bcgov

Use this skill when a BC Small Claims Notice of Claim draft is already captured in canonical JSON and the next step is deterministic PDF-generation readiness review, renderer handoff, or artifact verification. This skill is for JSON-to-PDF generation only. It must not take over guided intake or canonical JSON authoring.

Use this skill when a BC Small Claims Notice of Claim draft already exists in canonical JSON and the next step is to produce a deterministic mock filing payload, simulate downstream submission, or inspect adapter artifacts. This skill is for JSON-to-adapter handoff only. It must not take over guided intake or PDF rendering.

This skill should be used when the user wants to start a BC Small Claims Notice of Claim, answer the Form 1 questions interactively, turn freeform facts into a structured intake packet, align the answers to the observed Filing Assistant question flow and canonical case JSON, or identify what information is still missing before validation or rendering.

Use this skill when a BC Small Claims Notice of Claim draft is already captured in canonical JSON and the next step is deterministic PDF-generation readiness review, renderer handoff, or artifact verification. This skill is for JSON-to-PDF generation only. It must not take over guided intake or canonical JSON authoring.

Use this skill when a BC Small Claims Notice of Claim draft already exists in canonical JSON and the next step is to produce a deterministic mock filing payload, simulate downstream submission, or inspect adapter artifacts. This skill is for JSON-to-adapter handoff only. It must not take over guided intake or PDF rendering.

This skill should be used when the user wants to start a BC Small Claims Notice of Claim, answer the Form 1 questions interactively, turn freeform facts into a structured intake packet, align the answers to the observed Filing Assistant question flow and canonical case JSON, or identify what information is still missing before validation or rendering.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Diagnose and fix a bug in the Grants Applicant Portal — takes a bug report or stack trace, locates the root cause, implements a targeted fix, and verifies with tests.

End-to-end ticket implementation for the Grants Applicant Portal — parses ticket details, architects a solution across frontend and/or backend, implements using specialist sub-agents in parallel, runs tests, and produces a PR-ready summary.

New developer orientation for the Grants Applicant Portal — tours the codebase, explains key architecture patterns, answers "how do I..." questions, and produces a personalised cheat sheet.

Refactor a component, service, or domain area in the Grants Applicant Portal — understands existing code, plans changes, implements via specialist sub-agents, and verifies nothing broke.

Full PR review for the Grants Applicant Portal — runs security, architecture/conventions, and test coverage reviews in parallel and produces a structured report ready to paste into GitHub.

Scaffold a complete FastEndpoints endpoint for the Grants Applicant Portal backend — creates the endpoint class, request, response, and validator files, then registers it within the domain folder.

Create a new Entity Framework Core migration for the Grants Applicant Portal backend — runs dotnet ef migrations add, then summarises the generated Up/Down SQL.

Scaffold a CQRS use case for the Grants Applicant Portal backend — creates a Command or Query record and its Handler, following the MediatR + Ardalis.Result pattern.

Manage OpenShift instance deployments: deploy, teardown, list, build images, backup/restore databases, and setup service accounts. Trigger phrases: deploy instance, teardown instance, list instances, build images, backup database, restore database, setup service account, oc deploy, instance management. Do NOT invoke for: local development setup, docker-compose, writing application code, database migrations.

Splits a feature branch into multiple sequential draft PRs targeting develop. Trigger phrases: split branch into PRs, break branch into PRs, create stacked PRs, split into multiple PRs. Do NOT invoke for: creating a single PR, cherry-picking individual commits, or rebasing.

Requirements Refiner: Iteratively questions the user to clarify vague requirements and outputs a single consolidated requirements document in feature-docs.

Implements user stories from a user_stories directory in dependency order using subagents. Reads README.md to find the next unchecked story, spawns Agent tool subagents to implement each one, tracks progress via scenario checkboxes in story files and story checkboxes in README. Trigger phrases: implement stories, implement user stories, story implementer, work on stories, implement next story. Do NOT invoke for: writing user stories (use write-user-stories), general code changes, checklist execution.

User Story Writer: Converts refined requirements into individual User Story files following a strict template, plus a README.md with phase breakdown. Trigger phrases: write user stories, generate user stories, create user stories from requirements.

Converts a user-provided list of issues, bugs, or tasks into a structured markdown checklist file in docs-md/. Trigger phrases: create checklist, make a checklist, turn these into a checklist, create todo file, checklist from these items. Do NOT invoke for: executing/working through checklist items, editing existing checklists, or general markdown file creation.

Works through a markdown checklist file, implementing each unchecked item sequentially. Trigger phrases: work through checklist, execute checklist, fix checklist items, work on the checklist, continue the checklist, next checklist item. Do NOT invoke for: creating new checklists (use checklist-creator), general code changes not tied to a checklist file.

Create a new Claude Agent Skill. Auto-invoke when the user asks to create a skill, make a new skill, or scaffold a workflow automation. Do NOT invoke for general coding tasks.

Guidance for producing Terraform, Bash, and GitHub Actions changes in ai-hub-tracking. Use when implementing Terraform modules, stacks, deployment scripts, or GitHub Actions workflows.

Guidance for writing and running Python/pytest integration tests against APIM, App Gateway, and AI services in ai-hub-tracking.

Guidance for Azure AI Evaluation SDK usage in the Python integration harness for ai-hub-tracking.

Guidance for APIM policies, routing, and backend configuration in ai-hub-tracking. Use when modifying APIM inbound/outbound policies, rate limiting, backend routing, or API key authentication.

Guidance for Application Gateway rewrite rules, WAF custom rules, and request security layers in ai-hub-tracking. Use when modifying App Gateway rewrite rules, WAF custom rules, subscription key normalization, or SSL configuration.

Guidance for upgrading tracked Python and npm dependencies in ai-hub-tracking. Use when updating pyproject.toml or package.json, regenerating uv.lock or package-lock.json through package managers, responding to Dependabot or Renovate dependency alerts, or adjusting dependency automation in renovate.json.

Guidance for maintaining documentation in the docs/ site for ai-hub-tracking. Use when updating HTML pages, partials, build scripts, or Terraform reference docs.

Guidance for researching authoritative external documentation using Microsoft Learn MCP and Upstash Context7, with explicit approval for fallback sources. Use when looking up Azure, Terraform, or BC Gov platform documentation.

Apply the unified-scheduling backend logging pattern for .NET API services. Use when adding or changing logging in api/ services, controllers, background startup services, exception handling, or tests that directly instantiate logged services. Covers ILogger constructor injection, Microsoft logging level guidance, structured message templates, sensitive data handling, and validation commands.

Add or update Calendar module functionality using the contribution-based frontend architecture and Calendar-owned backend event model. Use when modifying calendar views, calendar data contributions, create/detail actions, or Calendar Event/EventSeries backend behavior.

Refactor FluentValidation validators to use inline WithMessage strings instead of WithErrorCode + shared error-code constants. Use when asked to remove error codes, inline validation messages, or clean up validators that reference ApiValidationErrorCodes.

Refactor or create Vue 3 form modal components using a formData object, generated Zod schemas, and consistent save/error handling. Use when asked to clean up, refactor, or build a form modal in web/src/.

Add or update permission seed entries using module-owned PermissionSeedConfiguration contributions, then let PermissionSeeder aggregate across modules. Use when introducing a new permission or moving permissions between modules.

Write minimal xUnit tests for .NET/C# changes in the unified-scheduling API. Use when adding tests for endpoints, validators, services, or handlers in api/. Covers test project layout, naming conventions, fixture setup, and run commands.

Write minimal Vitest + Vue Test Utils tests for the unified-scheduling web frontend. Use when adding tests for Vue components, composables, stores, or utilities in web/src/. Covers test layout, setup helpers, mocking patterns, and run commands.

Explain BC Gov design tokens, their naming convention, and how to apply them. Use when asked about design tokens, CSS variables, token naming, or how to map BC Gov values to a framework theme (e.g. Vuetify).

BC Gov hardening patterns for GitHub Actions workflows — deny-all `permissions: {}` baseline with per-job step-ups, first-party tag vs third-party SHA pinning, fork-gate, single results-aggregator required check, pinned ubuntu-24.04 runners, script-injection-safe env handling, and signed-commit ruleset interaction. Covers `.github/workflows/*.yml`, `dependabot.yml`, and the branch-protection / repository-ruleset settings that pair with them. Use when authoring or reviewing a workflow in a BC Gov repo, debugging permission-denied errors, or onboarding Dependabot.

Tangle code out of prose runbooks and wikis into version-controlled snippets, per source and losslessly, and detect doc/code drift. Use it to author or extend a RunbookParser config.yaml, run the parser (ingest, check, seal, diff), turn raw snippets into safe parameterized building blocks for n8n, or backport a snippet fix to the source doc.

Compose and chain cleaned snippets into n8n operational triage workflows — a webhook trigger, read-only idempotent triage steps in order, and a markdown-to-HTML response served back to the caller. Produces n8n workflow JSON in tools/n8n/workflows/ ready to POST to the n8n API (you post it, not the skill), plus a local_workflow.sh equivalent a developer can run without n8n. Use when building or iterating a triage workflow from cleaned snippets.

Assess GitHub repository maturity against BC Gov DevOps and security standards. Generates a MATURITY_REPORT.md scorecard covering branch protection rulesets, TypeScript strictness, Renovate preset tracing, vulnerability SLAs, CI/CD quality gates, and OpenShift container security. Use when onboarding repos, running compliance reviews, or evaluating vendor conformance.

BC Gov Private Cloud OpenShift workload-manifest guidance: picking the right controller (Deployment, StatefulSet, DaemonSet, Job, CronJob) and shaping it for the platform — container resources and QoS, namespace LimitRange defaults, pod and container securityContext hardening (runAsNonRoot, drop ALL capabilities, no privilege escalation, read-only root filesystem) for the restricted-v2 SCC, liveness/readiness/startup probes, terminationGracePeriod and SIGTERM handling, PID-1 reaping with tini or dumb-init, PodDisruptionBudgets, horizontal scaling (HPA, VPA), and CronJob admission rules. Use when authoring or reviewing a workload manifest bound for a license-plate runtime namespace. Out of scope: NetworkPolicies, Vault/ESO, Argo CD/GitOps, Artifactory image pulls, Porter TCP exposure, storage class choice, Sysdig, ACS runtime policies, security assessment.

Scaffolds a new skill profile in this repo and fills in the required SKILL.md structure when a contributor wants to add a skill.

Validates skill profiles against the spec and explains how to fix failures before a PR is opened or merged.

Azure subnet, NSG, and private-endpoint patterns for adding subnets inside an existing VNet — atomic NSG-at-creation, per-service delegation, PE subnet layout, ARM write serialization, and reference NSG layouts for PE, APIM, App Gateway, and Container Apps subnets. Tool-agnostic guidance with Terraform (azapi_resource), Bicep, and az CLI examples. Use when adding subnets, debugging delegation or PE errors, or sizing a PE subnet.

ABP Application Services, DTOs, AutoMapper profiles, validation, and error handling for Unity. Use when creating or modifying app services, DTOs, or mapping profiles in Application or Application.Contracts projects.

ABP module architecture and layering rules for Unity. Use when creating new modules, adding cross-module dependencies, or understanding project organization and dependency direction.

ABP CLI commands - generate-proxy, install-libs, add-package-ref, new-module, install-module, abp update, abp clean, abp suite generate. Use when the user asks how to run ABP CLI commands, generate proxies, install NPM libraries, or use ABP Suite.

Testing patterns for Unity - xUnit, Shouldly assertions, NSubstitute mocks, ABP test infrastructure. Use when writing or modifying unit tests or integration tests.

DDD patterns for Unity - Entities, Aggregate Roots, Repositories, Domain Services, Domain Events. Use when creating or modifying entities, repositories, or domain services in Domain or Domain.Shared projects.

ABP Entity Framework Core for Unity - DbContext configuration, entity mapping, repository implementation, EF migrations. Use when working in EntityFrameworkCore projects, adding migrations, or implementing repositories.

Audit pending npm package lifecycle scripts (postinstall, preinstall) for security risks before approving them. Trigger when scripts are blocked or pending approval.

Safely auto-patch local npm vulnerabilities and stage the changes with a pre-written commit message template. Trigger when asked to audit, patch dependencies, or fix CVEs.

Safely auto-patch local npm vulnerabilities and stage the changes with a pre-written commit message template. Trigger when asked to audit, patch dependencies, or fix CVEs.

Scaffolds Kysely database migrations, matching repository changes, and type definitions. Trigger on keywords migration, create table, modify table, alter column, drop table, database schema change.

Create native unit tests for Swift (iOS) and Kotlin (Android) code in the bcsc-core package. USE WHEN: testing native code, adding unit tests for native modules, writing XCTest or JUnit tests for bcsc-core, mocking native protocols or interfaces. DO NOT USE FOR: TypeScript/React tests, UI integration tests, or E2E tests.

Search the MMI Elasticsearch `content` index, a BC government media-monitoring corpus of ~8.9M news clips (print, online, radio, TV, wire). Use this skill WHENEVER the user asks to find, list, count, or analyze media content, news stories, clips, or coverage in Elasticsearch, OR mentions any of these by name — top stories, featured stories, alerts, commentary, tone or sentiment, tags (ministries), topics, media types, or sources. Also use it for queries like "top stories today", "what coverage did X get", "negative sentiment about Y", "clips from the Vancouver Sun", or any filtering by ministry/tag, topic, date, source, or sentiment. This skill defines the schema and the correct (often non-obvious) query patterns; consult it before writing any query against the `content` index, because several fields require nested queries or `.keyword` subfields that fail silently if used wrong.

Scans repository GitHub Actions workflows, updates action versions and SHAs safely, and writes a concise CHANGELOG summary.