Coding standards, frameworks, refactoring, and code review (16.7K skills)
Plan microservices by defining service responsibilities, communication methods, and data ownership. Use patterns for gradual migration, distributed transactions, and failure isolation to design systems made of independently responsible services.
Design and review PostgreSQL database schemas by choosing suitable column types, keys, constraints, and indexes. It also guides decisions about large-table partitioning, flexible JSONB data, and schema changes on a live database without downtime.
Design and implement Saga workflows across services, using compensating actions to undo completed work after failures. Define step deadlines, handle repeated messages safely, and monitor stalled order, booking, or other long-running processes.
Design query-ready data from streams of recorded events. The skill guides read models, databases shaped for queries, with practices for replaying events, resuming after failures, and tracking delays in dashboards or search indexes.
Build NFT contracts using ERC-721 and ERC-1155, standards for unique assets and multiple token types. Covers issuance limits, descriptive metadata, marketplace integration, and royalty information for art collections, collectibles, and game items.
Follow Conductor's development plans using test-driven development: write a failing test, implement the change, then improve the code. Manage phase verification, progress updates, and focused git commits as tasks move toward completion.
Build decentralized finance contracts from Solidity templates for staking and token swaps. Examples cover reward distribution, adding and removing pooled tokens, and swap calculations, with additional patterns for governance and flash loans.
Improve Bazel builds in large repositories containing multiple projects. Get guidance on build configuration, shared remote caches, remote execution, dependency management, custom build rules, and diagnosing build problems.
Plan and implement user login and access permissions using sessions, JWT tokens, or OAuth2. Apply role-based permissions, protect APIs, and review common weaknesses in password handling, cookies, token expiration, and server-side checks.
Design storage for event sourcing, an approach that records changes as events. Compare database options and plan event ordering, duplicate handling, concurrent writes, and scaling to build a consistent event persistence layer.
Organize feature development across multiple agents by dividing work, assigning one owner per file, and agreeing on interfaces before implementation. Provides strategies for shared files, branches, and integration so agents can build separate parts of the same system.
Design separate paths for updating and reading data using CQRS, an approach that splits these responsibilities. Organize read models, event handling, and validation to support complex queries and scale reads independently from writes.
Plan Claude Code agent teams by choosing team size, roles, and agent types with the tools each task needs. Preset compositions cover reviews, debugging, implementation, research, security audits, and migrations, alongside display settings for local or CI environments.
Create and maintain project documents in conductor/ covering the product, technology stack, development workflow, and work units. Extract context from existing code, check document consistency before implementation, and update documentation as the project evolves.
Design or refactor backend services with clear layers and dependency rules. Using Clean Architecture, Hexagonal Architecture, and Domain-Driven Design, it separates business logic from databases and frameworks and defines interfaces that support testing without external services.
Set up Python APIs with FastAPI using organized project templates. Build routes, asynchronous database operations, authentication, and error handling, with examples for sharing dependencies and testing endpoints through a separate test database.
Investigate complex bugs by assigning competing explanations to parallel agents. Compare code evidence, contradictory findings, and confidence levels to identify likely root causes, then check that a fix resolves the original failure and related edge cases.
Consult a field reference for slide JSON, the structured data behind each page. It explains where content and styling live, how edits are validated, and why a saved change may display differently or have no visible effect.
Find and edit specific fields in OpenMAIC classroom documents. This skill maps pages, content, and playback actions to their data locations, guides small changes, and checks saved results, with references for quizzes, interactive content, and projects.
Simplify code once its behavior is understood. Confirm the existing behavior through tests or reproduction, reduce unnecessary complexity in small, reviewable steps, and keep verification passing while preserving behavior and necessary safety checks.
Guide multi-step coding tasks with deepseek-v4-pro or deepseek-v4-flash in thinking mode. Verify files and symbols, write plans with confirmed file paths and line numbers, and use a verifier agent before changes spanning three or more files.
Review a pull request or code diff for bugs by reading callers, expected behavior, and nearby error handling. Receive findings tied to specific lines, ranked by severity, plus a summary of merge risks and needed tests.
Manage Codewhale skills from GitHub or local folders using native commands. List, install, update, activate, or remove skills, create a starter structure, and inspect community content before recommending trust for script and tool use.
Check a Rust project for compilation errors with cargo check, examine errors and warnings, and fix the issues found. An included command example also covers checking all project targets.