Coding standards, frameworks, refactoring, and code review (16.7K skills)
Format C++ code in the BE and Cloud modules using the project's clang-format v16 rules. Use the provided scripts to fix formatting or check for violations without changing files, then review the resulting differences before committing.
Diagnoses and fixes Java style violations in the FE module using Checkstyle, a tool that checks coding rules. It interprets errors, applies the project's formatting and import restrictions, and reruns checks to verify fixes.
Review Doris code changes using project-specific checklists for data correctness, concurrency, memory safety, compatibility, performance, and tests. Trace related code paths and explain findings with concrete failure scenarios, using query plan trees when reviewing optimizer behavior.
Merge GitHub pull requests while preserving credit for the original contributors. Covers straightforward merges, conflict resolution, selective file inclusion, duplicate PR closure, and checks that confirm both attribution and working code after integration.
Build UI animations by first deciding whether motion serves a useful purpose. Produces code with suitable timing, transitions, interruption behavior, exit paths, reduced motion support, and hover effects adapted to the input device.
Review UI animation code for purposeful motion, responsive timing, correct origins, performance, and accessibility. Get a table of specific changes with reasons, followed by an approval or blocking decision ranked by impact.
Choose a frontend library for tasks such as notifications, charts, drag and drop, or shared application state. The skill checks existing dependencies and recommends one library from a curated list, with setup when requested.
Find, add, and combine shadcn/ui components to build forms, dashboards, and other interfaces. Use project settings and component documentation to guide styling, debugging, preset changes, and updates that preserve local modifications.
Add map search categories and synonyms with multilingual names, optional emoji, and rules for when suggestions appear. Coordinate related files for categories shown on the search screen, then sort language entries and run relevant tests.
Turn recurring tasks and specialized knowledge into reusable agent skills. Plan instructions and supporting files, generate a starting structure, refine existing skills, and validate and package the result as a distributable .skill file.
Run apps/mobile on an EAS cloud iOS simulator from a workspace without local Xcode. Connect it to the workspace’s development server, interact with screens, capture screenshots, and check how source changes appear in the app.
Generate Drizzle database migrations on a fresh Neon branch and review their production safety. Check table sizes, locking order, execution time, and data transfer needs, with load testing for changes affecting busy or large tables.
Turn GitHub issue reports into actionable work by searching for duplicates, attempting reproduction, and assessing user impact. Organize issues with existing labels, appropriate owners, and milestones, while clearly recording what was and was not verified.
Work through design or implementation choices one at a time, with concise context and clear alternatives. You can also review completed code change by change, recording decisions, approvals, and requested revisions in a final table.
Build Stripe payments, subscriptions, and invoicing using verified documentation and API parameter definitions. The skill guides product selection, sandbox testing, and webhook handling, where server notifications determine payment and subscription state.
Review tRPC API changes against released desktop, mobile, CLI, and SDK clients. Use release history and usage data to choose compatible changes, assess whether deprecated features can be removed, and plan recovery when deployed changes break clients.
Turn rough bug reports or requests into Linear issues with clear symptoms, reproduction steps, evidence, and routing details. Check for duplicates, distinguish observations from guesses, and present the proposed issue for approval before creating it.
Prepare an open source contribution to Superset, from forking the code and setting up local development to running checks and opening a pull request. Follow repository rules and include evidence that the change works.
Investigate production errors using Sentry stack traces, which show the code execution path, and events leading up to the failure. Identify likely causes, triggering conditions, affected users, and releases before changing code.
Coordinate multiple coding agents through Superset in separate workspaces. Split work into bounded tasks, track dependencies and progress, send follow-ups, and collect structured results covering changed files, verification checks, blockers, and the order for combining work.
Inspect the current QM web interface through its HTML and structured app state, with optional stylesheets and a rendered image. Use it to explain visible UI elements, help with interface questions, or check how a canvas appeared.
Take an agreed code change through a GitHub or GitLab pull request, automated checks, independent review, and fixes. Merge only after the latest commit passes all checks and has no unresolved review findings.
Inspect GitHub and GitLab repositories, issues, and proposed code changes, then prepare small fixes with tests and review summaries. Uses existing command-line authentication and requires approval before publishing changes or modifying repository records.
Prepare a pull request to contribute local qm changes back to the shared project. Builds a clean contribution branch and checks commit history, files, authorship, and review materials for private organizational details before submission.