arckit

Document architectural decisions with options analysis and traceability

Assess UK Government AI Playbook compliance for responsible AI deployment

Perform comprehensive governance quality analysis across architecture artifacts (requirements, principles, designs, assessments)

Generate Algorithmic Transparency Recording Standard (ATRS) record for AI/algorithmic tools

Research AWS services and architecture patterns using AWS Knowledge MCP for authoritative guidance

Research Azure services and architecture patterns using Microsoft Learn MCP for authoritative guidance

Generate prioritised product backlog from ArcKit artifacts - convert requirements to user stories, organise into sprints

Assess architecture conformance — ADR decision implementation, cross-decision consistency, design-principles alignment, architecture drift, technical debt, and custom constraint rules

Copy plugin templates to project for customization

Create federated data product contracts for mesh architectures with SLAs, governance, and interoperability guarantees (project)

Create comprehensive data model with entity relationships, GDPR compliance, and data governance

Discover external data sources (APIs, datasets, open data portals) to fulfil project requirements

Create DevOps strategy with CI/CD pipelines, IaC, container orchestration, and developer experience

Generate Yourdon-DeMarco Data Flow Diagrams (DFDs) with structured analysis notation

Generate architecture diagrams using Mermaid or PlantUML C4 for visual documentation

Review Detailed Design (DLD) for implementation readiness

Generate Digital Outcomes and Specialists (DOS) procurement documentation for UK Digital Marketplace

Generate Data Protection Impact Assessment (DPIA) for UK GDPR Article 35 compliance

Create vendor evaluation framework and score vendor proposals

Create FinOps strategy with cloud cost management, optimization, governance, and forecasting

Transform existing project artifacts into a structured, phased framework with overview and executive guide

Analyze G-Cloud service gaps and generate supplier clarification questions

Find G-Cloud services on UK Digital Marketplace with live search and comparison

Research Google Cloud services and architecture patterns using Google Developer Knowledge MCP for authoritative guidance

Generate a consolidated project glossary of terms, acronyms, and definitions from existing artifacts

Search 24,500+ UK government repositories using natural language queries

Map the UK government code landscape for a domain — who built what, common patterns, standards, maturity

Discover reusable UK government code before building from scratch

Scan all projects for stale research, forgotten ADRs, unresolved review conditions, orphaned artifacts, missing traceability, and version drift

Review High-Level Design (HLD) against architecture principles and requirements

Analyse the blast radius of a change to a requirement, decision, or design document

Initialize ArcKit project structure for enterprise architecture governance

Generate a capability maturity model with assessment criteria and level definitions

Create MLOps strategy with model lifecycle, training pipelines, serving, monitoring, and governance

Generate a MOD Secure by Design assessment for UK Ministry of Defence projects using CAAT and continuous assurance

Create operational readiness pack with support model, runbooks, DR/BCP, on-call, and handover documentation

Generate documentation site with governance dashboard, document viewer, and Mermaid diagram support

Create project plan with timeline, phases, gates, and Mermaid diagrams

Create platform strategy using Platform Design Toolkit (8 canvases for multi-sided ecosystems)

Generate MARP presentation slides from existing project artifacts for governance boards and stakeholder briefings

Assess compliance with architecture principles and generate scorecard with evidence, gaps, and recommendations

Create or update enterprise architecture principles

Create comprehensive business and technical requirements

Research technology, services, and products to meet requirements with build vs buy analysis

Create comprehensive risk register following HM Treasury Orange Book principles

Create strategic architecture roadmap with multi-year timeline, capability evolution, and governance

Score vendor proposals against evaluation criteria with persistent structured storage

Search across all project artifacts by keyword, document type, or requirement ID

Generate a Secure by Design assessment for UK Government projects (civilian departments)

Prepare for GDS Service Standard assessment - analyze evidence against 14 points, identify gaps, generate readiness report

Create comprehensive ServiceNow service design with CMDB, SLAs, incident management, and change control

Create Strategic Outline Business Case (SOBC) using UK Government Green Book 5-case model

Generate Statement of Work (SOW) / RFP document for vendor procurement

Analyze stakeholder drivers, goals, and measurable outcomes

Get oriented with ArcKit — guided project onboarding, workflow selection, and command recommendations

Generate comprehensive project story with timeline analysis, traceability, and governance achievements (project)

Synthesise strategic artifacts into executive-level Architecture Strategy document

Generate a Technology Code of Practice (TCoP) review document for a UK Government technology project

Create new document templates by interviewing the user about their organization's requirements

Generate requirements traceability matrix from requirements to design to tests

Export product backlog to Trello - create board, lists, cards with labels and checklists from backlog JSON

Assess climatic patterns affecting Wardley Map components

Assess organizational doctrine maturity using Wardley's 4-phase framework

Analyze strategic play options from Wardley Maps using 60+ gameplay patterns

Create strategic Wardley Maps for architecture decisions and build vs buy analysis

Decompose user needs into value chains for Wardley Mapping

Use this agent when the user needs AWS-specific technology research using the AWS Knowledge MCP server to match project requirements to AWS services, architecture patterns, Well-Architected guidance, and Security Hub controls. Examples: <example> Context: User has a project with requirements and wants AWS service recommendations user: "/arckit:aws-research Research AWS services for microservices platform" assistant: "I'll launch the AWS research agent to match your requirements to AWS services using official AWS documentation via the MCP server. It will check regional availability, map to Well-Architected pillars, and produce cost estimates." <commentary> The AWS research agent makes 15-30+ MCP calls (search_documentation, read_documentation, get_regional_availability, recommend) that accumulate large documentation chunks in context. Running as an agent keeps this isolated. </commentary> </example> <example> Context: User wants to know which AWS services to use for their UK Government project user: "What AWS services should we use for this project?" assistant: "I'll launch the AWS research agent to research AWS services for your project, including UK region availability, G-Cloud status, and NCSC compliance." <commentary> Any request for AWS-specific service recommendations should trigger this agent since it involves heavy MCP documentation retrieval. </commentary> </example> <example> Context: User wants AWS architecture patterns and cost estimates user: "/arckit:aws-research AWS options for UK Government data analytics platform" assistant: "I'll launch the AWS research agent to research data analytics services on AWS, check eu-west-2 availability, verify G-Cloud procurement, and produce cost estimates with Well-Architected assessment." <commentary> UK Government AWS research needs regional availability checks, G-Cloud verification, and NCSC compliance — all requiring multiple MCP calls. </commentary> </example>

Use this agent when the user needs Azure-specific technology research using the Microsoft Learn MCP server to match project requirements to Azure services, architecture patterns, Well-Architected guidance, and Security Benchmark controls. Examples: <example> Context: User has a project with requirements and wants Azure service recommendations user: "/arckit:azure-research Research Azure services for microservices platform" assistant: "I'll launch the Azure research agent to match your requirements to Azure services using official Microsoft documentation via the MCP server. It will check UK region availability, map to Well-Architected pillars, and produce cost estimates." <commentary> The Azure research agent makes 15-30+ MCP calls (microsoft_docs_search, microsoft_docs_fetch, microsoft_code_sample_search) that accumulate large documentation chunks in context. Running as an agent keeps this isolated. </commentary> </example> <example> Context: User wants to know which Azure services to use for their UK Government project user: "What Azure services should we use for this project?" assistant: "I'll launch the Azure research agent to research Azure services for your project, including UK region availability, G-Cloud status, and NCSC compliance." <commentary> Any request for Azure-specific service recommendations should trigger this agent since it involves heavy MCP documentation retrieval. </commentary> </example> <example> Context: User wants Azure architecture patterns and cost estimates user: "/arckit:azure-research Azure options for UK Government data analytics platform" assistant: "I'll launch the Azure research agent to research data analytics services on Azure, check UK South/West availability, verify G-Cloud procurement, and produce cost estimates with Well-Architected assessment." <commentary> UK Government Azure research needs regional availability checks, G-Cloud verification, and NCSC compliance — all requiring multiple MCP calls. </commentary> </example>

Use this agent when the user needs to discover external data sources — APIs, datasets, open data portals, and commercial data providers — to fulfil project requirements. This agent performs extensive web research to find real, current data sources. Examples: <example> Context: User has a project with requirements and wants to find external data sources user: "/arckit:datascout Discover data sources for the fuel price transparency project" assistant: "I'll launch the datascout agent to discover external data sources for the fuel price transparency project. It will search UK Government open data, commercial APIs, and free data sources that match your requirements." <commentary> The datascout agent is ideal here because it needs to perform many WebSearch and WebFetch calls to discover APIs, check documentation, verify rate limits, and assess data quality. Running as an agent keeps this research isolated. </commentary> </example> <example> Context: User wants to find APIs and datasets for their project user: "What external data sources and APIs are available for this project?" assistant: "I'll launch the datascout agent to systematically discover and evaluate external data sources, APIs, and datasets that can fulfil your project's data requirements." <commentary> Any request for external data source discovery should trigger this agent since it involves heavy web research across government portals, API catalogues, and commercial providers. </commentary> </example> <example> Context: User needs UK Government open data for their project user: "Find what government open data we can use for the smart meter app" assistant: "I'll launch the datascout agent to search UK Government open data portals, the API catalogue at api.gov.uk, and data.gov.uk for relevant datasets and APIs." <commentary> UK Government data discovery requires searching multiple portals (api.gov.uk, data.gov.uk, department developer hubs) which benefits from agent isolation. </commentary> </example>

Use this agent when the user wants to transform existing project artifacts into a structured framework with phased organization, an overview document, and an executive guide. This agent reads all project artifacts and synthesises them into a coherent framework structure. Examples: <example> Context: User has multiple artifacts and wants to create a framework user: "/arckit:framework Create framework for the data governance project" assistant: "I'll launch the framework agent to read all project artifacts and create a structured framework with phased organization and executive guide." <commentary> The framework agent reads many artifacts to synthesise the overview, benefiting from agent isolation. </commentary> </example> <example> Context: User wants to organize existing work into a publishable framework user: "Can you turn all our architecture documents into a framework?" assistant: "I'll launch the framework agent to organise your artifacts into a phased framework structure with an overview and executive guide." <commentary> Even without the explicit slash command, the request to create a framework from existing artifacts triggers this agent. </commentary> </example>

Use this agent when the user needs Google Cloud-specific technology research using the Google Developer Knowledge MCP server to match project requirements to Google Cloud services, architecture patterns, Architecture Framework guidance, and Security Command Center controls. Examples: <example> Context: User has a project with requirements and wants Google Cloud service recommendations user: "/arckit:gcp-research Research Google Cloud services for microservices platform" assistant: "I'll launch the Google Cloud research agent to match your requirements to Google Cloud services using official Google documentation via the MCP server. It will check regional availability, map to Architecture Framework pillars, and produce cost estimates." <commentary> The Google Cloud research agent makes 15-30+ MCP calls (search_documents, get_document, batch_get_documents) that accumulate large documentation chunks in context. Running as an agent keeps this isolated. </commentary> </example> <example> Context: User wants to know which Google Cloud services to use for their UK Government project user: "What Google Cloud services should we use for this project?" assistant: "I'll launch the Google Cloud research agent to research Google Cloud services for your project, including europe-west2 region availability, G-Cloud status, and NCSC compliance." <commentary> Any request for Google Cloud-specific service recommendations should trigger this agent since it involves heavy MCP documentation retrieval. </commentary> </example> <example> Context: User wants Google Cloud architecture patterns and cost estimates user: "/arckit:gcp-research Google Cloud options for UK Government data analytics platform" assistant: "I'll launch the Google Cloud research agent to research data analytics services on Google Cloud, check europe-west2 availability, verify G-Cloud procurement, and produce cost estimates with Architecture Framework assessment." <commentary> UK Government Google Cloud research needs regional availability checks, G-Cloud verification, and NCSC compliance — all requiring multiple MCP calls. </commentary> </example>

Use this agent when the user wants to search UK government repositories using natural language queries. This agent provides general-purpose semantic search across 24,500+ government repos via govreposcrape. Examples: <example> Context: User wants to find how government teams implemented something user: "/arckit:gov-code-search How did government teams implement FHIR patient data integration?" assistant: "I'll launch the gov-code-search agent to search 24,500+ UK government repositories for FHIR patient data integration implementations and produce a search report." <commentary> The gov-code-search agent performs multiple query variations and uses WebFetch on top results for detail. Running as an agent keeps the search context isolated. </commentary> </example> <example> Context: User wants to find specific technology usage user: "Who in government uses Redis for session management?" assistant: "I'll launch the gov-code-search agent to search government repositories for Redis session management implementations." <commentary> Technology-specific searches benefit from agent isolation since multiple query variations and result analysis accumulate context. </commentary> </example> <example> Context: User wants pattern research across government user: "/arckit:gov-code-search GOV.UK Design System accessible form components" assistant: "I'll launch the gov-code-search agent to search for accessible form component implementations using the GOV.UK Design System." <commentary> Pattern research across many repos benefits from the agent's ability to compare and synthesize results. </commentary> </example>

Use this agent when the user wants to understand what UK government has built in a domain — mapping organisations, technology patterns, standards, and maturity levels. Examples: <example> Context: User wants to understand the government landscape for a domain user: "/arckit:gov-landscape Map the government landscape for health data integration" assistant: "I'll launch the gov-landscape agent to map what UK government organisations have built for health data integration, including technology patterns, standards adopted, and maturity levels." <commentary> The gov-landscape agent performs extensive searches across the domain, fetches details on many repositories, and synthesizes a landscape view. Running as an agent keeps this heavy analysis isolated. </commentary> </example> <example> Context: User wants to survey government technology usage in a domain user: "What's the government landscape for citizen identity verification?" assistant: "I'll launch the gov-landscape agent to survey government repositories related to identity verification and produce a landscape analysis." <commentary> Domain landscape mapping requires many searches and cross-referencing to identify patterns, standards, and collaboration opportunities. </commentary> </example> <example> Context: User wants to understand government adoption of a technology user: "/arckit:gov-landscape Survey government use of event-driven architecture" assistant: "I'll launch the gov-landscape agent to map government adoption of event-driven architecture patterns across departments." <commentary> Technology adoption surveys need broad searches and synthesis across many repos and orgs. </commentary> </example>

Use this agent when the user wants to discover reusable UK government open-source code before building from scratch. This agent searches 24,500+ government repositories via govreposcrape and assesses candidates for reusability. Examples: <example> Context: User has a project and wants to check for existing government code user: "/arckit:gov-reuse Check for existing government code for appointment booking" assistant: "I'll launch the gov-reuse agent to search 24,500+ UK government repositories for existing appointment booking implementations and assess their reusability." <commentary> The gov-reuse agent is ideal here because it performs multiple govreposcrape searches per capability, then uses WebFetch on each candidate's GitHub page to assess reusability. Running as an agent keeps this research isolated. </commentary> </example> <example> Context: User wants to avoid rebuilding what government already has user: "Has anyone in government already built a case management system we could reuse?" assistant: "I'll launch the gov-reuse agent to search government repositories for case management implementations and assess which ones could be forked, used as a library, or referenced." <commentary> Any request to find existing government code for reuse should trigger this agent since it involves searching and deep assessment of multiple repositories. </commentary> </example> <example> Context: User wants reuse assessment after creating requirements user: "Before we start building, check what the government has already built for this" assistant: "I'll launch the gov-reuse agent to systematically search government repositories for each capability in your requirements and produce a reuse assessment." <commentary> Pre-build reuse check requires reading requirements, extracting capabilities, and searching for each — benefits from agent isolation. </commentary> </example>

Use this agent when the user needs technology and service market research for a project, including build vs buy analysis, vendor evaluation, TCO comparison, and UK Government Digital Marketplace search. This agent performs extensive web research autonomously. Examples: <example> Context: User has a project with requirements and wants to research available technology solutions user: "/arckit:research Research technology options for the NHS appointment booking project" assistant: "I'll launch the research agent to conduct market research for the NHS appointment booking project. It will search for vendors, open source options, UK Government platforms, and produce a build vs buy analysis with TCO comparison." <commentary> The research agent is ideal here because it needs to perform dozens of WebSearch and WebFetch calls to gather vendor pricing, reviews, and product details. Running as an agent keeps this context-heavy work isolated. </commentary> </example> <example> Context: User wants to explore technology options after creating requirements user: "Can you research what platforms and services we could use for this project?" assistant: "I'll launch the research agent to discover and evaluate technology options based on your project requirements." <commentary> Even without the explicit slash command, the request for technology/service research should trigger this agent since it involves heavy web research. </commentary> </example> <example> Context: User wants build vs buy analysis user: "Should we build or buy for authentication and payment processing?" assistant: "I'll launch the research agent to perform a detailed build vs buy analysis for authentication and payment processing, including vendor comparison and TCO estimates." <commentary> Build vs buy analysis requires extensive vendor research with pricing, which benefits from agent isolation. </commentary> </example>

This skill should be used when the user asks how to start an architecture project, which ArcKit commands to run and in what order, what workflow to follow, getting started, new project setup, guide me through, or what comes next.

This skill should be used when the user asks about Mermaid diagram syntax, how to write flowchart, sequence, class, state, ER, Gantt, C4, mindmap, timeline, or other diagram types, node shapes, styling, theming, or rendering errors.

This skill should be used when the user asks about PlantUML syntax for C4-PlantUML, sequence, class, activity, state, ER, component, deployment, or use case diagrams, rendering errors, layout conflicts, skinparams, or themes.

This skill should be used when the user asks about Wardley Mapping, evolution stages, strategic positioning, creating maps, value chain decomposition, gameplay patterns, doctrine assessment, climatic patterns, build vs. buy, or inertia analysis.

18 hooks across 7 events