Boxfusion-plugins

Generates a safe, read-only Microsoft SQL Server (T-SQL) query from a natural-language request against a Shesha database, using the Shesha entity metadata to find relevant tables, build schema context, and validate the result. Ports the Shesha Automate Engine's SQL generator (prompts + validation rules) so it runs directly in Claude Code without the MCP server. Use when asked to "generate a SQL query", "write SQL from natural language", "query the Shesha database", "generate a view or stored procedure", or similar. Produces only SELECT/INSERT/UPDATE — blocks DELETE/DROP/TRUNCATE/ALTER/CREATE/RENAME.

Upgrades Shesha framework dependencies in both frontend and backend projects to a specified BoxStack version. Handles monorepo and standard project structures. Use when user wants to upgrade, update, or migrate Shesha/BoxStack versions.

Removes all Intent Architect artifacts and references from a Shesha (or any .NET) project. Deletes the root-level intent/ metadata folder and .isln solution files, removes Intent.* NuGet package references, and strips Intent-related using statements, [IntentManaged(...)] attributes, and [assembly: IntentTemplate(...)] / [assembly: DefaultIntentManaged(...)] statements. Use when the user asks to remove, drop, clean up, or decouple from Intent Architect, the intent folder, or Intent.RoslynWeaver / Intent.VisualStudio dependencies.

Set up a Shesha-based project development environment aligned to Boxfusion development standards and best practices. Run this when a new Shesha project has just been created to verify and configure the dev environment.

Installs the Claude Logger configuration into Claude Code settings.json files — the CLAUDE_LOGGER_API_URL env var, the shesha-utils plugin, and the boxfusion-plugins marketplace. The UserPromptSubmit/PreToolUse/PostToolUse/SessionStart/Stop ingest hooks ship with the plugin (hooks/hooks.json) and reference the bundled cc_logger.py via ${CLAUDE_PLUGIN_ROOT} — no machine-specific absolute path. Each hook runs cc_logger.py, which enriches the event (turn cost, transcript details on Stop) and forwards it directly to the ingest backend — no local server required. Applies the configuration to both the global user settings and the current project settings as an additive merge — creating files where missing, updating these specific values in place where they already exist, and never removing or overwriting unrelated keys. Use when the user asks to set up, install, configure, add, enable, or update the Claude logger, logger hooks, telemetry hooks, or the ingest hooks for Claude Code.

Imports Azure DevOps Test Plan / Test Suite test cases via the Azure DevOps MCP server (@azure-devops/mcp) and generates paired markdown test plans + recorded Playwright specs under test-plans/. Trigger phrases include "create test from devops", "import test plan from azure devops", "generate tests from test plan <id>", "pull test cases from devops", "create tests from ADO suite". The user provides an Azure DevOps Test Plan ID (and optionally a Suite ID to narrow it). The skill connects via the MCP, lists the suites and test cases, fetches each test case work item's Microsoft.VSTS.TCM.Steps field, converts the action/expected-result pairs into the prefixed TC-NN plan format per test-plans/RULES.md (one .md plan per suite, one TC per ADO test case), then records real selectors live via Playwright MCP into a paired .spec.ts using the same recording loop as the create-test skill. Reads App URL, environment, credentials, and the Azure DevOps org/project from CLAUDE.md. This skill authors only — the plans are exec

Author a new markdown test plan at test-plans/<folder>/<name>.md AND a paired Playwright spec at test-plans/<folder>/<name>.spec.ts with real selectors recorded live via MCP browser. Trigger phrases include "create a test", "create a test plan", "new test for X", "test plan for Y", "add a test that...". The user provides only a title and a numbered list of high-level steps. The skill pulls App URL, environment, and credentials from CLAUDE.md, expands each step into full action steps per test-plans/RULES.md, matches the style of existing plans, AND walks each step against the real app via Playwright MCP to capture the resolved locator before writing the spec. Steps that can't be located after 2 retries fall back to a `// TODO[selector]:` marker for AI-repair on first run. The plan + spec are executed later by the run-test skill — this skill authors only, it does NOT run.

Self-reliant, fast bootstrap for the hybrid Markdown + Playwright testing workflow. One command — `/test-setup` — gets a fresh project to a state where `/CreateTest` works first try. Scaffolds every file the workflow needs (CLAUDE.md, package.json, playwright.config.ts, tsconfig.json, .gitignore, scripts/run-plan.js, scripts/build-dashboard.js, scripts/generate-allure-results.js, scripts/sync-to-hub.js, scripts/hub.config.example.json, test-plans/RULES.md, empty test-plans/ and test-reports/ folders) directly from templates bundled inside this skill — does NOT copy from any other project. Prompts the user once for project-specific values (project slug, app name, app URL, environment, admin credentials), substitutes them into the scaffolded files, then verifies prerequisites (Node ≥ 18, npm install, Playwright Chromium, Java for Allure) and offers to install what's missing. Registers the Playwright MCP server with Claude Code via `claude mcp add playwright -- npx -y @playwright/mcp@latest --headless` so `/Crea

Dispatch a test plan to GitHub Actions instead of running it locally — the cloud-side workflow uses claude-code-action to drive the test, posts a Teams Adaptive Card on failure, and publishes an Allure report to gh-pages. Trigger phrases include "/Run-test-remote", "run test remote", "run on CI", "dispatch test on github actions", "run remote test", "trigger e2e workflow", "kick off the workflow". If `.github/workflows/e2e-test.yml` is missing the skill scaffolds it from a template and walks the user through wiring the three required secrets (`ANTHROPIC_API_KEY`, `APP_PASSWORD`, `TEAMS_WEBHOOK_URL`). If present, the skill picks plan(s) via the same disambiguation UX as `/RunTest`, dispatches each via `gh workflow run e2e-test.yml -f test_plan=<path>`, and prints the resulting run URL. Optional `--watch` flag blocks until the run completes.

Execute one or more markdown test plans from test-plans/ locally using the Playwright-first / AI-repair hybrid runner. Trigger phrases include "run test X", "run the X test", "run test-plans/<folder>/<name>.md", "execute the call log test", "run the test plan for Y". When the plan name is ambiguous (multiple matches, or none specified), the skill lists every plan with its last-run status and asks the user to pick one or more (`1,3,5`, `1-3`, or `all`). The skill invokes scripts/run-plan.js (which runs the paired .spec.ts via @playwright/test); on failure it falls back to AI-driven MCP browser execution to repair the failing line in the spec, then re-runs. After 2 failed AI-repair attempts it auto-classifies the failure by signature — stale-plan symptoms trigger a plan/spec fix, business-logic symptoms auto-log a bug under test-reports/bugs/ and the run continues. Writes a markdown report to test-reports/YYYY-MM-DD/, regenerates test-reports/index.html and the Allure report. **Does NOT push to the hub** — the

Analyzes a Shesha form configuration JSON and removes dead/obsolete component properties, strips console.log calls from JS code strings, validates property value types, validates the shape of dropdown values items, detects scripts referencing component labels instead of propertyNames, runs layout validations (container dimension overflow, labelCol+wrapperCol span checks, device-specific style path conflicts), validates JavaScript syntax of embedded code strings, auto-fixes API calls missing try-catch by wrapping the function body in try/catch, and auto-fixes API calls in async-context properties that are missing async/await by adding the async keyword and awaiting calls. Falls back to manual review when function structure is ambiguous. Also detects API calls using .then() chaining and flags them for conversion to async/await + try-catch. Use when a form has been migrated, components have been refactored, or you want to clean up stale properties and debug statements.