing which skill produced them.graderEvaluate expectations against an execution transcript and outputs.schemasThis document defines the JSON schemas used by skill-creator.

typed-holes-refactor

constraint-rulesReference guide for constraint propagation rules in typed holes refactoring including dependency tracking and solution space narrowing. Use as reference when propagating constraints between resolved holes.hole-typesReference taxonomy of refactoring hole types including current state holes, architecture holes, and implementation holes. Use as reference during typed holes refactoring for identifying and categorizing unknowns.typed-holes-examplesComplete worked examples of typed holes refactoring including simple file reorganization and complex API consolidation scenarios with full test suites and constraint validation.validation-patternsReference guide for test patterns to validate hole resolutions including characterization tests, property tests, and integration tests. Use as reference when validating refactoring steps.

wasm

wasm-browser-integrationLoading WebAssembly modules in browsers with JavaScript interop, DOM access, WebGL, and performance optimization wasm-fundamentalsWebAssembly basics including binary format, modules, linear memory, WASI, and core tooling wasm-rust-toolchainRust to WebAssembly compilation using wasm-pack, wasm-bindgen, optimization, and JavaScript interop wasm-server-sideServer-side WebAssembly execution with Wasmtime, WASI support, edge computing, and plugin systems

analytics

event-libraryComprehensive list of events to track by business type and context.ga4-implementationDetailed implementation guide for Google Analytics 4.gtm-implementationDetailed guide for implementing tracking via Google Tag Manager.

code-review

correctness-taxonomyReference for the correctness sub-case — the core of the code-review skill.performance-reviewA specialisation of the parent engine.security-reviewA specialisation of the parent engine.

copy-editing

checklistUse this checklist alongside the Seven Sweeps Framework (see SKILL.md) as a final QA pass before delivering edited copy.content-refreshCopy editing isn't just for new content.plain-english-alternativesReplace complex or pompous words with plain English alternatives.

email-sequence

copy-guidelines1. Hook: First line grabs attention 2.email-typesA comprehensive guide to lifecycle and campaign emails.sequence-templatesDetailed templates for common email sequences.

hanzo-api

hanzo-api-aiHanzo AI — the model API on /v1 (/v1/chat/completions, /v1/messages, /v1/models and the rest of hanzoai/ai's surface) — mounted into a cloud binary with the money, ingest and telemetry callbacks…hanzo-api-kmsSecret custody: your org's secrets sealed at rest, plus threshold signing.hanzo-api-sandboxThe ONE compute primitive: a sandbox is a gVisor pod that runs somebody else's code, and every lifetime is the same object.

site-architecture

mermaid-templatesCopy-paste-ready Mermaid diagrams for visual sitemaps.navigation-patternsDetailed navigation patterns for different site types and contexts.site-type-templatesFull page hierarchy templates with ASCII trees, URL maps, and navigation recommendations for common site types.

zoo-gym

bitdeltaBitDelta enables millions of personalized model variants for individual users WITHOUT LoRA.deltasoupDeltaSoup enables community-driven model improvement through Byzantine-robust aggregation of personalized model deltas.training-free-grpoTraining-Free GRPO (Group Relative Policy Optimization) is Zoo Gym's default RLHF method that eliminates value networks entirely, achieving 40-60% memory reduction and 2× speedup compared to PPO.

1password

cli-examples- op signin - op signin --account <shorthand|signin-address|account-id|user-id>get-started- Works on macOS, Windows, and Linux.

ab-test-setup

sample-size-guideReference for calculating sample sizes and test duration.test-templatesTemplates for planning, documenting, and analyzing experiments.

ad-creative

generative-toolsReference for using AI image generators, video generators, and code-based video tools to produce ad visuals at scale.platform-specsComplete character limits, format requirements, and best practices for each ad platform.

churn-prevention

cancel-flow-patternsDetailed cancel flow patterns by business type, billing provider, and industry.dunning-playbookComplete guide to recovering failed payments and reducing involuntary churn.

competitor-alternatives

content-architectureHow to structure and maintain competitor data for scalable comparison pages.templatesReady-to-use templates for each section of competitor comparison pages.

cro

experimentsComprehensive list of A/B tests and experiments organized by page type.formYou are an expert in form optimization.

directory-submissions

directory-listCanonical list of directories organized by tier.positioning-variationsDirectory audiences respond to different framings.

himalaya

configurationConfiguration file location: ~/.config/himalaya/config.toml message-compositionHimalaya uses MML for composing emails.

pricing

research-methodsThe Van Westendorp survey identifies the acceptable price range for your product.tier-structure2 tiers: Simple, clear choice - Works for: Clear SMB vs.

referral-program

affiliate-programsDetailed guidance for building and managing affiliate programs.program-examplesReal-world examples of successful referral programs.

seo-audit

ai-writing-detectionWords, phrases, and punctuation patterns commonly associated with AI-generated text.international-seoDetailed evidence backing the International SEO & Localization section of the SEO Audit skill.

bot

skills-hubUse the Hanzo Skills Hub CLI to search, install, update, and publish agent skills from the Hanzo skills hub (hub.hanzo.bot, API at api.hanzo.ai/v1/skills). Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed skills-hub CLI.

competitor-profiling

tool-referenceQuick reference for the Firecrawl and DataForSEO MCP tools used in competitor profiling.

content-strategy

headless-cmsReference for choosing, modeling, and implementing a headless CMS for marketing content.

customer-research

source-guidesDetailed, source-by-source playbooks for gathering customer intelligence from online watering holes.

free-tool-strategy

tool-typesDetailed guide to each type of marketing tool you can build.

hanzo-ml-research

core-stackThis reference accompanies the hanzo-ml-research skill.

image

ai-image-promptingHow to write effective prompts for AI image generation models (Gemini/Nano Banana, Flux, Ideogram, DALL-E, Midjourney).

lead-magnets

format-guideDetailed creation guidance for each lead magnet format.

marketing-ideas

ideas-by-categoryComplete list of proven marketing approaches organized by category.

model-usage

codexbar-cli- App: Preferences -> Advanced -> Install CLI - Repo: ./bin/install-codexbar-cli.sh

programmatic-seo

playbooksBeyond mixing and matching data point permutations, these are the proven playbooks for programmatic SEO.

schema

schema-examplesComplete JSON-LD examples for common schema types.

sms

platformsDeep-dive on the major SMS marketing platforms — features, pricing, A2P 10DLC support, and integration paths.

video

ai-video-promptingHow to write effective prompts for AI video generation models (Veo, Runway, Kling, Pika).

Standards: Core AI & Models

Standards: Cloud & Native Infrastructure

Standards: Interfaces & Realtime Protocols

Standards: Security, IAM & Cryptography

Standards: Platform & Applications

The native cloud in a single binary.Go. Rust. C++. Zero interpreter bloat.

The native cloud in a single binary.
Go. Rust. C++. Zero interpreter bloat.