dev-cleanup

Plugin dev-cleanup from marketplace bmsuisse-skills in bmsuisse/skills. Commands read from the repo's manifest — 2 days ago.

Skills (58)

• agent-coordinator

  Coordinate several agents working in parallel on one repo: partition the work, give each agent a worktree off a policy-free consolidation branch, then ship everything in one PR to dev (agents review their own slice, one CI run). Use when asked to "run agents in parallel", "split this across agents",

• aiochannel-python

  Correct patterns for channel-based asyncio concurrency in Python using the aiochannel library. Use this skill whenever the user is working with aiochannel, writing producer/consumer pipelines in asyncio, or asking how to pass data between async tasks without a shared queue. Trigger on any mention of

• autoresearch

  Autonomous iterative optimization loop for Python, SQL, ML, and Spark/Databricks. Define a measurable goal; the skill runs code changes, measures, and keeps/reverts until you stop it or the budget runs out. Use for: Python runtime (cProfile, hyperfine), SQL latency, pytest pass rate/coverage, ty/pyr

• azure-cost

  Query, analyze, and reduce Azure spending via the Cost Management REST API and Azure CLI. Covers cost breakdowns by service/resource-group/resource, month-over-month spike detection, orphaned-resource hunting, storage tiering savings, VM rightsizing, and spend forecasting. Use this whenever the user

• bms-code-review

  BMS code review that fans out one focused subagent per concern (architecture, duplication, security, correctness, agent-docs/skills, performance, and per-layer SQL/backend/frontend reviews) depending on what changed. Use instead of, or in addition to, the generic `/code-review` for any BMS repo diff

• bms-frontend-design

  The BMS visual identity for internal web apps, built on the shared `@bmsuisse/ui` (sidebar/nav, form, dialog, and other primitives) and `@bmsuisse/datagrid` (`<DataGrid>`/`<TreeDataGrid>`) packages — plus the brand tokens (BMS red accent, background/surface scale, border-radius scale, typography) ev

• bms-plan-review

  Review an implementation plan before any code is written: checks it against BMS conventions and the existing skills (layering, SQL-first, testing, auth, frontend packages) and flags gaps. Use for step 3 of `dev-workflow` (implementation plan) — "review the plan", "is this plan right", "check my impl

• bms

  Master skill for the bmsuisse platform — routes to the relevant skills based on sub-command. Always enables caveman communication style. Use /bms for core guidelines (SQL + Python + TypeScript + glossary), /bms sql for SQL + Databricks optimization, /bms python for Python + autotuner, /bms data for

• bmsapp-native

  Use when a web app or FastAPI backend should talk to the BMS iOS app (`@bmsuisse/app-native`, `bmsdna-app-native`). Triggers: BMSNative, push to the app, widget, Live Activity, approvals, scan barcode, native form, Entra token.

• bmsui

  Pick the right shared component from `@bmsuisse/ui` / `@bmsuisse/datagrid` before writing a local one: dialogs, forms, dates, search/filters, tables, toasts, empty/error/loading states. Use for any React UI work in a BMS app.

• branching-strategy

  Set up or audit a repo's dev -> test -> main branching, build policies, per-area test labels and nightly deploy.

• clean-code

  Language-agnostic, pragmatic clean-code principles for writing and refactoring code at BMS: naming, function size and shape, control flow, error handling, abstraction, duplication, structure, and safe refactoring. Use whenever the user is writing new code, cleaning up or refactoring existing code, r

• clockify

  Query and log time entries in Clockify via its REST API — check a timesheet, look up the workspace/user/project, create or update time entries, and ALWAYS tag the description with a Jira issue key (`[JIRA-KEY]: Summary`) — never leave a Clockify entry without one. Use whenever the user asks about th

• code-comments

  Write and review code comments so they earn their place instead of adding noise. Use this whenever writing new code (to decide whether a comment is needed and how to phrase it), whenever reviewing a diff or file for comment quality, and whenever the user says things like "review these comments", "ar

• codebase-design

  Shared vocabulary and principles for designing deep modules (module, interface, depth, seam, adapter, leverage, locality). Use whenever the user wants to design or improve a module's interface, decide where a seam or boundary goes, make code more testable or easier for AI to navigate, split or merge

• codeunit-analyzer

  Comprehensive C-AL performance analyzer for Classic Microsoft Dynamics NAV (Navision). Targets Classic NAV anti-patterns: N+1 queries, LOCKTABLE overuse, FlowField overuse, key/index misalignment, heavy transactions, and page trigger abuse. Zero-dependency Python — no packages required. Use when the

• coding-guidelines-python

  Apply and enforce Python-specific coding standards. Use alongside coding-guidelines for any Python file — covers typing, Pyright, dataclasses, enums, abstract base classes, mutable defaults, and module-level state. Trigger on any Python work session, PR review, or when the user asks to "follow Pytho

• coding-guidelines-sql

  SQL and data warehouse coding guidelines for the BME data platform. Use whenever writing, reviewing, or refactoring SQL — including SparkSQL, T-SQL, and Databricks SQL. Apply when naming tables, columns, CTEs, views, functions, or procedures; building fact or dimension tables; working with business

• coding-guidelines-typescript

  Apply and enforce TypeScript-specific coding standards. Use alongside coding-guidelines for any TypeScript file — covers typing, no-any policy, interfaces, abstract classes, async typing, discriminated unions, and pre-commit checks. Trigger on any TypeScript work session, PR review, code generation

• cross-repo-discovery

  Find where a repo lives — locally or in the Azure DevOps org — before assuming a piece of functionality doesn't exist yet. Use this whenever the user asks about "other repos", "which repo has X", cross-repo/cross-service work, wants to find or clone a repo they don't have locally yet, or when you're

• data-modeling-dimensional

  Dimensional data modeling guide for the Fabricks platform — covers the full pipeline from staging through raw, transf, core, and semantic layers; fact and dimension table design; key strategy; SCD types; bridge tables; degenerate dimensions; and config. Use whenever designing or reviewing fact/dimen

• databricks-cli

  Databricks CLI operations: auth, profiles, data exploration, bundles, and notebook execution. Use this skill for ANY Databricks task — running or debugging notebooks on the cluster, executing SQL queries, exploring tables, deploying jobs, or fixing notebook errors. Trigger whenever the user mentions

• databricks-sql-autotuner

  Databricks SQL query optimizer and error fixer: analyzes a slow or broken SQL query, rewrites it for speed using SQL-level optimizations only, validates byte-for-byte result equivalence, and benchmarks both versions with statistical significance testing. Also diagnoses and fixes SQL errors (syntax e

• dead-code-audit

  Find unused functions, classes, exports, files, stale or unused dependencies, outdated and vulnerable packages, and circular imports in Python and TypeScript/JS/Vue/React projects, using vulture, ruff, deptry, knip, madge and friends via ready-made scripts, then verify each finding before deleting a

• design-review

  Review a web app or page for visual design quality — layout, spacing, typography, colour/contrast, visual hierarchy, component consistency, interaction states, and responsive behaviour. Not a UX audit (that checks usability/flow) — this checks whether it *looks* professional and polished. Works from

• deslop

  Remove AI slop from code and pull requests. Use this skill whenever the user wants to clean up AI-generated code, review a diff for unnecessary noise, audit a file or PR for style inconsistencies, over-abstraction, defensive checks that don't belong, redundant comments, or anything that "doesn't fee

• dev-cleanup

  Free disk space on a developer workstation: scan podman/docker storage, uv/npm/bun/pnpm/pip/cargo/gradle caches, app caches in ~/Library/Caches, stale git worktrees and old node_modules/.venv, show an overview with sizes and risk, and let the user pick what to clean. Use for "clean up my machine", "

• dev-workflow

  End-to-end workflow for non-trivial coding tasks: worktree, draft PR early, implement, review, test, publish. Trigger whenever starting a task that's more than a trivial one-file fix — "implement X", "fix issue #N", "build feature Y" — or when the user says "follow the workflow", "use a worktree", o

• duckdb

  Guide for working with DuckDB — CLI usage, SQL execution, reading files (CSV, Parquet, JSON, Excel), extensions (httpfs, spatial, json, excel, postgres, etc.), and the Python duckdb package. Use this skill whenever the user is working with DuckDB, whether via CLI, SQL scripts, or Python. Trigger on:

• ducklake

  Guide for working with DuckLake — the open lakehouse format and DuckDB extension that pairs a SQL catalog (metadata, transactions) with Parquet files on object/file storage. Covers ATTACH syntax, choosing a catalog database (DuckDB, SQLite, PostgreSQL), storing data files on Azure Blob Storage / Dat

• fabricks-devops-issues-resolver

  End-to-end resolver for Fabricks.Runtime DevOps issues that have already been diagnosed and locally fixed by the fabricks-devops-issues skill: commits and pushes the fix, reruns the affected job on Databricks to verify it actually works, and — only after explicit confirmation — closes the ticket wit

• fabricks-devops-issues

  Orchestrates Azure DevOps "Issue" work-item workflows in the Fabricks.Runtime repo — listing open issues so the user can pick one, surfacing which ones look like easy/ low-hanging-fruit fixes, auto-assigning issues by git blame, reporting on open issues, and diagnosing (and locally fixing) a job-run

• fabricks-glossary

  Use this skill whenever company-specific jargon, acronyms, or domain terminology is needed to answer correctly.

• fabricks-sql-analyzer

  Analyzes all SQL files in the Fabricks.Runtime repository, builds a dependency DAG, runs performance heuristics, and produces a Markdown report with ranked findings and improvement suggestions. Optionally fetches row counts and EXPLAIN COST plans from Databricks. Pass --fix to automatically create a

• fastapi-azure-auth

  Azure Entra ID SSO for FastAPI using cookie-based sessions (MSAL, /login → /callback → session). Trigger on: Azure AD login, Entra SSO, protect routes, RBAC, DEV_MODE bypass, download links with auth. Covers App Registration, AuthMiddleware, role checks via Postgres, and cookie auth enabling native

• fastapi-guideline

  Use this skill whenever working with FastAPI — building APIs, adding routes, structuring projects, streaming responses, handling authentication, database access, or running the server. Triggers on: "fastapi", "build an API", "add an endpoint", "stream response", "SSE", "server-sent events", "async e

• history-lessons

  Mine a mature repo's git history (reverts, commits that state a root cause, refactors, repeatedly-fixed files, optionally PR review comments) to learn what the team corrected over time, then distil that into short, evidence-backed rules for AGENTS.md / CLAUDE.md. Use when the user wants to teach age

• improve-codebase-architecture

  Scan a codebase for architectural friction and propose "deepening" refactors that turn many shallow modules into fewer deep ones, so the code is easier to test and easier for humans and AI to navigate. Presents candidates as a visual HTML report, then walks through the chosen one. Use whenever the u

• init-app-stack

  Use this skill whenever the user wants to bootstrap, scaffold, or initialize a new full-stack app with a Vite + React + TanStack + @bmsuisse/ui (shadcn/ui-based) frontend and a FastAPI + Postgres backend. Triggers on requests like "create a new app", "set up a project", "scaffold a full-stack app",

• inter-without-ai-slop

  Use Inter as a UI typeface in data-dense B2B apps (dashboards, tables, cockpits) without triggering the "generic AI dashboard" look. Trigger when styling a new screen, reviewing an existing one for genericness, or when Inter is already the base face and the app needs to look more considered.

• issue-triage

  Triage business users' Azure DevOps work items: research, then mark ready for an agent or ask business/technical questions (tags needs-business, needs-techie).

• kendo-ui-angular

  Use this skill whenever the user is working with Kendo UI for Angular — including the Data Grid, TreeList, TreeView, DropDownList, AutoComplete, or any @progress/kendo-angular-* package. Covers server-side paging/filtering/sorting, inline CRUD editing, row selection, custom cell templates, master-de

• kendo-ui-react

  KendoReact component library patterns and best practices for React developers. Trigger whenever the user works with KendoReact components, imports from @progress/kendo-react-*, asks how to set up Grid, Form, DateInputs, Charts, or any KendoReact component, asks about theming or licensing, or asks to

• kendo-ui-vue

  Use this skill whenever the user is working with Kendo UI for Vue — including the Data Grid, DropDownList, ComboBox, AutoComplete, or any @progress/kendo-vue-* package. Covers server-side paging/filtering/sorting, inline CRUD editing, row selection, custom cell templates, master-detail rows, groupin

• kull-generic-backend

  Kull.GenericBackend — an ASP.NET Core middleware (Kull-AG/kull-generic-backend, NuGet package Kull.GenericBackend) that exposes SQL Server stored procedures, views, and table-valued functions as REST endpoints from a backendconfig.json file, with Swagger/ OpenAPI generated automatically from sp_desc

• maintenance

  Periodic upkeep of BMS uv/bun repos, one mode per run: dead-code, bump, lint, audit, prod, nightly, xfail, db-perf, cost, tests, incident (security incident / supply chain attack), all. Use for "maintenance", "bump dependencies", "bun audit", "uv audit", "CVE", "nightly failed", "slow queries", "azu

• nicegui

  Build Python web UIs with NiceGUI — covering layout, widgets, data binding, routing, and the AgGrid data grid. Use this skill whenever the user mentions NiceGUI, wants to build a Python web app, dashboard, or internal tool, asks about ui.aggrid, ui.page, or any NiceGUI component. Triggers on: "niceg

• playwright-python

  Browser automation and visual verification with Playwright in Python. Use this whenever the user wants to drive a browser from Python — taking screenshots of a running dev server or deployed page, scraping rendered content, automating clicks/forms, mocking network requests, or writing pytest browser

• prek

  Set up code formatting and pre-commit hooks using prek (fast Rust-based alternative to pre-commit) with prek.toml config. Use whenever the user wants to configure prek, add formatters, set up pre-commit hooks, or enforce code style. Triggers on "set up prek", "add formatting", "configure formatters"

• procrastinate

  PostgreSQL-based async task queue for Python using Procrastinate. Use this skill whenever the user is working with Procrastinate — setting it up, defining tasks, deferring jobs, running workers, configuring retries, periodic tasks, or deploying to Azure (Web App or Container App). Also triggers on:

• python-autotuner

  Python code optimizer and error fixer: analyzes a Python file or function, rewrites it for speed and quality one change at a time, validates with pytest, benchmarks with timeit, checks with ruff/ty, and measures complexity reduction. Also diagnoses broken Python code (SyntaxError, ImportError, TypeE

• remove-ai-writing

  Detect and surgically fix AI writing patterns in English, German, French, or Italian text. Use this skill whenever the user asks to 'remove AI writing', 'fix AI tells', 'make this sound less like ChatGPT/Claude', 'avoid AI patterns', 'make this more human', 'de-slop my text', 'nettoyer le texte IA',

• rich-data-tables

  Use whenever building a UI table, list view, or dashboard panel showing records with amounts, dates, or statuses (invoices, tickets, orders, tasks, leads, log entries, etc.) — in React/HTML/artifacts, TanStack Table column defs, or when writing/reviewing component code for one. Consult before render

• scientific-revision

  Use this skill whenever the user wants to verify, revise, or improve a scientific essay, academic paper, or any written document. It checks citation consistency, verifies bibliography entries via CrossRef and Google Scholar/Semantic Scholar, and detects AI-generated writing patterns (slop). Trigger

• spark-connect

  Guide for running PySpark code locally against a remote Databricks cluster via Spark Connect (databricks-connect). Use this skill when asked how to set up Databricks Connect, connect to a cluster from a local machine, run notebooks or scripts locally with Spark semantics, understand the get_spark_se

• sql-optimization

  Universal SQL performance optimization assistant for comprehensive query tuning, indexing strategies, and database performance analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle, Databricks). SQL style: sqlfmt lowercase, CTEs over subqueries, QUALIFY over row_number subqueries,

• tanstack-best-practices

  Comprehensive best practices for TanStack libraries in React applications — covering TanStack Query (React Query) data fetching, caching, and mutations; TanStack Router type-safe routing and search params; TanStack Query + Router integration patterns; TypeScript usage; and common pitfalls to avoid.

• testing-strategy

  Decide what kind of test to write and in what order for a backend feature: HTTP-level first, then Playwright e2e for the same flow. Use whenever adding or reviewing tests for an API endpoint or a user-facing flow, when the user asks "how should I test this", "add tests for X", "write an e2e test", o

Subagents (5)

• bms-ci-watch

  Waits for the CI of an already published PR to finish and reports the outcome compactly. Dispatched by dev-workflow step 10 (Watch CI); not for direct invocation.

• bms-design-review

  Captures desktop/mobile (light/dark) screenshots of a running UI, runs the design-review skill on them and reports findings compactly, so the images never enter the main thread's context. Dispatched by dev-workflow step 7 (Screenshots); not for direct invocation.

• bms-review-core

  Deep reviewer for the BMS code review: Correctness, Security and the verify pass. Dispatched by the bms-code-review skill; not for direct invocation.

• bms-review-light

  Light reviewer for the BMS code review: Agent-docs and Duplication roles. Dispatched by the bms-code-review skill; not for direct invocation.

• bms-review-standard

  Reviewer for the BMS code review: architecture gate, SQL/Database, Backend, Frontend and Performance roles. Dispatched by the bms-code-review skill; not for direct invocation.