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

> Reference for splitting a research-heavy ArcKit agent into three tiers

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>

Writer subagent invoked by the /arckit:competitors orchestrator command. Renders a validated, orchestrator-prepared payload into a CMPT Competitor Landscape artefact under projects/{P}-{NAME}/research/, and spawns/enriches per-vendor Government Award History profiles. Has no web/MCP/Agent tools. Not user-invocable — only the orchestrator command dispatches this subagent via the Agent tool.

Reader subagent invoked by arckit-datascout (orchestrator). Fetches and extracts factual evidence about external data sources for one (category, source_type) pair. Returns a JSON payload conforming to arckit-claude/schemas/datascout-handoff.schema.json. Not user-invocable — only the orchestrator dispatches this subagent via the Agent tool.

This skill should be used when the user is starting an architecture project or asking what to run next. Load whenever the task sounds like 'I'm starting a new project', 'guide me through', 'what command should I run', 'what comes next', 'how do I begin', 'help me get started', 'which /arckit:* in what order', 'set up a new project', 'new system build', or 'where do I start'. Recommends a tailored command sequence based on sector, project type, current stage, and timeline.

This skill should be used when the user wants to bulk-build ArcKit artefacts in parallel rather than running individual /arckit:* commands one at a time. Invoke manually with /arckit:arckit-build when the task sounds like 'kick off a build', 'build everything', 'generate all artefacts', 'run all the commands', 'rebuild this project from scratch', 'resume the build', 'pick up where we left off', 'refresh the artefacts', 'run the recipe', 'build the whole project end-to-end', or 'parallel build', or mentions `--plan`, `--resume`, `--target`, `--refresh`, `--recipe`, or `.arckit/state.json`. The skill orchestrates parallel /arckit:* generation using subagent isolation: reads project state, computes the artefact dependency DAG, dispatches one subagent per target per wave (each subagent invokes a /arckit:* skill in its own context), validates outputs, commits the wave, and persists progress to .arckit/state.json for resumability.

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.

33 hooks across 10 events

Detect ArcKit artifacts with overdue reviews or long-unchanged drafts