Maintainers often need to understand issue reports before they answer. This skill guides Claude, Codex, or Claude Code through diagnosis, classification, decision support, and reply drafting.

Cross-platform desktop teams often trade native feel for shared UI speed. This skill guides Claude, Codex, and Claude Code through architecture, WebView, IPC, memory, and launch-readiness checks.

Teams need repeatable agent skills that are documented, tested, and packaged. This skill guides creation, evaluation, governance, and release evidence across Claude, Codex, and Claude Code.

Frontend reviews often miss accessibility gaps, unsafe rendering paths, and incomplete UI states. This skill gives Claude, Codex, or Claude Code a focused review checklist for practical pre-merge feedback.

Skill authors need examples that expose incomplete marketplace metadata. This fixture provides a minimal broken skill for testing package validation and adapter handling.

Lint failures slow reviews and hide real defects. This skill runs lint checks, guides safe fixes, and verifies behavior with tests.

Cross-browser extension work often breaks across Chrome, Firefox, Edge, and localization files. This skill guides WXT extension development, builds, compatibility checks, and i18n updates.

Userscripts often fail because metadata, permissions, and runtime behavior do not match. This skill guides Claude, Codex, and Claude Code through portable Tampermonkey and ScriptCat development.

AI coding can turn weak ideas into lasting complexity before teams evaluate value and risk. Boyue applies evidence-based boundaries to scope, ownership, delivery, and retirement decisions.

Teams often lose task status, test discipline, and commit traceability during implementation. This skill guides Claude, Codex, and Claude Code through TDD tasks, verification gates, and checkpoint commits.

Python dependency workflows can be slow and inconsistent across local, CI, and Docker environments. This skill gives practical uv commands for projects, environments, locking, migration, and performance.

Complex TypeScript types can be hard to design, review, and maintain. This skill guides Claude, Codex, and Claude Code through safer advanced type patterns.

Temporal workflow tests can be slow, flaky, and hard to structure. This skill gives pytest patterns for unit, integration, replay, and local server testing.

Payment integrations require secure checkout, subscriptions, and webhook handling. This skill guides Stripe implementation patterns for billing flows, refunds, customer portals, and testing.

Shell scripts can hide portability, quoting, and reliability problems until production. This skill helps teams configure ShellCheck and apply practical linting workflows.

Async Rust can be difficult to design, debug, and scale safely. This skill gives practical Tokio patterns for tasks, channels, errors, shutdown, streams, and resource management.

React teams often mix local, global, and server state without clear boundaries. This skill helps apply Redux Toolkit, Zustand, Jotai, and React Query patterns.

RAG projects often fail when retrieval, chunking, and evaluation are unclear. This skill gives practical patterns for grounded LLM applications with citations.

Python projects often grow complex when responsibilities mix and abstractions appear too early. This skill guides focused refactors using KISS, SRP, layering, composition, and dependency injection.

Event-sourced systems need fast read models that stay consistent with event streams. This skill provides projection patterns for CQRS queries, dashboards, search, and reporting.