hmcts

Use when working inside an api-cp-* repo and the user wants to publish/expose their API docs, "add my API to the catalog", set up the publish-api-docs workflow, or get a hmcts.github.io docs site. Wires the current repo into the amp-catalog Swagger UI pipeline, handles the two one-time GitHub Pages admin gaps that fail silently otherwise, and verifies the live site. This is the per-repo counterpart to the catalog-publisher agent, which only touches amp-catalog/docs/apis.json.

Wire up auto-dev and auto-SIT deployment CI for a service-cp-* repo after Azure provisioning and cp-vp-aks-deploy registration are complete. Idempotent — safe to invoke again if the jobs already exist. Use when a service-cp-* repo is missing the deploy-dev and deploy-sit jobs in its ci-build-publish.yml, or when setting up a newly bootstrapped service for the first time.

Start a new HMCTS API-Marketplace API specification repo using the canonical HMCTS template (api-hmcts-crime-template) as master source. Use when creating a new api-cp-* repo (OpenAPI-first, spec-only) distinct from a runtime service-cp-* service.

Stand up a new HMCTS API-Marketplace service-cp-* using the canonical HMCTS template (service-hmcts-crime-springboot-template) as master source. Use when creating a new Spring Boot service for the Common Platform.

Bootstrap the gitignored .claude/CLAUDE.md for any api-cp-* or service-cp-* repo with three @import lines pointing to hmcts-apim-sdlc-orchestrator context standards. Runs automatically on every session start via the SessionStart hook — invoke manually only to force an update.

Use when the user wants to review, audit, or check an OpenAPI v3 spec — applies HMCTS data-sharing policy (UK GDPR/DPA 2018), infrastructure SLA (Azure APIM/AKS), API standards, and security standards (OAuth 2, TLS, input validation). Returns a scored report with Critical/Warning/Info findings.

Export a self-contained, night-friendly HTML artifact for a CPP pipeline stage — using the right template from the bundled gallery. Use whenever a decision must be made, a plan needs improving, or a design gap is discovered — AND always to export the implementation plan before any code is written. Picks the template that fits the scenario (plan, decision, comparison, architecture, investigation, status) and writes it to docs/pipeline/artifacts/. <example> user: "We've finished the design — get ready to implement the booking engine." assistant: "Before implementation starts I'll use export-design-artifact to export the implementation plan (template 03) to docs/pipeline/artifacts/ and surface it at the Stage 4 gate." </example> <example> user: "Should the move-to-past action be a new endpoint or extend the existing one?" assistant: "That's a decision — I'll use export-design-artifact to produce a decision record (template 07) weighing the options before we commit." </example> <example> user: "The design does

Review a pull request for a CPP or HMCTS Crime Common Platform repository against CPP coding standards. Use when asked to review a PR or code changes specifically in a CP or HMCTS context service.

Validate API contracts (RAML/JSON Schema/OpenAPI) against their implementations. Use when checking for API drift, reviewing schema changes, or verifying contract consistency.

Design a new CPP capability or service — choose between CQRS context service and Modern by Default patterns, define bounded contexts, events, APIs, and produce a design proposal with diagrams and trade-offs. Use when the user asks to "design", "architect", "plan the architecture of", or decide "how should we build X" for a CPP feature, service, integration, or cross-context change.

Author or extend automated tests in HMCTS CPP test repos. Use when writing a new Serenity BDD/Cucumber UI scenario in cpp-ui-e2e-serenity, or a new JUnit 5 + REST Assured *IT.java in cpp-apitests, or when extending existing features, step definitions, page objects, or integration tests in those repos.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

Debug and understand Azure DevOps pipeline configurations. Use when a pipeline fails, when setting up CI/CD for a new repo, or when tracing variable resolution across templates.

Summarise one HMCTS service's OpenAPI spec from cnp-api-docs. Reports title, version, auth, endpoint count by tag, owning product, hosted Swagger UI link, and local file path. Use when the user asks "what does pcs-api expose", "summarise ccd-data-store-api", "what auth does X use", "show me the endpoints of Y".

Find every product that uses a given CCD feature token (e.g. notice_of_change, case_flags). Use when the user asks "which services use X", "who has NoC enabled", "what products configure case flags".

Trace a CCD callback for a given event-id and service from definition through to controller. Returns the chain of file:line locations. Use when the user wants to know what runs when an event is submitted in a specific service.

Search across all cloned HMCTS repos using the workspace's pre-tuned ripgrep wrapper. Use when the user asks about code or text patterns spanning multiple service teams or platform components.

Answer a "what is X" / "how does Y work" / "explain Z" question about any CFT topic — workspace, CCD, XUI, WA, AM, bulk-scan, platform/CNP. Routes via DOCS.md to the right page in either the root docs/ tree or a product-level apps/<product>/docs/ tree.

Find which HMCTS API service exposes a given HTTP path. Searches cnp-api-docs for matching OpenAPI paths and reports the owning service, methods, the local spec file, the hosted Swagger UI link and the workspace product that publishes it. Use when the user asks "which service has POST /cases/{id}/...", "what exposes /hearings", "where is /case-types defined", etc.

Find real, in-repo examples of how a feature is implemented in any HMCTS CFT product (CCD, XUI, WA, AM, bulk-scan, service teams). Use when the user wants concrete code references — "show me a real Notice of Change implementation", "where do they use case_flags", "give me an example of a mid-event callback".

Find a Diátaxis how-to recipe for an action-shaped task across the workspace docs. Use when the user asks "how do I add an event in CCD", "where do I configure work allocation tasks", "how do I add a repo", "how do I publish a definition to AAT".

Validate API contracts (RAML/JSON Schema/OpenAPI) against their implementations. Use when checking for API drift, reviewing schema changes, or verifying contract consistency.

Design a new CPP capability or service — choose between CQRS context service and Modern by Default patterns, define bounded contexts, events, APIs, and produce a design proposal with diagrams and trade-offs. Use when the user asks to "design", "architect", "plan the architecture of", or decide "how should we build X" for a CPP feature, service, integration, or cross-context change.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

Debug and understand Azure DevOps pipeline configurations. Use when a pipeline fails, when setting up CI/CD for a new repo, or when tracing variable resolution across templates.

Review a pull request for a CP repository. Use when asked to review a PR, check code changes, or provide feedback on a pull request.

Validate API contracts (RAML/JSON Schema/OpenAPI) against their implementations. Use when checking for API drift, reviewing schema changes, or verifying contract consistency.

Scaffold new modules, commands, queries, events, or viewstore entities within an existing cpp-context-* service. Use when adding new capabilities to a context service.

Navigate and understand any cpp-context-* service. Use when onboarding to a context service, exploring its modules, or understanding its CQRS structure and integrations.

Audit dependency versions across CPP repositories. Use when checking for version mismatches, outdated libraries, or parent POM alignment across context services.

Bootstrap a new Modern by Default (MbD) Spring Boot service for the Common Platform. Use when creating a new microservice, event processor, or API service.

Debug and understand Azure DevOps pipeline configurations. Use when a pipeline fails, when setting up CI/CD for a new repo, or when tracing variable resolution across templates.

Review a pull request for a CPP repository. Use when asked to review a PR, check code changes, or provide feedback on a pull request.

Validate Terraform modules and configurations across CPP infrastructure repos. Use when checking Terraform code, reviewing infrastructure changes, or verifying module consistency.

Use when the user wants to review, audit, or check an OpenAPI v3 spec — applies HMCTS data-sharing policy (UK GDPR/DPA 2018), infrastructure SLA (Azure APIM/AKS), API standards, and security standards (OAuth 2, TLS, input validation). Returns a scored report with Critical/Warning/Info findings.

Use when the user wants to wire Claude context for a repo, set up shared templates, or run the one-time per-repo Claude onboarding — creates the gitignored .claude/CLAUDE.md with three @import lines pointing to shared apim-claude-template standards.

Use when the user wants to create a pull request, raise a PR, or open a PR — extracts JIRA ticket from branch name, drafts a rich PR description, runs gh pr create, and transitions the JIRA ticket status.

Use when cutting a new GitHub release for an APIM service — finds PRs merged since the last tag, filters out dependencies, chores and docs, computes the next version, and creates the release with a functional changelog.

Automated review rules for opal-frontend-common-ui-lib PRs. Use when asked to review code, run @codex review, or provide PR feedback; apply severity levels and the required comment format.

Guardrails for Vitest changes in opal-frontend-common-ui-lib. Use when editing Vitest config, Angular test setup, or VS Code Vitest Explorer support so the extension path works without regressing the normal Angular CLI Vitest flow.

Repository structure, build/test commands, coding style, and contribution rules for opal-frontend-common-ui-lib. Use when navigating the repo, running or debugging builds/lint/tests, or following style conventions.

Use when the user asks to produce a data-dependencies architecture document for a system from a folder of source binary documents (.docx, .doc, .pdf, .pptx, .md, .txt). The skill distils the binaries into plain text via the BMAD-style distillation process (pandoc + textutil + pdftotext), analyses them for the system's inbound and outbound data dependencies, writes a deterministic Markdown document with a top-level "At a Glance" summary table, a clustered Mermaid overview diagram (Inbound / Platform / Outbound subgraphs), and a compact `Attribute / Detail` summary table under every dependency, then renders the Markdown to a styled PDF using the house typography and Mermaid theme. Triggered by phrases like "create a data dependencies doc from this folder", "build the data-dependency architecture for X", "generate the data-dependencies PDF from these source docs".

Use when the user asks to produce a module-organised functional architecture document for a system from a folder of source binary documents (.docx, .doc, .pdf, .md, .txt). The skill distils the binaries to plain text, identifies the application's functional modules, writes a deterministic Markdown document with a top-level "At a Glance" module table, a single Mermaid `Module overview` diagram, and a per-module section (lead paragraph + Capabilities bullets + Attribute / Detail table + Key user actions + Sources blockquote), then renders the Markdown to a styled PDF using the same house typography and Mermaid theme as the sibling `create-data-dependency-architecture` skill. Triggered by phrases like "build a functional modules document", "what modules does this system have", "describe the application module by module", "create a module architecture PDF".

Transform a folder of mixed-format source documents (Markdown, PDF, DOCX, XLSX, images, etc.) into a C4 architecture model. Runs bmad-distillator on the sources, synthesizes a Structurizr DSL workspace (at minimum a System Context view; adds Container and Component views when the documents support them), and generates a browsable static site with `structurizr-site-generatr`. Also exposes a serve command so the model can be explored in a browser. Use this skill whenever the user wants to derive architecture diagrams, a C4 model, or a Structurizr workspace from existing documentation — even when they don't use those exact terms. Common triggers include "create an architecture diagram from these docs", "I have a folder of design docs, visualise the system", "generate a C4 model for this project", "build a Structurizr workspace", "reverse-engineer an architecture from docs".

Upgrade dependencies and maintain CVE-focused resolution hygiene in a Yarn 4 Node.js project. Use when asked to upgrade one dependency, multiple dependencies, or all dependencies to latest versions, when asked to remediate CVEs from `yarn-audit-known-issues` produced by `yarn npm audit --recursive --environment production --json`, or when asked to check and remove unnecessary `package.json` `resolutions` after upstream dependency upgrades. Follow this precedence for CVE remediation: (1) upgrade the vulnerable package if it is in package.json `dependencies`, (2) otherwise upgrade a direct parent dependency that pulls in the vulnerable transitive package, (3) otherwise use a package-level CVE resolution for the vulnerable package, falling back to descriptor-level resolution only when a broad override is incompatible.

Start, restart, run up, or smoke-check the WA Reporting Frontend app locally with the preferred Flyway-backed seeded Docker Postgres database and auth disabled. Use when asked to run up the app, start the app locally, get the app running with local data, restart local app, seed local database, rebuild local DB data, change local seed size, set LOCAL_DB_SEED_RECORD_COUNT or LOCAL_DB_SEED_RANDOM_SEED, disable auth for local development, or verify local analytics routes.

Repository structure, build/lint commands, export map rules, and release guidance for opal-frontend-common-node-lib. Use when navigating the repo, adding modules, or running tooling.

Automated review rules for opal-frontend-common-node-lib PRs. Use when asked to review code, run @codex review, or provide PR feedback; apply severity levels and the required comment format.

Creates operational runbooks and documentation for HMCTS platform team following Middleman conventions. Generates .html.md.erb files with proper YAML frontmatter, standard sections, and HMCTS-specific patterns (cluster names, environments, PR examples). Uses contribution guides and templates. Triggers on "create runbook", "new runbook", "generate guide", "create documentation", "add page", "new operational doc".

Use when adding, modifying, or reviewing C4 model elements — new subdomains, products, shared components, relationships, or views. Also use when asked to explore or document system architecture.