claude-plugins

AI software architecture design — modules, layers, boundaries, design patterns, ADRs, quality attributes, and technical debt strategy for AI-enabled systems. This skill should be used when the user asks to 'design AI system structure', 'define AI module boundaries', 'select AI architecture patterns', 'document AI architecture decisions', 'evaluate AI code architecture', or mentions AI pipelines, feature stores, model serving, drift detection, ML quality attributes, explainability architecture, or AI technical debt. [EXPLICIT]

Comprehensive testing strategy for AI systems — testing scope matrix (6 types x 6 layers), model prediction testing, data quality testing, compliance and fairness testing, integration approaches, and CI/CD test automation. This skill should be used when the user asks to 'define AI testing strategy', 'test ML models', 'design data quality tests', 'plan fairness testing', 'test AI pipelines', 'design integration tests for ML', or mentions adversarial testing, drift simulation, model regression testing, bias testing, explainability testing, or AI test automation. [EXPLICIT]

Analytics pipeline design — dbt-style transformations, data modeling, testing, documentation. Use when the user asks to 'design analytics models', 'set up dbt project', 'plan data transformations', 'define data contracts', 'model star schema', or mentions staging models, marts, incremental strategies, or materializations. [EXPLICIT]

Designs REST and GraphQL API contracts with OpenAPI/Swagger specifications, versioning strategies, pagination patterns, error handling, and rate limiting. [EXPLICIT] Produces production-ready API specifications. [EXPLICIT] Trigger: 'API design', 'REST', 'GraphQL', 'OpenAPI', 'API contract'

Hands-on application security: authn/authz (OAuth/SAML/IAM), RBAC, input validation and sanitization, CORS, HTTP security headers, rate limiting, and security audit/testing (SAST/DAST). [EXPLICIT] Implementation-level, complements security-architecture (strategy). Trigger: 'app security', 'rbac', 'cors', 'rate limit', 'input sanitization', 'security headers', 'xss'.

This skill should be used when the user asks to publish or share Claude Code artifacts, create a visual or interactive session output, decide whether an Artifact is appropriate, validate artifact source and output contracts, handle artifact privacy, produce share links, or choose between workspace artifacts, Claude Code Artifacts, files, and output styles.

Audits AWS AI/GenAI architectures against the Well-Architected GenAI Lens — operational excellence, security, reliability, performance, cost optimization, and sustainability. This skill should be used when the user asks to 'audit AWS AI architecture', 'review Bedrock configuration', 'assess SageMaker security', 'optimize AWS AI costs', 'evaluate AWS GenAI compliance', 'review AWS Well-Architected for AI', or mentions AWS AI audit, Bedrock audit, SageMaker review, AWS GenAI security assessment, or AWS AI cost optimization review. [EXPLICIT]

Designs AWS cloud architectures for AI and GenAI workloads applying the Well-Architected Framework GenAI Lens (6 pillars: GENOPS, GENSEC, GENREL, GENPERF, GENCOST, GENSUS), AWS service selection matrices, RAG/Agent/Fine-Tuning patterns, cost optimization strategies, and enterprise reference architectures. Activated when designing, evaluating, or migrating AI systems on AWS. [EXPLICIT]

Guides implementation of AI/GenAI architectures on AWS — Bedrock setup, SageMaker pipelines, OpenSearch vector stores, API Gateway configuration, security hardening, cost controls, and deployment automation. This skill should be used when the user asks to 'implement AI on AWS', 'set up Bedrock', 'deploy SageMaker pipeline', 'configure OpenSearch for RAG', 'implement AWS AI security', 'set up AWS AI monitoring', or mentions AWS AI deployment, Bedrock Knowledge Base setup, SageMaker endpoint deployment, AWS GenAI implementation, or AWS AI CI/CD pipeline. [EXPLICIT]

Generate Gherkin BDD scenarios across all quality angles — functional, accessibility, security, performance, SEO, offline, UI, backend, data, DevSecOps, CI/CD. Runner-agnostic step definitions with traceability to requirements and constitutional principles. [EXPLICIT] Trigger: 'BDD', 'Gherkin', 'Given When Then', 'full-spectrum testing', 'acceptance scenarios'

BI solution design — semantic layers, dashboard patterns, self-service analytics, KPI frameworks. Use when the user asks to 'design BI architecture', 'build a KPI framework', 'set up self-service analytics', 'design dashboard hierarchy', 'create a semantic layer', or mentions metric trees, drill-down patterns, or reporting strategy. [EXPLICIT]

Plan and validate bounded, fail-closed experiment loops (ExperimentSpec v2 with explicit cycle limits, guards and a sandbox receipt) via scripts/validate_spec.py and scripts/autoresearch.py. Use when the user asks to run an autoresearch loop, an iterative experiment with a budget, or to validate an experiment spec before executing it. [EXPLICIT]

This skill should be used when the user asks to design, configure, audit, or choose Claude Code channels, MCP channel servers, --channels startup flags, external push events, channel plugins, permission relay, or channel-vs-schedule/hook/headless decisions.

CI/CD and release engineering: pipeline architecture, multi-environment strategy, deployment rollback (blue-green/canary), code-quality gates, dependency governance, git-hook automation. [EXPLICIT] Trigger: 'ci/cd', 'pipeline', 'rollback', 'canary', 'blue-green', 'release', 'quality gate', 'staging'.

This skill should be used when the user asks to implement, audit, or harden application-side handlers for Anthropic-defined Claude API client tools: memory, bash, text editor, or computer use; including sandboxing, path containment, command/action allowlists, session state, idempotency, tool_result construction, and execution evidence. Do not use it for Claude Code permissions, Anthropic server tools, MCP, Claude Code headless CLI, Agent SDK automation, or the generic Messages API tool loop.

Use this skill when the user asks to design, audit, or harden Claude Platform Messages API context budgets, token counting, prompt caching, cache diagnostics, context editing, server-side compaction, context-window overflow policy, or mid-conversation system-message modes around a fixed effort setting. Do not use it for tool dispatch correlation, durable memory systems, generic context-writing advice, executor implementation, or Bash ownership.

This skill should be used when the user asks to design, audit, or harden Claude Platform Files API upload/reference/lifecycle flows or PDF document requests using file_id, URL, or base64 document sources. Use it for file metadata, deletion, conditional downloadability, PDF request limits, MIME-to-content-block contracts, and source/platform compatibility. Do not use it for text-editor operations, fetching web pages, generic object storage, document authoring, or arbitrary binary processing.

Use this skill to design, audit, or validate Claude Platform server-tool plans for server-tools, web search, web fetch, code execution, advisor, tool search, or the mechanical server-side portion of programmatic tool calling. It owns server_tool_use/result correlation, pause_turn continuation, versioned definitions, caller/container rules, domain controls, and source-supported privacy, retention, and cost controls. It does not own the application agent loop; route loop ordering and budgets to claude-api-tool-runtime and katas-deterministic-agent-loop.

This skill should be used when the user asks to build, audit, or harden a Claude Platform Messages API client-side tool execution loop, handle tool_use and tool_result messages, correlate tool_use_id values, stream partial tool JSON, enforce strict:true schemas, handle stop_reason values, or design retry/error behavior for Anthropic Messages API tools. Do not use it for Claude Code headless CLI or Agent SDK automation, prompt-cache design, MCP server design, tool catalog descriptions, or individual tool implementations.

This skill should be used when the user asks to 'create a slash command', 'author a Claude Code command', 'decide command vs skill', 'choose project vs user scope', 'version custom commands for my team', or 'design command frontmatter'. Covers commands/*.md authoring and the command-vs-skill decision; unifies the custom-commands kata with the extension decision tree.